{"id":1811,"date":"2023-05-05T08:36:47","date_gmt":"2023-05-05T08:36:47","guid":{"rendered":"https:\/\/sigir.org\/sigir2023\/?page_id=1811"},"modified":"2023-07-20T02:39:56","modified_gmt":"2023-07-20T02:39:56","slug":"keynotes","status":"publish","type":"page","link":"https:\/\/sigir.org\/sigir2023\/program\/keynotes\/","title":{"rendered":"Keynotes"},"content":{"rendered":"<div id='full_slider_1'  class='avia-fullwidth-slider main_color avia-shadow   avia-builder-el-0  el_before_av_section  avia-builder-el-first   container_wrap sidebar_right'  >\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522\">\n#top #wrap_all .avia-slideshow .av-slideshow-caption.av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522__0 .avia-caption-title{\nfont-size:45px;\n}\n#top .avia-slideshow .av-slideshow-caption.av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522__0 .avia-caption-content{\nfont-size:25px;\n}\n#top .avia-slideshow .av-slideshow-caption.av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522__0 .avia-caption-content p{\nfont-size:25px;\n}\n\n@media only screen and (max-width: 479px){ \n#top #wrap_all .avia-slideshow .av-slideshow-caption.av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522__0 .avia-caption-title{\nfont-size:30px;\n}\n}\n<\/style>\n<div  class='avia-slideshow av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522 av-control-default avia-slideshow-no scaling av_slideshow_full avia-slide-slider av-default-height-applied   avia-slideshow-1'  data-size='no scaling'  data-lightbox_size='large'  data-animation='slide'  data-conditional_play=''  data-ids='1803'  data-video_counter='0'  data-autoplay='false'  data-bg_slider='false'  data-slide_height=''  data-handle='av_slideshow_full'  data-interval='5'  data-class=''  data-extra_class=' '  data-el_id=''  data-css_id=''  data-scroll_down=''  data-control_layout='av-control-default'  data-custom_markup=''  data-perma_caption=''  data-autoplay_stopper=''  data-image_attachment=''  data-min_height='200px'  data-lazy_loading='disabled'  data-default-height='38.072916666667'  data-stretch=''  data-src=''  data-position='top left'  data-repeat='no-repeat'  data-attach='scroll'  data-img_scrset=''  data-av-desktop-hide=''  data-av-medium-hide=''  data-av-small-hide=''  data-av-mini-hide=''  data-id=''  data-custom_class=''  data-template_class=''  data-av_uid='av-l96qjn6c'  data-sc_version='1.0'  data-heading_tag=''  data-heading_class=''  data-min_width='526px'   itemprop=\"image\" itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/ImageObject\" ><ul class='avia-slideshow-inner ' style='padding-bottom: 38.072916666667%;'><li  class='avia-slideshow-slide av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522__0  av-single-slide slide-1 ' ><div data-rel='slideshow-1' class='avia-slide-wrap '   ><div class='av-slideshow-caption av-l96qjn6c-1741c8d27e9fc182ecd0f05e501bb522__0 caption_fullwidth caption_center'><div class=\"container caption_container\"><div class=\"slideshow_caption\"><div class=\"slideshow_inner_caption\"><div class=\"slideshow_align_caption\"><h2 class='avia-caption-title '  itemprop=\"name\" >Keynotes<\/h2><\/div><\/div><\/div><\/div><\/div><img decoding=\"async\" class=\"wp-image-1803 avia-img-lazy-loading-not-1803\"  src=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711.jpg\" width=\"1920\" height=\"731\" title='\u967d\u660e\u5c711' alt=''  itemprop=\"thumbnailUrl\"  style='min-height:200px; min-width:526px; ' srcset=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711.jpg 1920w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711-300x114.jpg 300w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711-1030x392.jpg 1030w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711-768x292.jpg 768w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711-1536x585.jpg 1536w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711-1500x571.jpg 1500w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711-705x268.jpg 705w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u967d\u660e\u5c711-845x321.jpg 845w\" sizes=\"(max-width: 1920px) 100vw, 1920px\" \/><div class='av-section-color-overlay' style='opacity: 0.3; background-color: #000000; '><\/div><\/div><\/li><\/ul><\/div><\/div>\n<div id='av_section_1'  class='avia-section av-5lyajc-3134daf831fbcef5bc794ceffe33e473 main_color avia-section-default avia-no-border-styling  avia-builder-el-1  el_after_av_slideshow_full  avia-builder-el-last  avia-bg-style-scroll container_wrap sidebar_right'  ><div class='container av-section-cont-open' ><div class='template-page content  av-content-small alpha units'><div class='post-entry post-entry-type-page post-entry-1811'><div class='entry-content-wrapper clearfix'>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-i8i34-db37dbf6681b9fa7bd58878e4937ab00\">\n.flex_column.av-i8i34-db37dbf6681b9fa7bd58878e4937ab00{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-i8i34-db37dbf6681b9fa7bd58878e4937ab00 av_one_full  avia-builder-el-2  el_before_av_one_fourth  avia-builder-el-first  first flex_column_div '   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-4vb7j4-b2f9224953362cd2d567ac30c421b063\">\n#top .av-special-heading.av-4vb7j4-b2f9224953362cd2d567ac30c421b063{\nmargin:0px 0px 0px 0px;\npadding-bottom:10px;\n}\nbody .av-special-heading.av-4vb7j4-b2f9224953362cd2d567ac30c421b063 .av-special-heading-tag .heading-char{\nfont-size:25px;\n}\n.av-special-heading.av-4vb7j4-b2f9224953362cd2d567ac30c421b063 .av-subheading{\nfont-size:15px;\n}\n<\/style>\n<div  class='av-special-heading av-4vb7j4-b2f9224953362cd2d567ac30c421b063 av-special-heading-h3 blockquote modern-quote  avia-builder-el-3  el_before_av_hr  avia-builder-el-first  av-linked-heading'><h3 class='av-special-heading-tag'  itemprop=\"headline\"  >Generative Information Retrieval<\/h3><div class=\"special-heading-border\"><div class=\"special-heading-inner-border\"><\/div><\/div><\/div><br \/>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-4oil7c-66a007c3864951ce006119e2f6214644\">\n#top .hr.av-4oil7c-66a007c3864951ce006119e2f6214644{\nmargin-top:0px;\nmargin-bottom:10px;\n}\n.hr.av-4oil7c-66a007c3864951ce006119e2f6214644 .hr-inner{\nwidth:100%;\nborder-color:#e1e1e1;\n}\n<\/style>\n<div  class='hr av-4oil7c-66a007c3864951ce006119e2f6214644 hr-custom  avia-builder-el-4  el_after_av_heading  avia-builder-el-last  hr-left hr-icon-no'><span class='hr-inner inner-border-av-border-fat'><span class=\"hr-inner-style\"><\/span><\/span><\/div><\/p><\/div><div class='flex_column_table av-lhe6ydev-1654bf5d9051bff6745b15a90c8ba7ea sc-av_one_fourth av-equal-height-column-flextable'>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe6ydev-1654bf5d9051bff6745b15a90c8ba7ea\">\n.flex_column.av-lhe6ydev-1654bf5d9051bff6745b15a90c8ba7ea{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-lhe6ydev-1654bf5d9051bff6745b15a90c8ba7ea av_one_fourth  avia-builder-el-5  el_after_av_one_full  el_before_av_three_fourth  first no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe6wjny-e164ccaec1060fc2855bb53178fa1553\">\n.avia-image-container.av-lhe6wjny-e164ccaec1060fc2855bb53178fa1553 .av-image-caption-overlay-center{\ncolor:#ffffff;\n}\n<\/style>\n<div  class='avia-image-container av-lhe6wjny-e164ccaec1060fc2855bb53178fa1553 av-styling- avia-align-center  avia-builder-el-6  avia-builder-el-no-sibling '  itemprop=\"image\" itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/ImageObject\" ><div class=\"avia-image-container-inner\"><div class=\"avia-image-overlay-wrap\"><img decoding=\"async\" class='wp-image-1836 avia-img-lazy-loading-not-1836 avia_image' src=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/4567.jpg\" alt='' title='4567'  height=\"350\" width=\"350\"  itemprop=\"thumbnailUrl\" srcset=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/4567.jpg 350w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/4567-300x300.jpg 300w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/4567-80x80.jpg 80w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/4567-36x36.jpg 36w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/4567-180x180.jpg 180w\" sizes=\"(max-width: 350px) 100vw, 350px\" \/><\/div><\/div><\/div><\/div><div class='flex_column av-tld39v-6e0d6b07dca4405e43ce31ba1a77508c av_three_fourth  avia-builder-el-7  el_after_av_one_fourth  el_before_av_one_full  no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><p><section  class='av_textblock_section av-lhe6zs5k-a99523da44d57db30476a9aec5cb3765'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-small-hide av-mini-hide avia_textblock text_justify'  itemprop=\"text\" ><p><strong>Marc Najork<\/strong><\/p>\n<p><strong>Distinguished Research Scientist, Google DeepMind<\/strong><\/p>\n<\/div><\/section><br \/>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe7iny4-61c22d35bd490daa441377e7f3176304\">\n#top .av_textblock_section.av-lhe7iny4-61c22d35bd490daa441377e7f3176304 .avia_textblock{\ntext-align:left;\n}\n<\/style>\n<section  class='av_textblock_section av-lhe7iny4-61c22d35bd490daa441377e7f3176304'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-desktop-hide av-medium-hide avia_textblock text_justify'  itemprop=\"text\" ><p style=\"margin-left: 40px;\"><strong>Marc Najork<\/strong><\/p>\n<p style=\"margin-left: 40px;\"><strong>Sr. Director, Google Research<\/strong><\/p>\n<\/div><\/section><br \/>\n<\/p><\/div><\/div><!--close column table wrapper. Autoclose: 1 -->\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-a0jsj-29b790c6784190c922b8c762aefb1221\">\n.flex_column.av-a0jsj-29b790c6784190c922b8c762aefb1221{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-a0jsj-29b790c6784190c922b8c762aefb1221 av_one_full  avia-builder-el-11  el_after_av_three_fourth  el_before_av_one_full  first flex_column_div column-top-margin'   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe77hc3-364024c23e9a46735457c9f58a6dca89\">\n#top .hr.hr-invisible.av-lhe77hc3-364024c23e9a46735457c9f58a6dca89{\nmargin-top:-10px;\nheight:1px;\n}\n<\/style>\n<div  class='hr av-lhe77hc3-364024c23e9a46735457c9f58a6dca89 hr-invisible  avia-builder-el-12  el_before_av_textblock  avia-builder-el-first  av-small-hide av-mini-hide'><span class='hr-inner '><span class=\"hr-inner-style\"><\/span><\/span><\/div><br \/>\n<section  class='av_textblock_section av-p5s2ab-a915d3aefa4550e5cedcf5cee10cd55f'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='avia_textblock text_justify'  itemprop=\"text\" ><p style=\"text-align: left;\"><strong>Abstract:<\/strong><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Historically, information retrieval systems have all followed the same paradigm: information seekers frame their needs in the form of a short query, the system selects a small set of relevant results from a corpus of available documents, rank-orders the results by decreasing relevance, possibly excerpts a responsive passage for each result, and returns a list of references and excerpts to the user. Retrieval systems typically did not attempt fusing information from multiple documents into an answer and displaying that answer directly. This was largely due to available technology: at the core of each retrieval system is an index that maps lexical tokens or semantic embeddings to document identifiers. Indices are designed for retrieving responsive documents; they do not support integrating these documents into a holistic answer. More recently, the coming-of-age of deep neural networks has dramatically improved the capabilities of large language models (LLMs). Trained on a large corpus of documents, these models not only memorize the vocabulary, morphology and syntax of human languages, but have shown to be able to memorize facts and relations [2]. Generative language models, when provided with a prompt, will extend the prompt with likely completions \u2013 an ability that can be used to extract answers to questions from the model. Two years ago, Metzler et al. argued that this ability of LLMs will allow us to rethink the search paradigm: to answer information needs directly rather that directing users to responsive primary sources [1]. Their vision was not without controversy; the following year Shaw and Bender argued that such a system is neither feasible nor desirable [3]. Nonetheless, the past year has seen the emergence of such systems, with offerings from established search engines and multiple new entrants to the industry. The keynote will summarize the short history of these generative information retrieval systems, and focus on the many open challenges in this emerging field: ensuring that answers are grounded, attributing answer passages to a primary source, providing nuanced answers to non-factoid-seeking questions, avoiding bias, and going beyond simple regurgitation of memorized facts. It will also touch on the changing nature of the content ecosystem. LLMs are starting to be used to generate web content. Should search engines treat such derived content equal to human-authored content? Is it possible to distinguish generated from original content? How should we view hybrid authorship where humans contribute ideas and LLMs shape these ideas into prose? And how will this parallel technical evolution of search engines and content ecosystems affect their respective business models?<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">&#8212;&#8212;&#8212;&#8211;<\/span><\/p>\n<p>Marc Najork is a Distinguished Research Scientist in Google DeepMind, working on new techniques to make it easier for people to obtain relevant and useful information when and where they need it. Marc is interested in using generative language models to answer questions directly, rather than referring users to relevant sources.\u00a0 Direct answers represent a major paradigm shift in Information Retrieval, affecting the user experience, the fundamental architecture of the retrieval system, and the economic foundation of commercial web search and the entire web content ecosystem.\u00a0 Prior to joining Google, Marc was a Principal Researcher at Microsoft Research, and a Research Scientist at Digital Equipment Corporation.\u00a0 He is an ACM Fellow, IEEE Fellow, and a SIGIR Academy member.<\/p>\n<\/div><\/section><\/p><\/div>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-orjdcg-b68d187a17e4f4c55db33aa3f56e2f1c\">\n.flex_column.av-orjdcg-b68d187a17e4f4c55db33aa3f56e2f1c{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-orjdcg-b68d187a17e4f4c55db33aa3f56e2f1c av_one_full  avia-builder-el-14  el_after_av_one_full  el_before_av_one_fourth  first flex_column_div column-top-margin'   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lezbnous-f0e7a48ff14a27f6854db34f544eefbf\">\n#top .av-special-heading.av-lezbnous-f0e7a48ff14a27f6854db34f544eefbf{\nmargin:0px 0px 0px 0px;\npadding-bottom:10px;\n}\nbody .av-special-heading.av-lezbnous-f0e7a48ff14a27f6854db34f544eefbf .av-special-heading-tag .heading-char{\nfont-size:25px;\n}\n.av-special-heading.av-lezbnous-f0e7a48ff14a27f6854db34f544eefbf .av-subheading{\nfont-size:15px;\n}\n<\/style>\n<div  class='av-special-heading av-lezbnous-f0e7a48ff14a27f6854db34f544eefbf av-special-heading-h3 blockquote modern-quote  avia-builder-el-15  el_before_av_hr  avia-builder-el-first  av-linked-heading'><h3 class='av-special-heading-tag'  itemprop=\"headline\"  >On the <span class='special_amp'>\u201c<\/span>Rough Use<span class='special_amp'>\u201d<\/span> of Machine Learning Techniques<\/h3><div class=\"special-heading-border\"><div class=\"special-heading-inner-border\"><\/div><\/div><\/div><br \/>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-mjpcu8-75fac574350fef4c708e813311e764b8\">\n#top .hr.av-mjpcu8-75fac574350fef4c708e813311e764b8{\nmargin-top:0px;\nmargin-bottom:10px;\n}\n.hr.av-mjpcu8-75fac574350fef4c708e813311e764b8 .hr-inner{\nwidth:100%;\nborder-color:#e1e1e1;\n}\n<\/style>\n<div  class='hr av-mjpcu8-75fac574350fef4c708e813311e764b8 hr-custom  avia-builder-el-16  el_after_av_heading  avia-builder-el-last  hr-left hr-icon-no'><span class='hr-inner inner-border-av-border-fat'><span class=\"hr-inner-style\"><\/span><\/span><\/div><\/p><\/div><div class='flex_column_table av-lhe75qg3-139c1dd6629b57bd305f97efa7fe7309 sc-av_one_fourth av-equal-height-column-flextable'>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe75qg3-139c1dd6629b57bd305f97efa7fe7309\">\n.flex_column.av-lhe75qg3-139c1dd6629b57bd305f97efa7fe7309{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-lhe75qg3-139c1dd6629b57bd305f97efa7fe7309 av_one_fourth  avia-builder-el-17  el_after_av_one_full  el_before_av_three_fourth  first no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe752w4-7fcc9ea0d1960ec009d7153c62daad06\">\n.avia-image-container.av-lhe752w4-7fcc9ea0d1960ec009d7153c62daad06 .av-image-caption-overlay-center{\ncolor:#ffffff;\n}\n<\/style>\n<div  class='avia-image-container av-lhe752w4-7fcc9ea0d1960ec009d7153c62daad06 av-styling- avia-align-center  avia-builder-el-18  avia-builder-el-no-sibling '  itemprop=\"image\" itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/ImageObject\" ><div class=\"avia-image-container-inner\"><div class=\"avia-image-overlay-wrap\"><img decoding=\"async\" class='wp-image-1835 avia-img-lazy-loading-not-1835 avia_image' src=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/46534.jpg\" alt='' title='46534'  height=\"350\" width=\"350\"  itemprop=\"thumbnailUrl\" srcset=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/46534.jpg 350w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/46534-300x300.jpg 300w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/46534-80x80.jpg 80w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/46534-36x36.jpg 36w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/46534-180x180.jpg 180w\" sizes=\"(max-width: 350px) 100vw, 350px\" \/><\/div><\/div><\/div><\/div><div class='flex_column av-nna1kj-2f902bf5f5f3613082b9889f4062bac6 av_three_fourth  avia-builder-el-19  el_after_av_one_fourth  el_before_av_one_full  no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><p><section  class='av_textblock_section av-lhe76je6-280d176be355625db443c00139d00ec7'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-small-hide av-mini-hide avia_textblock text_justify'  itemprop=\"text\" ><p><strong>Chih-Jen Lin<\/strong><\/p>\n<p><strong>Distinguished Professor,\u00a0<\/strong><\/p>\n<p><strong>Department of Computer Science, National Taiwan University\u00a0<\/strong><\/p>\n<p><strong>Department of Machine Learning, MBZUAI<\/strong><\/p>\n<\/div><\/section><br \/>\n<section  class='av_textblock_section av-lhe7npf0-cedb8a0d5524e95e04990dee2102300b'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-desktop-hide av-medium-hide avia_textblock text_justify'  itemprop=\"text\" ><p style=\"margin-left: 40px;\"><strong>Chih-Jen Lin<\/strong><\/p>\n<p style=\"margin-left: 40px;\"><strong>Distinguished Professor,\u00a0<\/strong><\/p>\n<p style=\"margin-left: 40px;\"><strong>Department of Computer Science National Taiwan University\u00a0<\/strong><\/p>\n<p style=\"margin-left: 40px;\"><strong>Department of Machine Learning MBZUAI<\/strong><\/p>\n<\/div><\/section><\/p><\/div><\/div><!--close column table wrapper. Autoclose: 1 -->\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lpgbqr-7b77bdb7039e4c20b455006019a3517b\">\n.flex_column.av-lpgbqr-7b77bdb7039e4c20b455006019a3517b{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-lpgbqr-7b77bdb7039e4c20b455006019a3517b av_one_full  avia-builder-el-22  el_after_av_three_fourth  el_before_av_one_full  first flex_column_div column-top-margin'   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-k7o0yb-c72cbc455ffd859da0f925f8a123e751\">\n#top .hr.hr-invisible.av-k7o0yb-c72cbc455ffd859da0f925f8a123e751{\nmargin-top:-10px;\nheight:1px;\n}\n<\/style>\n<div  class='hr av-k7o0yb-c72cbc455ffd859da0f925f8a123e751 hr-invisible  avia-builder-el-23  el_before_av_textblock  avia-builder-el-first  av-small-hide av-mini-hide'><span class='hr-inner '><span class=\"hr-inner-style\"><\/span><\/span><\/div><br \/>\n<section  class='av_textblock_section av-jnn05v-dcaba5b1184b458b29e95f5e6152b0eb'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='avia_textblock text_justify'  itemprop=\"text\" ><p style=\"text-align: left;\"><strong>Abstract:\u00a0<\/strong><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Machine learning is everywhere, but unfortunately, we are not experts of every method. Sometimes we \u201cinappropriately\u201d use machine learning techniques. Examples include reporting training instead of test performance and comparing two methods without suitable hyper-parameter searches. However, the reality is that there are more sophisticated or more subtle examples, which we broadly call the \u201crough use\u201d of machine learning techniques. The setting may be roughly fine, but seriously speaking, is inappropriate. We briefly discuss two intriguing examples.\u00a0<\/span><\/p>\n<ul style=\"text-align: left;\">\n<li><span style=\"font-weight: 400;\"> In the topic of graph representation learning, to evaluate the quality of the obtained representations, the multi-label problem of node classification is often considered. An unrealistic setting was used in almost the entire area by assuming that the number of labels of each test instance is known in the prediction stage. In practice, such ground truth information is rarely available. Details of this interesting story are in Lin et al. [1].\u00a0<\/span><\/li>\n<li><span style=\"font-weight: 400;\"> In training deep neural networks, the optimization process often relies on the validation performance for termination or selecting the best epoch. Thus in many public repositories, training, validation, and test sets are explicitly provided. Many think this setting is standard in applying any machine learning technique. However, except that the test set should be completely independent, users can do whatever the best setting on all the available labeled data (i.e., training and validation sets combined). Through real stories, we show that many did not clearly see the relation between training, validation, and test sets. The rough use of machine learning methods is common and sometimes unavoidable. The reason is that nothing is called a perfect use of a machine learning method. Further, it is not easy to assess the seriousness of the situation. We argue that having high-quality and easy-to-use software is an important way to improve the practical use of machine learning techniques.<\/span><\/li>\n<\/ul>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">&#8212;&#8212;&#8212;&#8211;<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Chih-Jen Lin is currently a distinguished professor at the Department of Computer Science, National Taiwan University, and an affiliated professor at the Department of Machine Learning, MBZUAI. He obtained his B.S. degree from National Taiwan University in 1993 and Ph.D. degree from University of Michigan in 1998. His major research areas include machine learning, data mining, and numerical optimization. He is best known for his work on support vector machines (SVM) for data classification. His software LIBSVM is one of the most widely used and cited SVM packages. For his research work he has received many awards, including best paper awards in some top computer science conferences. He is an IEEE fellow, a AAAI fellow, and an ACM fellow for his contribution to machine learning algorithms and software design. More information about him can be found at http:\/\/www.csie.ntu.edu.tw\/~cjlin.<\/span><\/p>\n<\/div><\/section><\/p><\/div>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-khfbeo-35d706531b6270916a5dec177e59d6c3\">\n.flex_column.av-khfbeo-35d706531b6270916a5dec177e59d6c3{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-khfbeo-35d706531b6270916a5dec177e59d6c3 av_one_full  avia-builder-el-25  el_after_av_one_full  el_before_av_one_fourth  first flex_column_div column-top-margin'   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lezbpmzd-201266dd89da91a58e167d2ef1b628e5\">\n#top .av-special-heading.av-lezbpmzd-201266dd89da91a58e167d2ef1b628e5{\nmargin:0px 0px 0px 0px;\npadding-bottom:10px;\n}\nbody .av-special-heading.av-lezbpmzd-201266dd89da91a58e167d2ef1b628e5 .av-special-heading-tag .heading-char{\nfont-size:25px;\n}\n.av-special-heading.av-lezbpmzd-201266dd89da91a58e167d2ef1b628e5 .av-subheading{\nfont-size:15px;\n}\n<\/style>\n<div  class='av-special-heading av-lezbpmzd-201266dd89da91a58e167d2ef1b628e5 av-special-heading-h3 blockquote modern-quote  avia-builder-el-26  el_before_av_hr  avia-builder-el-first  av-linked-heading'><h3 class='av-special-heading-tag'  itemprop=\"headline\"  >Bridging Quantitative and Qualitative Digital Experience Testing<\/h3><div class=\"special-heading-border\"><div class=\"special-heading-inner-border\"><\/div><\/div><\/div><br \/>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-j351nk-857866ffad8d3fc6723b1adff172f63b\">\n#top .hr.av-j351nk-857866ffad8d3fc6723b1adff172f63b{\nmargin-top:0px;\nmargin-bottom:10px;\n}\n.hr.av-j351nk-857866ffad8d3fc6723b1adff172f63b .hr-inner{\nwidth:100%;\nborder-color:#e1e1e1;\n}\n<\/style>\n<div  class='hr av-j351nk-857866ffad8d3fc6723b1adff172f63b hr-custom  avia-builder-el-27  el_after_av_heading  avia-builder-el-last  hr-left hr-icon-no'><span class='hr-inner inner-border-av-border-fat'><span class=\"hr-inner-style\"><\/span><\/span><\/div><\/p><\/div><div class='flex_column_table av-1sbplf-bf9614c1e83bb9d2cb6f7526ac46d5ec sc-av_one_fourth av-equal-height-column-flextable'>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-1sbplf-bf9614c1e83bb9d2cb6f7526ac46d5ec\">\n.flex_column.av-1sbplf-bf9614c1e83bb9d2cb6f7526ac46d5ec{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-1sbplf-bf9614c1e83bb9d2cb6f7526ac46d5ec av_one_fourth  avia-builder-el-28  el_after_av_one_full  el_before_av_three_fourth  first no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe79sl3-f72930beddc5dbeacd7c61cf339bd213\">\n.avia-image-container.av-lhe79sl3-f72930beddc5dbeacd7c61cf339bd213 .av-image-caption-overlay-center{\ncolor:#ffffff;\n}\n<\/style>\n<div  class='avia-image-container av-lhe79sl3-f72930beddc5dbeacd7c61cf339bd213 av-styling- avia-align-center  avia-builder-el-29  avia-builder-el-no-sibling '  itemprop=\"image\" itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/ImageObject\" ><div class=\"avia-image-container-inner\"><div class=\"avia-image-overlay-wrap\"><img decoding=\"async\" class='wp-image-1837 avia-img-lazy-loading-not-1837 avia_image' src=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/9958.jpg\" alt='' title='9958'  height=\"350\" width=\"350\"  itemprop=\"thumbnailUrl\" srcset=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/9958.jpg 350w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/9958-300x300.jpg 300w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/9958-80x80.jpg 80w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/9958-36x36.jpg 36w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/9958-180x180.jpg 180w\" sizes=\"(max-width: 350px) 100vw, 350px\" \/><\/div><\/div><\/div><\/div><div class='flex_column av-g0pzyb-7fe01f95760683aab776b55000d0d152 av_three_fourth  avia-builder-el-30  el_after_av_one_fourth  el_before_av_one_full  no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><p><section  class='av_textblock_section av-lhe79fyy-de8c9784f6df35f29cecbca8ecc0ff3a'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-small-hide av-mini-hide avia_textblock text_justify'  itemprop=\"text\" ><p><strong>Ranjitha Kumar\u00a0<\/strong><\/p>\n<p><strong>Associate Professor, University of Illinois at Urbana-Champaign<\/strong><\/p>\n<p><strong>Chief Research Scientist, UserTesting, Inc.<\/strong><\/p>\n<\/div><\/section><br \/>\n<section  class='av_textblock_section av-lhe7o979-3ce34b98415e75e3ec34f4a130cbedea'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-desktop-hide av-medium-hide avia_textblock text_justify'  itemprop=\"text\" ><p style=\"margin-left: 40px;\"><strong>Ranjitha Kumar\u00a0<\/strong><\/p>\n<p style=\"margin-left: 40px;\"><strong>Associate Professor, University of Illinois at Urbana-Champaign<\/strong><\/p>\n<p style=\"margin-left: 40px;\"><strong>Chief Research Scientist, UserTesting, Inc.<\/strong><\/p>\n<\/div><\/section><\/p><\/div><\/div><!--close column table wrapper. Autoclose: 1 -->\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-eken0z-cbc69f2c507499408c992ee4485e0ec6\">\n.flex_column.av-eken0z-cbc69f2c507499408c992ee4485e0ec6{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-eken0z-cbc69f2c507499408c992ee4485e0ec6 av_one_full  avia-builder-el-33  el_after_av_three_fourth  el_before_av_one_full  first flex_column_div column-top-margin'   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-16byib-5233daf7bad078861c5df82c161a0c31\">\n#top .hr.hr-invisible.av-16byib-5233daf7bad078861c5df82c161a0c31{\nmargin-top:-10px;\nheight:1px;\n}\n<\/style>\n<div  class='hr av-16byib-5233daf7bad078861c5df82c161a0c31 hr-invisible  avia-builder-el-34  el_before_av_textblock  avia-builder-el-first  av-small-hide av-mini-hide'><span class='hr-inner '><span class=\"hr-inner-style\"><\/span><\/span><\/div><br \/>\n<section  class='av_textblock_section av-a6pk0z-138ea76c9f8bfec4091f89fd1cdea104'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='avia_textblock text_justify'  itemprop=\"text\" ><p style=\"text-align: left;\"><strong>Abstract:<\/strong><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Digital user experiences are a mainstay of modern communication and commerce; multi-billion dollar industries have arisen around optimizing digital design. Usage analytics and A\/B testing solutions allow growth hackers to quantitatively compute conversion over key user journeys, while user experience (UX) testing platforms enable UX researchers to qualitatively analyze usability and brand perception. Although these workflows are in pursuit of the same objective \u2014 producing better UX \u2014 the gulf between quantitative and qualitative testing is wide: they involve different stakeholders, and rely on disparate methodologies, budget, data streams, and software tools. This gap belies the opportunity to create one platform that optimizes digital experiences holistically: using quantitative methods to uncover what and how much and qualitative analysis to understand why. Such a platform could monitor conversion funnels, identify anomalous behaviors, intercept live users exhibiting those behaviors, and solicit explicit feedback in situ. This feedback could take many forms: survey responses, screen recordings of participants performing tasks, think-aloud audio, and more. By combining data from multiple users and correlating across feedback types, the platform could surface not just insights that a particular conversion funnel had been affected, but hypotheses about what had caused the change in user behavior. The platform could then rank these insights by how often the observed behavior occurred in the wild, using large-scale analytics to contextualize the results from small-scale UX tests. To this end, a decade of research has focused on interaction mining: a set of techniques for capturing interaction and design data from digital artifacts, and aggregating these multi-modal data streams into structured representations bridging quantitative and qualitative experience testing [1\u20135]. During user sessions, interaction mining systems capture user interactions (e.g., clicks, scrolls, text input), screen captures, and render-time data structures (e.g., website DOMs, native app view hierarchies). Once captured, these data streams are aligned and combined into user traces, sequences of user interactions contextualized by the design data of their UI targets. The structure of these traces affords new workflows for composing quantitative and qualitative methods, building toward a unified platform for optimizing digital experiences.<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">&#8212;&#8212;&#8212;&#8211;<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Ranjitha Kumar is an Associate Professor of Computer Science at the University of Illinois at Urbana-Champaign and the Chief Scientist at UserTesting, Inc. Her research has won best paper awards and nominations at premier conferences in human-computer interaction, and is supported by grants from the NSF, Google, Amazon, and Adobe. She received her BS and PhD from the Computer Science Department at Stanford University, and was previously a co-founder and the Chief Scientist of Apropose, Inc., a data-driven design startup.<\/span><\/p>\n<\/div><\/section><\/p><\/div>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-1oalog-8add698cc599d4af497a6ad019f4eee4\">\n.flex_column.av-1oalog-8add698cc599d4af497a6ad019f4eee4{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-1oalog-8add698cc599d4af497a6ad019f4eee4 av_one_full  avia-builder-el-36  el_after_av_one_full  el_before_av_one_fourth  first flex_column_div column-top-margin'   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lezbqb9e-18339849c3e5dfa18f94038b098190cc\">\n#top .av-special-heading.av-lezbqb9e-18339849c3e5dfa18f94038b098190cc{\nmargin:0px 0px 0px 0px;\npadding-bottom:10px;\n}\nbody .av-special-heading.av-lezbqb9e-18339849c3e5dfa18f94038b098190cc .av-special-heading-tag .heading-char{\nfont-size:25px;\n}\n.av-special-heading.av-lezbqb9e-18339849c3e5dfa18f94038b098190cc .av-subheading{\nfont-size:15px;\n}\n<\/style>\n<div  class='av-special-heading av-lezbqb9e-18339849c3e5dfa18f94038b098190cc av-special-heading-h3 blockquote modern-quote  avia-builder-el-37  el_before_av_hr  avia-builder-el-first  av-linked-heading'><h3 class='av-special-heading-tag'  itemprop=\"headline\"  >Tasks, Copilots, and the Future of Search<\/h3><div class=\"special-heading-border\"><div class=\"special-heading-inner-border\"><\/div><\/div><\/div><br \/>\n\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-fvro1s-262c5b5ca5cd06fc206c136a6fe1bba3\">\n#top .hr.av-fvro1s-262c5b5ca5cd06fc206c136a6fe1bba3{\nmargin-top:0px;\nmargin-bottom:10px;\n}\n.hr.av-fvro1s-262c5b5ca5cd06fc206c136a6fe1bba3 .hr-inner{\nwidth:100%;\nborder-color:#e1e1e1;\n}\n<\/style>\n<div  class='hr av-fvro1s-262c5b5ca5cd06fc206c136a6fe1bba3 hr-custom  avia-builder-el-38  el_after_av_heading  avia-builder-el-last  hr-left hr-icon-no'><span class='hr-inner inner-border-av-border-fat'><span class=\"hr-inner-style\"><\/span><\/span><\/div><\/p><\/div><div class='flex_column_table av-8msiw3-bb9b33195066f4b0a3f2d7565604cb7f sc-av_one_fourth av-equal-height-column-flextable'>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-8msiw3-bb9b33195066f4b0a3f2d7565604cb7f\">\n.flex_column.av-8msiw3-bb9b33195066f4b0a3f2d7565604cb7f{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-8msiw3-bb9b33195066f4b0a3f2d7565604cb7f av_one_fourth  avia-builder-el-39  el_after_av_one_full  el_before_av_three_fourth  first no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-lhe7b9bc-f37e388b01c42a96137bfd03a3c3c270\">\n.avia-image-container.av-lhe7b9bc-f37e388b01c42a96137bfd03a3c3c270 .av-image-caption-overlay-center{\ncolor:#ffffff;\n}\n<\/style>\n<div  class='avia-image-container av-lhe7b9bc-f37e388b01c42a96137bfd03a3c3c270 av-styling- avia-align-center  avia-builder-el-40  avia-builder-el-no-sibling '  itemprop=\"image\" itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/ImageObject\" ><div class=\"avia-image-container-inner\"><div class=\"avia-image-overlay-wrap\"><img decoding=\"async\" class='wp-image-1838 avia-img-lazy-loading-not-1838 avia_image' src=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u672a\u547d\u540d-1.jpg\" alt='' title='\u672a\u547d\u540d-1'  height=\"350\" width=\"350\"  itemprop=\"thumbnailUrl\" srcset=\"https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u672a\u547d\u540d-1.jpg 350w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u672a\u547d\u540d-1-300x300.jpg 300w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u672a\u547d\u540d-1-80x80.jpg 80w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u672a\u547d\u540d-1-36x36.jpg 36w, https:\/\/sigir.org\/sigir2023\/wp-content\/uploads\/2023\/05\/\u672a\u547d\u540d-1-180x180.jpg 180w\" sizes=\"(max-width: 350px) 100vw, 350px\" \/><\/div><\/div><\/div><\/div><div class='flex_column av-703m2r-51f766e70657452c79857d8898dc8c9f av_three_fourth  avia-builder-el-41  el_after_av_one_fourth  el_before_av_one_full  no_margin flex_column_table_cell av-equal-height-column av-align-middle column-top-margin'   ><p><section  class='av_textblock_section av-lhe7aw3v-4f12fc654d726698d615368c6d5d90db'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-small-hide av-mini-hide avia_textblock text_justify'  itemprop=\"text\" ><p><strong>Ryen W. White<\/strong><\/p>\n<p><strong>General Manager and Deputy Lab Director, Microsoft Research<\/strong><\/p>\n<\/div><\/section><br \/>\n<section  class='av_textblock_section av-lhe7pa4v-fd971d144c09a330c7d61b6573ba7571'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='av-desktop-hide av-medium-hide avia_textblock text_justify'  itemprop=\"text\" ><p style=\"margin-left: 40px;\"><strong>Ryen W. White<\/strong><\/p>\n<p style=\"margin-left: 40px;\"><strong>General Manager and Deputy Lab Director, Microsoft Research<\/strong><\/p>\n<\/div><\/section><\/p><\/div><\/div><!--close column table wrapper. Autoclose: 1 -->\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-5f4uwz-4dd13c078142e0e6bc8eefaf505e098d\">\n.flex_column.av-5f4uwz-4dd13c078142e0e6bc8eefaf505e098d{\npadding:0 40px 0 40px;\n}\n<\/style>\n<div class='flex_column av-5f4uwz-4dd13c078142e0e6bc8eefaf505e098d av_one_full  avia-builder-el-44  el_after_av_three_fourth  avia-builder-el-last  first flex_column_div column-top-margin'   ><p>\n<style type=\"text\/css\" data-created_by=\"avia_inline_auto\" id=\"style-css-av-3srirn-a1c2f4a64b372675fbf7ad4f124a40f9\">\n#top .hr.hr-invisible.av-3srirn-a1c2f4a64b372675fbf7ad4f124a40f9{\nmargin-top:-10px;\nheight:1px;\n}\n<\/style>\n<div  class='hr av-3srirn-a1c2f4a64b372675fbf7ad4f124a40f9 hr-invisible  avia-builder-el-45  el_before_av_textblock  avia-builder-el-first  av-small-hide av-mini-hide'><span class='hr-inner '><span class=\"hr-inner-style\"><\/span><\/span><\/div><br \/>\n<section  class='av_textblock_section av-25iw2r-8ae6eba3dbeb9d02b6becc63ad604f89'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/CreativeWork\" ><div class='avia_textblock text_justify'  itemprop=\"text\" ><p style=\"text-align: left;\"><strong>Abstract:<\/strong><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Tasks are central to information retrieval (IR) and drive interactions with search systems. Understanding and modeling tasks helps these systems better support user needs. This keynote focuses on search tasks, the emergence of generative artificial intelligence (AI), and the implications of recent work at their intersection for the future of search. Recent estimates suggest that half of Web search queries go unanswered, many of them connected to complex search tasks that are ill-defined or multi-step and span several queries. AI copilots, e.g., ChatGPT and Bing Chat, are emerging to address complex search tasks and many other challenges. These copilots are built on large foundation models such as GPT-4 and are being extended with skills and plugins. Copilots can broaden the surface of tasks achievable via search, moving toward creation not just finding (e.g., interview preparation, email composition), and can make searchers more efficient and more successful.\u00a0\u00a0<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Users currently engage with AI copilots via natural language queries and dialog and the copilots generate answers with source attribution. However, in delegating responsibility for answer generation, searchers also lose some control over aspects of the search process, such as directly manipulating queries and examining lists of search results. The efficiency gains from auto-generating a single, synthesized answer may also reduce opportunities for user learning and serendipity. A wholesale move to copilots for all search tasks is neither practical nor necessary: model inference is expensive, conversational interfaces are unfamiliar to many users in a search context, and traditional search already excels for many types of task. Instead, experiences that unite search and chat are becoming more common, enabling users to adjust the modality and other aspects (e.g., answer tone) based on the task.\u00a0\u00a0<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">The rise of AI copilots creates many opportunities for IR, including aligning generated answers with user intent, tasks, and applications via human feedback, using context and data to tailor responses to people and situations (e.g., grounding, personalization), new search experiences (e.g., unifying search and chat), reliability and safety (e.g., accuracy, bias), understanding impacts on user learning and agency, and evaluation (e.g., model-based feedback, searcher simulations, repeatability). Research in these and related areas will enable search systems to more effectively utilize new copilot technologies together with traditional search to help searchers better tackle a wider variety of tasks.<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">&#8212;&#8212;&#8212;&#8211;<\/span><\/p>\n<p style=\"text-align: left;\"><span style=\"font-weight: 400;\">Ryen White is General Manager and Deputy Lab Director of Microsoft Research in Redmond. His research takes a user- and task-centric view on AI, focused on search and assistance. Ryen led applied science for the Microsoft Cortana digital assistant, and he was chief scientist at Microsoft Health, establishing a science culture and infusing AI in both products. Technology derived from his and his team\u2019s research has shipped and significantly improved key business metrics in many Microsoft products, including Bing (e.g., using search context to improve result relevance), Windows, Office, and Azure. Ryen is a Fellow of the ACM and of the British Computer Society. He has published over 300 articles on search and related areas, including significant work on mining and modeling search activity at scale. Ryen was named &#8220;Center of the SIGIR Universe&#8221; (most central author in the co-authorship graph) in the 40 years of ACM SIGIR. He has received over 20 awards for his technical contributions, including three SIGIR best paper awards and a SIGIR test of time award. Ryen has received the Karen Sp\u00e4rck Jones Award (2015) and the Tony Kent Strix Award (2022) for outstanding contributions to information retrieval. He is editor-in-chief of ACM Transactions on the Web and Vice Chair of SIGIR.<\/span><\/p>\n<\/div><\/section><\/p><\/div><\/div><\/div><\/div><!-- close content main div --><\/div><\/div><div id='after_section_1'  class='main_color av_default_container_wrap container_wrap sidebar_right'  ><div class='container av-section-cont-open' ><div class='template-page content  av-content-small alpha units'><div class='post-entry post-entry-type-page post-entry-1811'><div class='entry-content-wrapper clearfix'>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":4,"featured_media":0,"parent":306,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-1811","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/pages\/1811","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/comments?post=1811"}],"version-history":[{"count":14,"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/pages\/1811\/revisions"}],"predecessor-version":[{"id":2346,"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/pages\/1811\/revisions\/2346"}],"up":[{"embeddable":true,"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/pages\/306"}],"wp:attachment":[{"href":"https:\/\/sigir.org\/sigir2023\/wp-json\/wp\/v2\/media?parent=1811"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}