{"id":"https://openalex.org/W4416034355","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.843","title":"Teaching Language Models To Gather Information Proactively","display_name":"Teaching Language Models To Gather Information Proactively","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034355","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.843"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.843","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.843","pdf_url":"https://aclanthology.org/2025.findings-emnlp.843.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.843.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029827648","display_name":"Tenghao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tenghao Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101823158","display_name":"Sihao Chen","orcid":"https://orcid.org/0000-0001-8416-4261"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sihao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861481","display_name":"Muhao Chen","orcid":"https://orcid.org/0000-0003-0118-3147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000874697","display_name":"Jonathan May","orcid":"https://orcid.org/0000-0002-5284-477X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan May","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057330200","display_name":"Longqi Yang","orcid":"https://orcid.org/0000-0002-6615-8615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longqi Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046172814","display_name":"Mengting Wan","orcid":"https://orcid.org/0000-0002-5298-1221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengting Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5068446737","display_name":"Pei Zhou","orcid":"https://orcid.org/0000-0002-2046-6081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15588","last_page":"15599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.08550000190734863,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.08550000190734863,"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/T13629","display_name":"Text Readability and Simplification","score":0.061000000685453415,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.03869999945163727,"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/information-system","display_name":"Information system","score":0.36550000309944153},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3061000108718872},{"id":"https://openalex.org/keywords/information-model","display_name":"Information model","score":0.304500013589859},{"id":"https://openalex.org/keywords/information-technology","display_name":"Information technology","score":0.3012000024318695},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29829999804496765},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.2847000062465668}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652899980545044},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3091999888420105},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C21338462","wikidata":"https://www.wikidata.org/wiki/Q1662581","display_name":"Information model","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C121017731","wikidata":"https://www.wikidata.org/wiki/Q11661","display_name":"Information technology","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.29190000891685486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.27570000290870667},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.843","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.843","pdf_url":"https://aclanthology.org/2025.findings-emnlp.843.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.843","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.843","pdf_url":"https://aclanthology.org/2025.findings-emnlp.843.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1795802330","display_name":"CICI: UCSS: Enabling a Safe and Directive Multi-modal Foundation Model Ecosystem for Food Science Research","funder_award_id":"2531126","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4706632707","display_name":"Proto-OKN Theme 1: Knowledge Graph Construction for Resilient, Trustworthy, and Secure Software Supply Chains","funder_award_id":"2333736","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6584218474","display_name":null,"funder_award_id":"HR00112490370","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034355.pdf","grobid_xml":"https://content.openalex.org/works/W4416034355.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4,166],"increasingly":[5],"expected":[6],"to":[7,16,29,191],"function":[8],"as":[9,127],"collaborative":[10,193],"partners,":[11],"engaging":[12],"in":[13,25,71,184],"back-and-forth":[14],"dialogue":[15],"solve":[17],"complex,":[18],"ambiguous":[19],"problems.However,":[20],"current":[21],"LLMs":[22,67,186],"often":[23],"falter":[24],"real-world":[26,99],"settings,":[27],"defaulting":[28],"passive":[30,188],"responses":[31],"or":[32,39,131],"narrow":[33],"clarifications":[34],"when":[35],"faced":[36],"with":[37],"incomplete":[38],"underspecified":[40],"prompts-falling":[41],"short":[42],"of":[43,181],"proactively":[44],"gathering":[45],"the":[46,72,179],"missing":[47],"information":[48,64,103],"that":[49,95,120,139,156],"is":[50,113],"crucial":[51],"for":[52],"high-quality":[53],"solutions.In":[54],"this":[55,88,108],"work,":[56],"we":[57,90],"introduce":[58],"a":[59,92,114],"new":[60],"task":[61],"paradigm:":[62],"proactive":[63,182],"gathering,":[65],"where":[66],"must":[68],"identify":[69],"gaps":[70],"provided":[73],"context":[74],"and":[75,86,104,159,173],"strategically":[76],"elicit":[77,121],"implicit":[78,124],"user":[79,125],"knowledge":[80],"through":[81],"targeted":[82],"questions.To":[83],"systematically":[84],"study":[85],"train":[87],"capability,":[89],"design":[91],"scalable":[93],"framework":[94],"generates":[96],"partially":[97],"specified,":[98],"tasks,":[100],"masking":[101],"key":[102],"simulating":[105],"authentic":[106],"ambiguity.Within":[107],"setup,":[109],"our":[110,140,164],"core":[111],"innovation":[112],"reinforcement":[115],"finetuning":[116],"strategy":[117],"rewards":[118],"questions":[119,158],"genuinely":[122,192],"new,":[123],"information-such":[126],"hidden":[128],"domain":[129],"expertise":[130],"fine-grained":[132],"requirements-that":[133],"would":[134],"otherwise":[135],"remain":[136],"unspoken.Experiments":[137],"demonstrate":[138],"trained":[141],"Qwen-2.5-7Bmodel":[142],"significantly":[143],"outperforms":[144],"o3-mini":[145],"by":[146,163,168,171],"18%":[147],"on":[148],"automatic":[149],"evaluation":[150,154],"metrics.More":[151],"importantly,":[152],"human":[153,169],"reveals":[155],"clarification":[157,183],"final":[160],"outlines":[161],"generated":[162],"model":[165],"favored":[167],"annotators":[170],"42%":[172],"28%":[174],"respectively.Together,":[175],"these":[176],"results":[177],"highlight":[178],"value":[180],"elevating":[185],"from":[187],"text":[189],"generators":[190],"thought":[194],"partners.":[195]},"counts_by_year":[],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-11-08T00:00:00"}