{"id":"https://openalex.org/W4400524512","doi":"https://doi.org/10.1145/3626772.3657689","title":"Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback","display_name":"Unsupervised Large Language Model Alignment for Information Retrieval via Contrastive Feedback","publication_year":2024,"publication_date":"2024-07-10","ids":{"openalex":"https://openalex.org/W4400524512","doi":"https://doi.org/10.1145/3626772.3657689"},"language":"en","primary_location":{"id":"doi:10.1145/3626772.3657689","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657689","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3626772.3657689","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101779837","display_name":"Qian Dong","orcid":"https://orcid.org/0000-0002-6858-5303"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qian Dong","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101677601","display_name":"Yiding Liu","orcid":"https://orcid.org/0000-0001-6857-261X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiding Liu","raw_affiliation_strings":["Baidu Inc., Beijing, Singapore","DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, Singapore","institution_ids":[]},{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089655391","display_name":"Qingyao Ai","orcid":"https://orcid.org/0000-0002-5030-709X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyao Ai","raw_affiliation_strings":["Quan Cheng Laboratory & DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Quan Cheng Laboratory & DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002597610","display_name":"Zhijing Wu","orcid":"https://orcid.org/0000-0003-2473-3746"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijing Wu","raw_affiliation_strings":["School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101638981","display_name":"Haitao Li","orcid":"https://orcid.org/0009-0006-8766-8610"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Li","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668121","display_name":"Yiqun Liu","orcid":"https://orcid.org/0000-0002-0140-4512"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiqun Liu","raw_affiliation_strings":["Baidu Inc., Beijing, Singapore","DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, Singapore","institution_ids":[]},{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050255638","display_name":"Shuaiqiang Wang","orcid":"https://orcid.org/0000-0002-9212-1947"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuaiqiang Wang","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101771060","display_name":"Dawei Yin","orcid":"https://orcid.org/0000-0002-0684-6205"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Yin","raw_affiliation_strings":["Baidu Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Baidu Inc., Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760812","display_name":"Shaoping Ma","orcid":"https://orcid.org/0000-0002-8762-8268"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoping Ma","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101779837"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.6765,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.95054213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"48","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8263869285583496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5936888456344604},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5922753810882568},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4404805302619934},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40406256914138794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263869285583496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5936888456344604},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5922753810882568},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4404805302619934},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40406256914138794}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3626772.3657689","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657689","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3626772.3657689","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3626772.3657689","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W912777836","https://openalex.org/W2155912844","https://openalex.org/W2912924812","https://openalex.org/W2963929190","https://openalex.org/W2970795039","https://openalex.org/W2981852735","https://openalex.org/W3156638011","https://openalex.org/W4212963993","https://openalex.org/W4226278401","https://openalex.org/W4252076394","https://openalex.org/W4284691245","https://openalex.org/W4287674181","https://openalex.org/W4288089799","https://openalex.org/W4327644554","https://openalex.org/W4388955716","https://openalex.org/W6609581451","https://openalex.org/W6636625392","https://openalex.org/W6675775337","https://openalex.org/W6782465632"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"capabilities":[7],"across":[8],"various":[9],"research":[10],"domains,":[11],"including":[12],"the":[13,20,33,43,123],"field":[14],"of":[15,35,45,125],"Information":[16],"Retrieval":[17],"(IR).":[18],"However,":[19],"responses":[21],"generated":[22],"by":[23],"off-the-shelf":[24],"LLMs":[25,46,85],"tend":[26],"to":[27,86,114,121],"be":[28],"generic,":[29],"i.e.,":[30],"cannot":[31],"capture":[32],"distinctiveness":[34],"each":[36],"document":[37,103],"with":[38],"similar":[39,57,102],"content.":[40],"This":[41],"limits":[42],"performance":[44],"in":[47,63],"IR":[48,65],"because":[49],"finding":[50],"and":[51,90,105],"distinguishing":[52],"relevant":[53],"documents":[54,58],"from":[55,80],"substantial":[56],"is":[59],"a":[60,107],"typical":[61],"problem":[62],"many":[64],"tasks.":[66],"To":[67],"address":[68],"this":[69],"issue,":[70],"we":[71],"propose":[72],"an":[73],"unsupervised":[74,96],"alignment":[75],"method,":[76],"namely":[77],"Reinforcement":[78],"Learning":[79],"Contrastive":[81],"Feedback":[82],"(RLCF),":[83],"empowering":[84],"generate":[87],"both":[88],"high-quality":[89],"context-specific":[91],"responses.":[92],"Our":[93],"approach":[94],"constructs":[95],"contrastive":[97],"feedback":[98],"signals":[99],"based":[100],"on":[101],"groups,":[104],"adopts":[106],"reward":[108],"function,":[109],"named":[110],"group-wise":[111],"reciprocal":[112],"rank,":[113],"optimize":[115],"LLMs.":[116],"We":[117],"conduct":[118],"extensive":[119],"experiments":[120],"evaluate":[122],"effectiveness":[124],"RLCF.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}