{"id":"https://openalex.org/W7214911883","doi":"https://doi.org/10.48550/arxiv.2609.36145","title":"From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text Detection","display_name":"From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text Detection","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214911883","doi":"https://doi.org/10.48550/arxiv.2609.36145"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36145","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36145","pdf_url":"https://arxiv.org/pdf/2609.36145","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.36145","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153617980","display_name":"Kaiqing Lin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Kaiqing","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153626932","display_name":"Songze Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Songze","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153652982","display_name":"Shen Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shen","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153654106","display_name":"Yunfei Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yunfei","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008630718","display_name":"Xiaoye Qiu","orcid":"https://orcid.org/0009-0003-9723-649X","observed_orcids":["https://orcid.org/0009-0003-9723-649X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Xiaoye","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153585767","display_name":"Haodong Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haodong","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033773467","display_name":"Taiping Yao","orcid":"https://orcid.org/0000-0002-2359-1523","observed_orcids":["https://orcid.org/0000-0002-2359-1523"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Taiping","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153621004","display_name":"Bo Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bo","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153622744","display_name":"Youchang Xiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao, Youchang","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","Shenzhen Key Laboratory of Media Security , and SZU-AFS Joint Innovation Center for AI Technology , Shenzhen University , Shenzhen 518060 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Media Security , and SZU-AFS Joint Innovation Center for AI Technology , Shenzhen University , Shenzhen 518060 , China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153671781","display_name":"Bin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Bin","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","Tencent Youtu Lab , Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]},{"raw_affiliation_string":"Tencent Youtu Lab , Shanghai , China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153629425","display_name":"Shouhong Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Shouhong","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9854000210762024,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9854000210762024,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.005900000222027302,"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/T10388","display_name":"Advanced Steganography and Watermarking Techniques","score":0.0027000000700354576,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9440000057220459},{"id":"https://openalex.org/keywords/forensic-document-examination","display_name":"forensic document examination","score":0.5720000267028809},{"id":"https://openalex.org/keywords/representation-alignment","display_name":"representation alignment","score":0.7110000252723694},{"id":"https://openalex.org/keywords/document-authenticity","display_name":"document authenticity","score":0.6000000238418579},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.796999990940094},{"id":"https://openalex.org/keywords/two-stage-framework","display_name":"two-stage framework","score":0.5080000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053999900817871},{"id":"https://openalex.org/C202269582","wikidata":"https://www.wikidata.org/wiki/Q2644277","display_name":"Complementarity (molecular biology)","level":2,"score":0.5651000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564000010490417},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4918999969959259},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4408999979496002},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3230000138282776},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C84418412","wikidata":"https://www.wikidata.org/wiki/Q3246940","display_name":"Digital forensics","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C102600418","wikidata":"https://www.wikidata.org/wiki/Q6517507","display_name":"Legal expert system","level":3,"score":0.27149999141693115},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C130440534","wikidata":"https://www.wikidata.org/wiki/Q14946528","display_name":"Conflation","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2603999972343445}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36145","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36145","pdf_url":"https://arxiv.org/pdf/2609.36145","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.2609.36145","doi":"https://doi.org/10.48550/arxiv.2609.36145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36145","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:2609.36145","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36145","pdf_url":"https://arxiv.org/pdf/2609.36145","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214911883.pdf","grobid_xml":"https://content.openalex.org/works/W7214911883.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2908510526","https://openalex.org/W4366208220","https://openalex.org/W4385387668","https://openalex.org/W4402502665","https://openalex.org/W4405634586","https://openalex.org/W4407794264","https://openalex.org/W4415269881","https://openalex.org/W4415343382","https://openalex.org/W4416060568","https://openalex.org/W4416068737","https://openalex.org/W4416623360","https://openalex.org/W4416780398","https://openalex.org/W7084059388","https://openalex.org/W7160274395","https://openalex.org/W7196931890","https://openalex.org/W7196961178"],"related_works":["https://openalex.org/W7138031105","https://openalex.org/W4415536931","https://openalex.org/W7165776097","https://openalex.org/W4405634586","https://openalex.org/W7215118008","https://openalex.org/W4416363426","https://openalex.org/W7204882027","https://openalex.org/W7204869867","https://openalex.org/W4403992146","https://openalex.org/W4313038702"],"abstract_inverted_index":{"Tampered":[0],"Text":[1],"Detection":[2],"(TTD)":[3],"is":[4,209],"essential":[5],"for":[6],"safeguarding":[7],"document":[8,29],"authenticity":[9],"in":[10],"security-critical":[11],"workflows.":[12],"Existing":[13],"expert":[14,57,208,233],"models":[15],"are":[16,177],"effective":[17],"at":[18,234],"capturing":[19],"subtle":[20],"manipulation":[21],"traces":[22],"but":[23],"often":[24],"generalize":[25],"poorly":[26],"across":[27],"diverse":[28],"domains,":[30],"while":[31],"Multimodal":[32],"Large":[33],"Language":[34],"Models":[35],"(MLLMs)":[36],"offer":[37],"stronger":[38,198],"semantic":[39,181],"understanding":[40],"and":[41,92,96,104,134,188,197,203],"transferability":[42],"yet":[43],"remain":[44],"insensitive":[45],"to":[46,54,169,218,224],"fine-grained":[47,171],"forensic":[48,58,106,124,164],"artifacts.":[49],"This":[50],"complementarity":[51],"motivates":[52],"us":[53],"investigate":[55],"how":[56],"perception":[59,173],"can":[60],"be":[61],"internalized":[62],"into":[63,126],"an":[64,71],"MLLM":[65,128,217],"rather":[66],"than":[67,200],"merely":[68],"accessed":[69],"through":[70],"external":[72,232],"module.":[73],"We":[74],"identify":[75],"a":[76,84,97,118,162],"fundamental":[77],"Double":[78],"Mismatch":[79,87,100],"that":[80,122,192],"hinders":[81],"this":[82],"goal:":[83],"Spatial":[85],"Precision":[86],"between":[88,101],"coarse":[89],"visual":[90],"tokens":[91],"tiny":[93],"tampered":[94],"regions,":[95],"Perceptual":[98],"Granularity":[99],"semantics-oriented":[102],"pre-training":[103],"low-level":[105],"perception.":[107],"To":[108],"address":[109],"these":[110],"challenges,":[111],"we":[112],"propose":[113],"Expert":[114],"Knowledge":[115],"Internalization":[116],"(EKI),":[117],"progressive":[119],"two-stage":[120],"framework":[121],"transfers":[123],"expertise":[125],"the":[127,148,167,207,215,225],"itself.":[129],"In":[130,145],"Stage":[131,146],"1,":[132],"Text-Focused":[133],"Image-Focused":[135],"strategies":[136],"establish":[137],"precise":[138],"spatial":[139],"focus":[140],"on":[141,185,230],"small":[142],"text":[143],"regions.":[144],"2,":[147],"proposed":[149],"Forensic-General":[150],"Representation":[151],"Alignment":[152],"(FGRA)":[153],"loss":[154],"aligns":[155],"shallow":[156],"LLM":[157],"representations":[158],"with":[159],"those":[160],"of":[161],"pre-trained":[163],"expert,":[165],"enabling":[166],"model":[168,227],"acquire":[170],"artifact":[172],"before":[174],"such":[175],"cues":[176],"diluted":[178],"by":[179],"deeper":[180],"abstraction.":[182],"Extensive":[183],"experiments":[184],"multiple":[186],"in-domain":[187],"cross-domain":[189],"benchmarks":[190],"demonstrate":[191],"EKI":[193],"achieves":[194],"state-of-the-art":[195],"performance":[196],"generalization":[199],"existing":[201],"expert-model-based":[202],"MLLM-based":[204],"methods.":[205],"Moreover,":[206],"required":[210],"only":[211],"during":[212],"training,":[213],"allowing":[214],"resulting":[216],"maintain":[219],"inference":[220],"efficiency":[221],"nearly":[222],"identical":[223],"vanilla":[226],"without":[228],"relying":[229],"any":[231],"inference.":[235]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}