{"id":"https://openalex.org/W7225664430","doi":"https://doi.org/10.21203/rs.3.rs-11394163/v1","title":"Explainability and Interpretability Methods for Large Language Models: An Exploratory Systematic Mapping Study","display_name":"Explainability and Interpretability Methods for Large Language Models: An Exploratory Systematic Mapping Study","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225664430","doi":"https://doi.org/10.21203/rs.3.rs-11394163/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11394163/v1","doi":"https://doi.org/10.21203/rs.3.rs-11394163/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11394163/v1","pdf_url":"https://www.researchsquare.com/article/rs-11394163/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11394163/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050942947","display_name":"Georgios Makridis","orcid":"https://orcid.org/0000-0002-6165-7239","observed_orcids":["https://orcid.org/0000-0002-6165-7239"]},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Makridis","raw_affiliation_strings":["University of Piraeus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Piraeus","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161306910","display_name":"George Fatouros","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"George Fatouros","raw_affiliation_strings":["University of Piraeus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Piraeus","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160373419","display_name":"Stefanos Kampouris","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stefanos Kampouris","raw_affiliation_strings":["University of Piraeus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Piraeus","institution_ids":["https://openalex.org/I154757721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135392146","display_name":"John Soldatos","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Soldatos","raw_affiliation_strings":["ExpertAI SARL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ExpertAI SARL","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105974390","display_name":"Dimosthenis Kyriazis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimosthenis Kyriazis","raw_affiliation_strings":["University of Piraeus"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Piraeus","institution_ids":["https://openalex.org/I154757721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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":1.0,"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":0.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"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/explainability","display_name":"explainability","score":0.7689999938011169},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.972000002861023},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":1.0},{"id":"https://openalex.org/keywords/circuit-analysis","display_name":"circuit analysis","score":0.7580000162124634},{"id":"https://openalex.org/keywords/feature-discovery","display_name":"feature discovery","score":0.9160000085830688},{"id":"https://openalex.org/keywords/attribution","display_name":"attribution","score":0.8069999814033508},{"id":"https://openalex.org/keywords/probing","display_name":"probing","score":0.6809999942779541},{"id":"https://openalex.org/keywords/model-editing","display_name":"model editing","score":0.6690000295639038},{"id":"https://openalex.org/keywords/source-attribution","display_name":"source attribution","score":0.8299999833106995},{"id":"https://openalex.org/keywords/evaluation-benchmark","display_name":"evaluation benchmark","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8489000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5942000150680542},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4634999930858612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4528000056743622},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3898000121116638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3269999921321869},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2776240099","wikidata":"https://www.wikidata.org/wiki/Q327018","display_name":"Interrogation","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11394163/v1","doi":"https://doi.org/10.21203/rs.3.rs-11394163/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11394163/v1","pdf_url":"https://www.researchsquare.com/article/rs-11394163/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11394163/v1","doi":"https://doi.org/10.21203/rs.3.rs-11394163/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11394163/v1","pdf_url":"https://www.researchsquare.com/article/rs-11394163/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[{"id":"https://openalex.org/study-designs/systematic-review","display_name":"Systematic Review"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225664430.pdf","grobid_xml":"https://content.openalex.org/works/W7225664430.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1999798506","https://openalex.org/W2020018978","https://openalex.org/W2053154970","https://openalex.org/W3015575765","https://openalex.org/W3118615836","https://openalex.org/W3123497531","https://openalex.org/W4385291106","https://openalex.org/W4385327568","https://openalex.org/W4391212767","https://openalex.org/W4392181812","https://openalex.org/W4402671231","https://openalex.org/W4404314166","https://openalex.org/W4406072863","https://openalex.org/W4408361331","https://openalex.org/W4409348217","https://openalex.org/W4412888771","https://openalex.org/W4414359498","https://openalex.org/W4415020510","https://openalex.org/W4415035631","https://openalex.org/W4416036098","https://openalex.org/W4416037058","https://openalex.org/W4416260402","https://openalex.org/W4417094175","https://openalex.org/W7082152151","https://openalex.org/W7117871696","https://openalex.org/W7166832698","https://openalex.org/W7166858675","https://openalex.org/W7166885958","https://openalex.org/W7166889768","https://openalex.org/W7222060862"],"related_works":["https://openalex.org/W7225295842","https://openalex.org/W4407124164","https://openalex.org/W7223761289","https://openalex.org/W4413423613","https://openalex.org/W4391212767","https://openalex.org/W7223264062","https://openalex.org/W7201956982","https://openalex.org/W4399038319","https://openalex.org/W7213303196","https://openalex.org/W7204812807"],"abstract_inverted_index":{"Abstract":[0],"Explainability":[1],"for":[2,52,151,165],"large":[3],"language":[4],"models":[5],"(LLMs)":[6],"spans":[7],"circuit":[8],"analysis,":[9],"feature":[10],"discovery,":[11],"attribution,":[12,19],"probing":[13],"and":[14,21,83,93,100,116,139,156,188,209,212,221],"editing,":[15],"rationale":[16],"faithfulness,":[17],"source":[18],"benchmarks":[20],"human-facing":[22],"explanation.":[23],"This":[24],"systematic":[25],"mapping":[26],"study":[27],"charts":[28],"studies":[29,80,155,187],"that":[30,40,59,197,203,210],"explain":[31,45,60],"an":[32,35,42],"LLM":[33,43],"or":[34,65,148,162,168],"LLM-centred":[36],"pipeline,":[37],"excluding":[38],"work":[39],"utilises":[41],"to":[44,56],"another":[46],"system.":[47],"Seven":[48],"sources":[49],"were":[50,81,102,117],"searched":[51],"reports":[53],"from":[54],"2019":[55],"August":[57],"2026":[58],"at":[61,69],"least":[62,70],"one":[63],"decoder-only":[64],"encoder\u2013decoder":[66],"model":[67],"of":[68,153],"1B":[71],"parameters.":[72],"Of":[73],"7,825":[74],"records":[75],"(5,730":[76],"after":[77,129],"deduplication),":[78],"1,252":[79],"included":[82],"coded":[84,172],"by":[85,104],"method":[86],"family,":[87],"explanandum,":[88],"required":[89],"access,":[90],"evaluation":[91],"construct":[92],"a":[94,105,113,120],"four-field":[95],"evidence":[96,170,214],"profile.":[97],"Screening,":[98],"eligibility":[99],"coding":[101],"performed":[103],"disclosed":[106],"AI":[107],"reviewer":[108],"whose":[109],"every":[110,222],"decision":[111,223],"carries":[112],"verbatim":[114],"quote,":[115],"validated":[118],"against":[119],"human":[121,179],"reviewer:":[122],"title/abstract":[123],"agreement":[124,135],"reached":[125],"\u03ba":[126,136],"=":[127,137],"0.84":[128],"two":[130],"failed":[131],"calibration":[132],"rounds,":[133],"full-text":[134],"0.72,":[138],"conservative":[140],"screening":[141],"recall":[142],"was":[143],"0.78.":[144],"Methods":[145],"requiring":[146],"weights":[147],"activations":[149],"account":[150],"69.8%":[152],"the":[154],"methods":[157,200],"compatible":[158],"with":[159],"hosted":[160,204],"text":[161],"logit":[163],"access":[164,202],"23.3%;":[166],"faithfulness":[167],"causal-validity":[169],"is":[171],"in":[173,181,185,192],"70.4%":[174],"(an":[175],"approximate":[176],"AI-coded":[177],"estimate),":[178],"utility":[180],"3.4%,":[182],"deployed":[183],"settings":[184],"7":[186],"specific":[189],"regulatory":[190],"obligations":[191],"10.":[193],"The":[194,217],"map":[195],"indicates":[196],"most":[198],"explanation":[199],"require":[201],"LLMs":[205],"do":[206],"not":[207],"expose,":[208],"human-centred":[211],"deployment":[213],"remains":[215],"scarce.":[216],"protocol,":[218],"its":[219],"amendment":[220],"are":[224],"released.":[225]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}