{"id":"https://openalex.org/W4414580661","doi":"https://doi.org/10.18653/v1/2026.acl-long.1878","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","display_name":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414580661","doi":"https://doi.org/10.18653/v1/2026.acl-long.1878"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1878","pdf_url":"https://aclanthology.org/2026.acl-long.1878.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1878.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013882133","display_name":"Tao Fu","orcid":"https://orcid.org/0000-0002-6356-1871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingchen Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032649444","display_name":"Yafu Li","orcid":"https://orcid.org/0000-0002-7895-9997"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yafu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015044456","display_name":"Jiawei Gu","orcid":"https://orcid.org/0000-0001-8170-4998"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065871371","display_name":"Xiaoye Qu","orcid":"https://orcid.org/0000-0002-4907-3978"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoye Qu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084146010","display_name":"Yu Cheng","orcid":"https://orcid.org/0000-0002-4837-3370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Cheng","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00646345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40445","last_page":"40463"},"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":0.8057000041007996,"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":0.8057000041007996,"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/benchmark","display_name":"Benchmark (surveying)","score":0.5321000218391418},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5238000154495239},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4578999876976013},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.45239999890327454},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.428600013256073},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4253000020980835},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.3864000141620636}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7595000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681999921798706},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5321000218391418},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41260001063346863},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3862999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3160000145435333},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1878","pdf_url":"https://aclanthology.org/2026.acl-long.1878.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.14810","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14810","pdf_url":"https://arxiv.org/pdf/2505.14810","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"doi:10.48550/arxiv.2505.14810","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.14810","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1878","pdf_url":"https://aclanthology.org/2026.acl-long.1878.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414580661.pdf","grobid_xml":"https://content.openalex.org/works/W4414580661.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction-following":[0],"is":[1],"essential":[2],"for":[3,123],"aligning":[4],"large":[5,45],"language":[6,30],"models":[7,47,60],"(LLMs)":[8],"with":[9,27],"user":[10],"intent.Yet":[11],"recent":[12],"reasoning-oriented":[13],"models,":[14],"despite":[15],"their":[16,73],"strong":[17],"performance":[18],"on":[19,70],"complex":[20],"mathematical":[21],"problems,":[22],"often":[23],"fail":[24],"to":[25,75,126],"comply":[26],"simple":[28],"natural":[29],"directives.In":[31],"this":[32],"work,":[33],"we":[34,54],"analyze":[35],"the":[36,100,121],"interaction":[37],"between":[38,111],"reasoning":[39,46,62,71,103,129],"ability":[40],"and":[41,113,119],"instruction":[42],"adherence":[43],"in":[44,115],"(LRMs).Using":[48],"a":[49,56,109],"controlled":[50],"evaluation":[51],"framework":[52],"(MathIF),":[53],"uncover":[55],"persistent":[57],"trade-off:":[58],"as":[59,88],"scale":[61],"capacity":[63],"through":[64],"long":[65],"chains-of-thought":[66],"or":[67,90],"reinforcement":[68],"learning":[69],"traces,":[72],"obedience":[74,114],"instructions":[76,92],"degrades,":[77],"particularly":[78],"when":[79],"generation":[80],"length":[81],"grows.We":[82],"further":[83],"show":[84],"that":[85],"interventions":[86],"such":[87],"constraining":[89],"repeating":[91],"can":[93],"partially":[94],"restore":[95],"compliance,":[96],"but":[97],"typically":[98],"at":[99],"expense":[101],"of":[102],"performance.Taken":[104],"together,":[105],"our":[106],"findings":[107],"expose":[108],"dilemma":[110],"intelligence":[112],"current":[116],"training":[117],"paradigms":[118],"underscore":[120],"need":[122],"instruction-aware":[124],"approaches":[125],"developing":[127],"controllable":[128],"models.":[130]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}