{"id":"https://openalex.org/W7117871696","doi":"https://doi.org/10.1145/3787470.3787477","title":"Towards Uncovering How Large Language ModelsWork: An Interpretability Perspective","display_name":"Towards Uncovering How Large Language ModelsWork: An Interpretability Perspective","publication_year":2025,"publication_date":"2025-12-30","ids":{"openalex":"https://openalex.org/W7117871696","doi":"https://doi.org/10.1145/3787470.3787477"},"language":"en","primary_location":{"id":"doi:10.1145/3787470.3787477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3787470.3787477","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},"type":"article","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/A5121710132","display_name":"Haiyan Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyan Zhao","raw_affiliation_strings":["New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101811222","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0002-4954-9681"},"institutions":[{"id":"https://openalex.org/I47251452","display_name":"Wake Forest University","ror":"https://ror.org/0207ad724","country_code":"US","type":"education","lineage":["https://openalex.org/I47251452"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Wake Forest University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wake Forest University","institution_ids":["https://openalex.org/I47251452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101364672","display_name":"Bo Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Shen","raw_affiliation_strings":["New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121717292","display_name":"Ali Payani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Payani","raw_affiliation_strings":["Cisco Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cisco Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015520086","display_name":"Himabindu Lakkaraju","orcid":"https://orcid.org/0000-0001-7922-6544"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Himabindu Lakkaraju","raw_affiliation_strings":["Harvard University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harvard University","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072191151","display_name":"Mengnan Du","orcid":"https://orcid.org/0000-0002-1614-6069"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengnan Du","raw_affiliation_strings":["New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75057013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"2","first_page":"79","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2883000075817108,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.2883000075817108,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.17980000376701355,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.11860000342130661,"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":0.8755000233650208},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6453999876976013},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6252999901771545},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.5993000268936157},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5346999764442444},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.451200008392334},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.44839999079704285},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.37119999527931213}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8755000233650208},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6453999876976013},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6252999901771545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067000031471252},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.5993000268936157},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5346999764442444},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4569999873638153},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.45660001039505005},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.44839999079704285},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.37119999527931213},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3634999990463257},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3312000036239624},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.3278000056743622},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.304500013589859},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2856999933719635},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C39389867","wikidata":"https://www.wikidata.org/wiki/Q380767","display_name":"Corporate governance","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.26829999685287476},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C39920170","wikidata":"https://www.wikidata.org/wiki/Q693083","display_name":"Soundness","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.257099986076355},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787470.3787477","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3787470.3787477","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4555826485157013,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,12],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"re2":[6],"markable":[7],"performance":[8,148],"in":[9,39,104],"tackling":[10],"natural":[11],"3":[13],"tasks,":[14],"yet":[15],"the":[16,52,67,76,118,137],"internal":[17,68],"mechanisms":[18,70],"that":[19],"enable":[20],"their":[21],"4":[22],"impressive":[23],"generalization":[24,125],"and":[25,48,54,111,130,158],"reasoning":[26],"abilities":[27],"5":[28],"remain":[29],"opaque.":[30],"This":[31,60],"lack":[32],"of":[33,58,78],"transparency":[34],"presents":[35],"6":[36],"significant":[37],"challenges":[38],"fundamentally":[40],"eliminating":[41],"7":[42],"undesirable":[43],"behaviors":[44],"such":[45],"as":[46],"hallucinations":[47],"8":[49],"toxicity,":[50],"hindering":[51],"safe":[53],"beneficial":[55],"deploy9":[56],"ment":[57],"LLMs.":[59],"survey":[61],"paper":[62],"aims":[63],"to":[64,122],"un10":[65],"cover":[66],"working":[69],"underly11":[71],"ing":[72],"LLM":[73,147],"functionality":[74],"through":[75,128,150,155],"lens":[77],"explain12":[79],"ability.":[80],"First,":[81],"we":[82,97,116,134],"review":[83],"how":[84,136],"knowledge":[85],"is":[86,102],"en13":[87],"coded":[88],"within":[89],"LLMs":[90],"via":[91],"mechanistic":[92],"interpretabil14":[93],"ity":[94],"techniques.":[95],"Then,":[96],"summarize":[98],"what":[99],"knowl15":[100],"edge":[101],"embedded":[103],"LLMrepresentations":[105],"by":[106],"lever16":[107],"aging":[108],"probing":[109],"techniques":[110],"representation":[112],"engi17":[113],"neering.":[114],"Additionally,":[115],"investigate":[117],"training":[119],"18":[120],"dynamics":[121],"explore":[123,135],"models'":[124],"abili19":[126],"ties":[127],"grokking":[129],"memorization.":[131],"Finally,":[132],"20":[133],"insights":[138],"gained":[139],"from":[140],"these":[141],"ex21":[142],"planations":[143],"can":[144],"further":[145],"enhance":[146],"22":[149],"model":[151],"editing,":[152],"improve":[153],"efficiency":[154],"23":[156],"pruning,":[157],"better":[159],"align":[160],"with":[161],"human":[162],"values.":[163]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-01T00:00:00"}