{"id":"https://openalex.org/W4416251887","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228901","title":"Learning to Follow Domain-specific Instruction with Verifiable Rewards","display_name":"Learning to Follow Domain-specific Instruction with Verifiable Rewards","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251887","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228901"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061624006","display_name":"Shaohan Huang","orcid":"https://orcid.org/0000-0003-4324-6337"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohan Huang","raw_affiliation_strings":["Beihang University,Sino-German Joint Software Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-German Joint Software Institute,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330624","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1829-2817"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Beihang University,Sino-German Joint Software Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-German Joint Software Institute,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103215539","display_name":"Jiaxing Qi","orcid":"https://orcid.org/0000-0002-5283-1813"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Qi","raw_affiliation_strings":["Beihang University,Sino-German Joint Software Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-German Joint Software Institute,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University,Sino-German Joint Software Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-German Joint Software Institute,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University,Sino-German Joint Software Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-German Joint Software Institute,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Beihang University,Sino-German Joint Software Institute,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Sino-German Joint Software Institute,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.20309999585151672,"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":0.20309999585151672,"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":0.15189999341964722,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08020000159740448,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/bridging","display_name":"Bridging (networking)","score":0.7620000243186951},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6528000235557556},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6111999750137329},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.6096000075340271},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5404000282287598},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5113999843597412},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4936999976634979},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4140999913215637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057000041007996},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7620000243186951},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6528000235557556},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6111999750137329},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.6096000075340271},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5404000282287598},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5113999843597412},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4936999976634979},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42739999294281006},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.39969998598098755},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35359999537467957},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2955999970436096},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.29409998655319214},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.27239999175071716},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2970482702","https://openalex.org/W3080649016","https://openalex.org/W3194309076","https://openalex.org/W3196731672","https://openalex.org/W4382998379","https://openalex.org/W4387321091","https://openalex.org/W4388994228","https://openalex.org/W4389519254","https://openalex.org/W4389521013","https://openalex.org/W4391136507","https://openalex.org/W4401386758","https://openalex.org/W4402684226","https://openalex.org/W4405347008","https://openalex.org/W4406602253"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,121],"paper,":[2],"we":[3,89,124],"address":[4],"the":[5,48,53,79,84,96,105,111,116,150,196,200,216,225,229,232,238,248],"challenge":[6],"of":[7,44,50,55,75,81,129,153,170,187,208,218,235,241],"enabling":[8],"large":[9],"language":[10],"models":[11],"(LLMs)":[12],"to":[13,38,66,107,115,148,173,212,224],"effectively":[14],"follow":[15],"domain-specific":[16,133,171,242],"instructions,":[17],"a":[18,30,91,156,167,204],"critical":[19],"requirement":[20],"for":[21,33,181,250],"their":[22],"successful":[23],"deployment":[24],"across":[25,257],"various":[26,146],"industries.":[27,259],"We":[28,165],"propose":[29],"novel":[31],"pipeline":[32,42],"constructing":[34],"verifiable":[35],"instructions":[36,57],"tailored":[37],"specific":[39],"domains.":[40],"This":[41,102,221],"consists":[43],"three":[45],"key":[46],"stages:":[47],"creation":[49],"meta-requirement":[51],"templates,":[52],"generation":[54],"custom":[56],"using":[58],"GPT-4":[59,194],"with":[60,132,155],"seed":[61],"prompts,":[62],"and":[63,70,138,161,195,237,253],"manual":[64],"refinement":[65],"ensure":[67],"clarity,":[68],"precision,":[69],"relevance.":[71],"A":[72],"unique":[73],"aspect":[74],"our":[76,188,219],"approach":[77,189],"is":[78,190],"incorporation":[80],"verifiability":[82],"into":[83],"instruction-following":[85,151],"tuning":[86],"process.":[87],"Specifically,":[88],"design":[90],"verified":[92,122],"reward":[93],"mechanism":[94,103],"within":[95],"Direct":[97],"Preference":[98],"Optimization":[99],"(DPO)":[100],"framework.":[101],"leverages":[104],"ability":[106],"automatically":[108],"verify":[109],"whether":[110],"generated":[112],"responses":[113],"adhere":[114],"given":[117],"instructions.":[118],"By":[119],"integrating":[120],"reward,":[123],"enable":[125],"more":[126,251],"effective":[127],"alignment":[128],"LLM":[130,255],"behavior":[131],"requirements,":[134],"ensuring":[135],"higher":[136],"reliability":[137],"consistency":[139],"in":[140],"outputs.":[141],"Our":[142,245],"study":[143],"also":[144],"explores":[145],"strategies":[147],"enhance":[149],"capabilities":[152,234],"LLMs,":[154],"focus":[157],"on":[158,193],"fine-tuning":[159],"methodologies":[160],"data":[162],"augmentation":[163],"techniques.":[164],"provide":[166],"comprehensive":[168],"analysis":[169],"requirements":[172],"better":[174],"understand":[175],"how":[176],"LLMs":[177,236],"can":[178],"be":[179],"adapted":[180],"practical,":[182],"real-world":[183],"applications.":[184],"The":[185],"efficacy":[186],"empirically":[191],"validated":[192],"LLaMA2":[197],"series.":[198],"Notably,":[199],"LLaMA-7B":[201],"model":[202],"demonstrates":[203],"significant":[205],"performance":[206],"improvement":[207],"over":[209],"19%":[210],"compared":[211],"zero-shot":[213],"settings,":[214],"underscoring":[215],"effectiveness":[217],"methods.":[220],"work":[222],"contributes":[223],"field":[226],"by":[227],"bridging":[228],"gap":[230],"between":[231],"general":[233],"nuanced":[239],"demands":[240],"instruction":[243],"following.":[244],"findings":[246],"pave":[247],"way":[249],"reliable":[252],"adaptable":[254],"applications":[256],"diverse":[258]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}
