{"id":"https://openalex.org/W4415163491","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1828","title":"Activation Steering for Chain-of-Thought Compression","display_name":"Activation Steering for Chain-of-Thought Compression","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415163491","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1828"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1828","pdf_url":"https://aclanthology.org/2026.findings-acl.1828.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: ACL 2026","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.findings-acl.1828.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103091182","display_name":"Seyedarmin Azizi","orcid":"https://orcid.org/0009-0006-8955-3577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seyedarmin Azizi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119753603","display_name":"Erfan Baghaei Potraghloo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erfan Baghaei Potraghloo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Souvik Kundu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Souvik Kundu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044650311","display_name":"Massoud Pedram","orcid":"https://orcid.org/0000-0002-2677-7307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Massoud Pedram","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":0.00447177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36676","last_page":"36687"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.6689000129699707,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.6689000129699707,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T13283","display_name":"Mental Health Research Topics","score":0.6662999987602234,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7361000180244446},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7087000012397766},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.5934000015258789},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5534999966621399},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5328999757766724},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5029000043869019},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4747999906539917}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7361000180244446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7182000279426575},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7087000012397766},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5934000015258789},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5534999966621399},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5328999757766724},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4747999906539917},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3707999885082245},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C81081738","wikidata":"https://www.wikidata.org/wiki/Q55542","display_name":"Lossless compression","level":3,"score":0.34599998593330383},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3167000114917755},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.29910001158714294},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.266400009393692}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1828","pdf_url":"https://aclanthology.org/2026.findings-acl.1828.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: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.04742","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.04742","pdf_url":"https://arxiv.org/pdf/2507.04742","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.2507.04742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.04742","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.findings-acl.1828","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1828","pdf_url":"https://aclanthology.org/2026.findings-acl.1828.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: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415163491.pdf","grobid_xml":"https://content.openalex.org/works/W4415163491.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,197],"(LLMs)":[3],"demonstrate":[4],"strong":[5],"performance":[6],"on":[7,67,214],"multi-step":[8],"reasoning":[9,83,185],"tasks":[10],"by":[11,97,131,178],"producing":[12],"intermediate":[13,56],"explanations,":[14],"commonly":[15],"referred":[16],"to":[17,50,75,117],"as":[18,179,181],"chains":[19],"of":[20,107,127,169,212],"thought":[21],"(CoTs).However,":[22],"the":[23,54,78,159,174],"generated":[24,175],"rationales":[25],"are":[26],"typically":[27],"verbose,":[28],"consuming":[29],"many":[30],"additional":[31],"tokens,":[32],"and":[33,37,46,142,191,202],"thus":[34],"degrading":[35],"throughput":[36],"increasing":[38],"inference":[39,210],"energy":[40,136],"consumption.Interestingly,":[41],"we":[42,70],"find":[43],"that":[44,60],"verbose":[45],"concise":[47,82,95],"CoTs":[48,96],"correspond":[49],"distinct":[51],"regions":[52],"in":[53],"model's":[55],"activation":[57,103],"space,":[58],"suggesting":[59],"verbosity":[61],"is":[62,109],"a":[63,114,119,124,133,148,163],"steerable":[64],"latent":[65],"attribute.Building":[66],"this":[68],"observation,":[69],"develop":[71],"an":[72,208,215],"inference-time":[73],"method":[74],"automatically":[76],"steer":[77],"model":[79,87],"response":[80],"towards":[81],"traces":[84],"without":[85],"updating":[86],"parameters.Our":[88],"method,":[89],"dubbed":[90],"ASC":[91,108,172,206],"(Activation-Steered":[92],"Compression),":[93],"generates":[94],"directly":[98],"adjusting":[99],"internal":[100],"representations":[101],"via":[102],"steering.A":[104],"key":[105],"component":[106],"Contrastive":[110],"Energy-Based":[111],"Steering":[112],"(CES),":[113],"principled":[115],"procedure":[116],"learn":[118],"single":[120],"steering":[121,141,154],"vector":[122,155],"from":[123],"small":[125],"set":[126],"verbose-concise":[128,170],"CoT":[129],"pairs":[130,168],"optimizing":[132],"lengthnormalized":[134],"contrastive":[135],"objective.To":[137],"further":[138],"ensure":[139],"reliable":[140],"preserve":[143],"general":[144],"utility,":[145],"CES":[146],"enforces":[147],"differentiable":[149],"KL":[150],"trust":[151],"region":[152],"during":[153],"optimization,":[156],"explicitly":[157],"constraining":[158],"distribution":[160],"shift":[161],"within":[162],"specified":[164],"budget.With":[165],"only":[166],"100":[167],"examples,":[171],"reduces":[173],"token":[176],"length":[177],"much":[180],"69.4%":[182],"across":[183,196],"five":[184],"benchmarks":[186],"(MATH500,":[187],"GSM8K,":[188],"LiveCodeBench,":[189],"GSM8K-Hard,":[190],"AQuA-RAT)":[192],"while":[193],"maintaining":[194],"accuracy":[195],"with":[198],"1.5B,":[199],"7B,":[200],"8B,":[201],"32B":[203],"parameters.On":[204],"MATH500,":[205],"achieves":[207],"end-to-end":[209],"speed-up":[211],"2.7\u00d7":[213],"8B":[216],"model.":[217]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-14T00:00:00"}