{"id":"https://openalex.org/W7128530285","doi":"https://doi.org/10.48550/arxiv.2602.07833","title":"SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models","display_name":"SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-02-08","ids":{"openalex":"https://openalex.org/W7128530285","doi":"https://doi.org/10.48550/arxiv.2602.07833"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.07833","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07833","pdf_url":"https://arxiv.org/pdf/2602.07833","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.07833","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125589490","display_name":"Weijiang Lv","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Weijiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159783452","display_name":"Yaoxuan Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yaoxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114803721","display_name":"Xiaobo Xia","orcid":"https://orcid.org/0000-0003-3615-0919","observed_orcids":["https://orcid.org/0000-0003-3615-0919"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Xiaobo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125503056","display_name":"Jiayu Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jiayu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125532742","display_name":"Yan Jing","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123552224","display_name":"Wenchao Chen","orcid":"https://orcid.org/0000-0002-8875-1161","observed_orcids":["https://orcid.org/0000-0002-8875-1161"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wenchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125522814","display_name":"Bo Chen","orcid":"https://orcid.org/0000-0002-5039-0663","observed_orcids":["https://orcid.org/0000-0002-5039-0663"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Bo","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":null,"has_fulltext":false,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.00019999999494757503,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.9240000247955322},{"id":"https://openalex.org/keywords/faithfulness","display_name":"faithfulness","score":0.7360000014305115},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9900000095367432},{"id":"https://openalex.org/keywords/reasoning-traces","display_name":"reasoning traces","score":0.640999972820282},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.3930000066757202}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8708000183105469},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6456999778747559},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6165000200271606},{"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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916000008583069},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.529699981212616},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5127000212669373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4909999966621399},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41780000925064087},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.36079999804496765},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.34850001335144043},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C2780929884","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Blindness","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.07833","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07833","pdf_url":"https://arxiv.org/pdf/2602.07833","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,"listed_in":[],"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.2602.07833","doi":"https://doi.org/10.48550/arxiv.2602.07833","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07833","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.07833","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.07833","pdf_url":"https://arxiv.org/pdf/2602.07833","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416191148","https://openalex.org/W4417448062","https://openalex.org/W7171669774","https://openalex.org/W7162118248","https://openalex.org/W7101703515","https://openalex.org/W4415068933","https://openalex.org/W7163208587","https://openalex.org/W7162557069","https://openalex.org/W4417137502","https://openalex.org/W7114808432"],"abstract_inverted_index":{"Chain-of-Thought":[0],"reasoning":[1,21,34,56,109],"is":[2],"widely":[3],"used":[4],"to":[5,80],"improve":[6],"the":[7,16,19,88,115],"interpretability":[8],"of":[9,18,117],"multimodal":[10],"large":[11],"language":[12],"models":[13],"(MLLMs),":[14],"yet":[15],"faithfulness":[17,40,120],"generated":[20],"traces":[22],"remains":[23],"unclear.":[24],"Prior":[25],"work":[26],"has":[27],"mainly":[28],"focused":[29],"on":[30,52,63],"perceptual":[31,71],"hallucinations,":[32],"leaving":[33],"level":[35],"unfaithfulness":[36],"underexplored.":[37],"To":[38],"isolate":[39],"from":[41],"linguistic":[42],"priors,":[43],"we":[44,95],"introduce":[45],"SPD-Faith":[46],"Bench,":[47],"a":[48,98],"diagnostic":[49],"benchmark":[50,125],"based":[51],"fine-grained":[53],"image":[54],"difference":[55],"that":[57,103],"enforces":[58],"explicit":[59],"visual":[60,82,100,105],"comparison.":[61],"Evaluations":[62],"state-of-the-art":[64],"MLLMs":[65],"reveal":[66],"two":[67],"systematic":[68],"failure":[69],"modes,":[70],"blindness":[72],"and":[73,84,107,126],"perception-reasoning":[74],"dissociation.":[75],"We":[76],"trace":[77],"these":[78],"failures":[79],"decaying":[81],"attention":[83],"representation":[85],"shifts":[86],"in":[87],"residual":[89],"stream.":[90],"Guided":[91],"by":[92],"this":[93],"analysis,":[94],"propose":[96],"SAGE,":[97],"train-free":[99],"evidence-calibrated":[101],"framework":[102],"improves":[104],"routing":[106],"aligns":[108],"with":[110],"perception.":[111],"Our":[112,124],"results":[113],"highlight":[114],"importance":[116],"explicitly":[118],"evaluating":[119],"beyond":[121],"response":[122],"correctness.":[123],"codes":[127],"are":[128],"available":[129],"at":[130],"https://github.com/Johanson-colab/SPD-Faith-Bench.":[131]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-02-11T00:00:00"}