{"id":"https://openalex.org/W4417114215","doi":"https://doi.org/10.18653/v1/2026.acl-long.1759","title":"Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy","display_name":"Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417114215","doi":"https://doi.org/10.18653/v1/2026.acl-long.1759"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1759","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1759","pdf_url":"https://aclanthology.org/2026.acl-long.1759.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.1759.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088789651","display_name":"Eric Hanchen Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Hanchen Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120721076","display_name":"Weixuan Ou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weixuan Ou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341945","display_name":"Run Liu","orcid":"https://orcid.org/0000-0002-1144-4366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Run Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108051911","display_name":"Shaoning Pang","orcid":"https://orcid.org/0000-0002-2833-5270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengyuan Pang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102638295","display_name":"Guancheng Wan","orcid":"https://orcid.org/0000-0002-7083-6423"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guancheng Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043909623","display_name":"Ranjie Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranjie Duan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391490","display_name":"Dong Wei","orcid":"https://orcid.org/0000-0002-6342-4658"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087096372","display_name":"Kai-Wei Chang","orcid":"https://orcid.org/0000-0001-5365-0072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai-Wei Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333245","display_name":"Xiaofeng Wang","orcid":"https://orcid.org/0000-0002-7040-2625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"XiaoFeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059211394","display_name":"Ying Wu","orcid":"https://orcid.org/0000-0001-6581-9816"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Nian Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044549752","display_name":"Xinfeng Li","orcid":"https://orcid.org/0000-0002-9686-4369"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinfeng Li","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":0.03383962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37930","last_page":"37950"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5454000234603882,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5454000234603882,"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/T10028","display_name":"Topic Modeling","score":0.14079999923706055,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0689999982714653,"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/decoupling","display_name":"Decoupling (probability)","score":0.586899995803833},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5375999808311462},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5293999910354614},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.49399998784065247},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4778999984264374},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.361299991607666},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.3499999940395355}],"concepts":[{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5774999856948853},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30799999833106995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30059999227523804},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C7817414","wikidata":"https://www.wikidata.org/wiki/Q1779504","display_name":"Energy management","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1759","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1759","pdf_url":"https://aclanthology.org/2026.acl-long.1759.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:2510.08646","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.08646","pdf_url":"https://arxiv.org/pdf/2510.08646","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.08646","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.08646","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.1759","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1759","pdf_url":"https://aclanthology.org/2026.acl-long.1759.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":[{"id":"https://openalex.org/G5268958991","display_name":null,"funder_award_id":"W912CG25CA007","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6791872014","display_name":"Collaborative Research: Graph Learning, Generation, and Optimization with Highly Expressive Graph Neural Network Models","funder_award_id":"2415226","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417114215.pdf","grobid_xml":"https://content.openalex.org/works/W4417114215.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Eric":[0],"Hanchen":[1],"Jiang,":[2],"Weixuan":[3],"Ou,":[4],"Run":[5],"Liu,":[6],"Shengyuan":[7],"Pang,":[8],"Guancheng":[9],"Wan,":[10],"Ranjie":[11],"Duan,":[12],"Wei":[13],"Dong,":[14],"Kai-Wei":[15],"Chang,":[16],"XiaoFeng":[17],"Wang,":[18],"Ying":[19],"Nian":[20],"Wu,":[21],"Xinfeng":[22],"Li.":[23],"Proceedings":[24],"of":[25,30],"the":[26,31],"64th":[27],"Annual":[28],"Meeting":[29],"Association":[32],"for":[33],"Computational":[34],"Linguistics":[35],"(Volume":[36],"1:":[37],"Long":[38],"Papers).":[39],"2026.":[40]},"counts_by_year":[],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2025-10-14T00:00:00"}