{"id":"https://openalex.org/W4412888258","doi":"https://doi.org/10.18653/v1/2025.findings-acl.679","title":"Mechanistic Interpretability of Emotion Inference in Large Language Models","display_name":"Mechanistic Interpretability of Emotion Inference in Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888258","doi":"https://doi.org/10.18653/v1/2025.findings-acl.679"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.679","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.679","pdf_url":"https://aclanthology.org/2025.findings-acl.679.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 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.679.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043676212","display_name":"Ala Nekouvaght Tak","orcid":"https://orcid.org/0000-0001-6735-7571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ala N. Tak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116235417","display_name":"Amin Banayeeanzade","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amin Banayeeanzade","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072074683","display_name":"Anahita Bolourani","orcid":"https://orcid.org/0000-0003-3003-4327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anahita Bolourani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094347705","display_name":"Mina Kian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mina Kian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041906762","display_name":"Robin Jia","orcid":"https://orcid.org/0009-0002-8123-7132"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Robin Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111548075","display_name":"Jonathan Gratch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Gratch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2763,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.9539362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"13090","last_page":"13120"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9580000042915344,"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":0.9580000042915344,"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/interpretability","display_name":"Interpretability","score":0.952193021774292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7001022696495056},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6911634206771851},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5908557176589966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48622241616249084},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.419908344745636},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.33076560497283936},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1671607494354248}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.952193021774292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7001022696495056},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6911634206771851},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5908557176589966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48622241616249084},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.419908344745636},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.33076560497283936},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1671607494354248}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.679","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.679","pdf_url":"https://aclanthology.org/2025.findings-acl.679.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 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.679","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.679","pdf_url":"https://aclanthology.org/2025.findings-acl.679.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 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888258.pdf","grobid_xml":"https://content.openalex.org/works/W4412888258.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,18],"(LLMs)":[3],"show":[4,63,101],"promising":[5],"capabilities":[6],"in":[7,46,128],"predicting":[8],"human":[9],"emotions":[10,82],"from":[11,84],"text.However,":[12],"the":[13,47,65,98,103],"mechanisms":[14],"through":[15],"which":[16],"these":[17],"process":[19],"emotional":[20],"stimuli":[21],"remain":[22],"largely":[23],"unexplored.Our":[24],"study":[25],"addresses":[26],"this":[27],"gap":[28],"by":[29,59,71],"investigating":[30],"how":[31],"autoregressive":[32],"LLMs":[33],"infer":[34],"emotions,":[35],"showing":[36],"that":[37,64,81,102],"emotion":[38,121],"representations":[39,67],"are":[40,68],"functionally":[41],"localized":[42],"to":[43,116],"specific":[44],"regions":[45],"model.Our":[48],"evaluation":[49],"includes":[50],"diverse":[51],"model":[52],"families":[53],"and":[54,56,100,108,119,126],"sizes,":[55],"is":[57],"supported":[58],"robustness":[60],"checks.We":[61],"then":[62],"identified":[66],"psychologically":[69],"plausible":[70],"drawing":[72],"on":[73,92],"cognitive":[74],"appraisal":[75,94],"theory-a":[76],"well-established":[77],"psychological":[78],"framework":[79],"positing":[80],"emerge":[83],"evaluations":[85],"(appraisals)":[86],"of":[87],"environmental":[88],"stimuli.By":[89],"causally":[90,117],"intervening":[91],"construed":[93],"concepts,":[95],"we":[96],"steer":[97],"generation":[99],"outputs":[104],"align":[105],"with":[106],"theoretical":[107],"intuitive":[109],"expectations.This":[110],"work":[111],"highlights":[112],"a":[113],"novel":[114],"way":[115],"intervene":[118],"control":[120],"inference,":[122],"potentially":[123],"benefiting":[124],"safety":[125],"alignment":[127],"sensitive":[129],"affective":[130],"domains.Code":[131],"at:":[132],"GitHub":[133],"repo.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}