{"id":"https://openalex.org/W4412673508","doi":"https://doi.org/10.1145/3731120.3744613","title":"Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking","display_name":"Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4412673508","doi":"https://doi.org/10.1145/3731120.3744613"},"language":"en","primary_location":{"id":"doi:10.1145/3731120.3744613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744613?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744613?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015911813","display_name":"Chris Samarinas","orcid":"https://orcid.org/0000-0002-1941-3310"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chris Samarinas","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457713","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Zamani","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015911813"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08850667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"430","last_page":"435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980000257492065,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9950000047683716,"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":0.7813019752502441},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7116726040840149},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5807359218597412},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44816821813583374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3863928020000458},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.34044086933135986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813019752502441},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7116726040840149},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5807359218597412},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44816821813583374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3863928020000458},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.34044086933135986},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3731120.3744613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744613?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.03947","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.03947","pdf_url":"https://arxiv.org/pdf/2504.03947","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3731120.3744613","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744613","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744613?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1462908608","display_name":"CAREER: Enriching Conversational Information Retrieval via Mixed-Initiative Interactions","funder_award_id":"2143434","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6128554767","display_name":null,"funder_award_id":"N000142212688","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6509441542","display_name":null,"funder_award_id":"N000142212688","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412673508.pdf","grobid_xml":"https://content.openalex.org/works/W4412673508.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1973435495","https://openalex.org/W2115584760","https://openalex.org/W2970641574","https://openalex.org/W3147292006","https://openalex.org/W3154670582","https://openalex.org/W3155375847","https://openalex.org/W3168659546","https://openalex.org/W4385570594","https://openalex.org/W4400531953"],"related_works":["https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2915512527","https://openalex.org/W51364034","https://openalex.org/W2793336762","https://openalex.org/W2091548507","https://openalex.org/W2368816706","https://openalex.org/W3159414774","https://openalex.org/W4385728102","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,42,59,70,138],"novel":[3],"approach":[4],"for":[5,10,143],"training":[6,49],"small":[7],"language":[8,34,74,129],"models":[9,100],"reasoning-intensive":[11],"document":[12,56],"ranking":[13,57],"that":[14,76,101,112],"combines":[15],"knowledge":[16],"distillation":[17],"with":[18,51,127],"reinforcement":[19,60],"learning":[20,61],"optimization.":[21],"While":[22],"existing":[23],"methods":[24],"often":[25],"rely":[26],"on":[27,80,88],"expensive":[28],"human":[29],"annotations":[30],"or":[31],"large":[32],"black-box":[33],"models,":[35],"our":[36,135],"methodology":[37],"leverages":[38],"web":[39],"data":[40],"and":[41,63,140],"teacher":[43],"LLM":[44],"to":[45],"automatically":[46],"generate":[47],"high-quality":[48],"examples":[50],"relevance":[52,121],"explanations.":[53],"By":[54],"framing":[55],"as":[58],"problem":[62],"incentivizing":[64],"explicit":[65],"reasoning":[66,126],"capabilities,":[67],"we":[68,110],"train":[69],"compact":[71],"3B":[72],"parameter":[73],"model":[75,85],"achieves":[77],"state-of-the-art":[78],"performance":[79],"the":[81,89],"BRIGHT":[82],"benchmark.":[83],"Our":[84],"ranks":[86],"third":[87],"leaderboard":[90],"while":[91],"using":[92],"substantially":[93],"fewer":[94],"parameters":[95],"than":[96,118],"other":[97],"approaches,":[98],"outperforming":[99],"are":[102],"over":[103],"20":[104],"times":[105],"larger.":[106],"Through":[107],"extensive":[108],"experiments,":[109],"demonstrate":[111],"generating":[113],"explanations":[114],"during":[115],"inference,":[116],"rather":[117],"directly":[119],"predicting":[120],"scores,":[122],"enables":[123],"more":[124],"effective":[125],"smaller":[128],"models.":[130],"The":[131],"self-supervised":[132],"nature":[133],"of":[134],"method":[136],"offers":[137],"scalable":[139],"interpretable":[141],"solution":[142],"modern":[144],"information":[145],"retrieval":[146],"systems.":[147]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}