{"id":"https://openalex.org/W7138940841","doi":"https://doi.org/10.1609/aaai.v40i39.40629","title":"Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following","display_name":"Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138940841","doi":"https://doi.org/10.1609/aaai.v40i39.40629"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i39.40629","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40629","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40629/44590","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40629/44590","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130013535","display_name":"Chenyang Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenyang Wang","raw_affiliation_strings":["Faculty of Computing, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130149303","display_name":"Liang Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I103261469","display_name":"Guilford Technical Community College","ror":"https://ror.org/03bq13516","country_code":"US","type":"education","lineage":["https://openalex.org/I103261469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Wen","raw_affiliation_strings":["Qiyuan Tech, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qiyuan Tech, China","institution_ids":["https://openalex.org/I103261469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130085141","display_name":"Shousheng Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I103261469","display_name":"Guilford Technical Community College","ror":"https://ror.org/03bq13516","country_code":"US","type":"education","lineage":["https://openalex.org/I103261469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shousheng Jia","raw_affiliation_strings":["Qiyuan Tech, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qiyuan Tech, China","institution_ids":["https://openalex.org/I103261469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047480930","display_name":"X. Brian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I103261469","display_name":"Guilford Technical Community College","ror":"https://ror.org/03bq13516","country_code":"US","type":"education","lineage":["https://openalex.org/I103261469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangzheng Zhang","raw_affiliation_strings":["Qiyuan Tech, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qiyuan Tech, China","institution_ids":["https://openalex.org/I103261469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129844060","display_name":"Liang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101542","display_name":"Benchmark Research (United States)","ror":"https://ror.org/0185yec04","country_code":"US","type":"company","lineage":["https://openalex.org/I4210101542"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Xu","raw_affiliation_strings":["Chinese Language Understanding Evaluation (CLUE) benchmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Language Understanding Evaluation (CLUE) benchmark","institution_ids":["https://openalex.org/I4210101542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5130013535"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47457627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"39","first_page":"33422","last_page":"33430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.14020000398159027,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10533","display_name":"Teaching and Learning Programming","score":0.14020000398159027,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.0754999965429306,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.06599999964237213,"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/initialization","display_name":"Initialization","score":0.5742999911308289},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5299000144004822},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5127000212669373},{"id":"https://openalex.org/keywords/adaptive-reasoning","display_name":"Adaptive reasoning","score":0.4666999876499176},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.46630001068115234},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.4341000020503998},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.34380000829696655},{"id":"https://openalex.org/keywords/logical-reasoning","display_name":"Logical reasoning","score":0.3222000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128000259399414},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5299000144004822},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49000000953674316},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.4666999876499176},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3206999897956848},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C2985612853","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogical reasoning","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C187179951","wikidata":"https://www.wikidata.org/wiki/Q7784616","display_name":"Thinking processes","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i39.40629","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40629","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40629/44590","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i39.40629","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40629","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40629/44590","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138940841.pdf","grobid_xml":"https://content.openalex.org/works/W7138940841.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"advancements":[1],"in":[2,13,24,97],"the":[3,42,46,114,129,163],"reasoning":[4,40,67,137,168,173],"abilities":[5,174],"of":[6,128],"LLMs":[7],"have":[8],"significantly":[9],"enhanced":[10],"their":[11,22],"performance":[12,188],"solving":[14],"mathematical":[15],"problems,":[16],"coding":[17],"tasks,":[18],"and":[19,71,87,106,131,178],"general":[20],"puzzles,":[21],"effectiveness":[23],"accurately":[25],"adhering":[26],"to":[27,50,64,92,117,135,165],"instructions":[28,83],"remains":[29],"inconsistent,":[30],"particularly":[31],"with":[32,84,149],"more":[33],"complex":[34,85],"directives.":[35],"Our":[36],"investigation":[37],"identifies":[38],"lazy":[39],"during":[41],"thinking":[43],"stage":[44],"as":[45,103],"primary":[47],"factor":[48],"contributing":[49],"poor":[51],"instruction":[52,77],"adherence.":[53],"To":[54],"mitigate":[55],"this":[56],"issue,":[57],"we":[58,80,109,140],"propose":[59],"a":[60,89,119,125],"comprehensive":[61],"framework":[62],"designed":[63],"enable":[65],"rigorous":[66],"processes":[68],"involving":[69],"preview":[70,177],"self-checking,":[72],"essential":[73],"for":[74],"satisfying":[75],"strict":[76],"constraints.":[78],"Specifically,":[79],"first":[81],"generate":[82],"constraints":[86],"apply":[88],"filtering":[90],"process":[91],"obtain":[93],"valid":[94],"prompts,":[95],"resulting":[96],"three":[98],"distinct":[99],"prompt":[100],"datasets":[101],"categorized":[102],"hard,":[104],"easy,":[105],"pass.":[107],"Then,":[108],"employ":[110,141],"rejection":[111],"sampling":[112],"on":[113,183],"pass":[115],"prompts":[116],"curate":[118],"small":[120],"yet":[121],"high-quality":[122],"dataset,":[123],"enabling":[124],"cold-start":[126],"initialization":[127],"model":[130,164,192],"facilitating":[132],"its":[133,167],"adaptation":[134],"effective":[136],"patterns.":[138],"Subsequently,":[139],"an":[142],"entropy-preserving":[143],"supervised":[144],"fine-tuning":[145],"(Entropy-SFT)":[146],"strategy":[147],"coupled":[148],"token-wise":[150],"entropy-adaptive":[151],"(TEA-RL)":[152],"reinforcement":[153],"learning":[154],"guided":[155],"by":[156],"rule-based":[157],"dense":[158],"rewards.":[159],"This":[160],"approach":[161],"encourages":[162],"transform":[166],"mechanism,":[169],"ultimately":[170],"fostering":[171],"generalizable":[172],"that":[175],"encompass":[176],"self-checking.":[179],"Extensive":[180],"experiments":[181],"conducted":[182],"instruction-following":[184],"benchmarks":[185],"demonstrate":[186],"remarkable":[187],"improvements":[189],"across":[190],"various":[191],"scales.":[193]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-20T00:00:00"}