{"id":"https://openalex.org/W7164843783","doi":"https://doi.org/10.1145/3805622.3810776","title":"Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting","display_name":"Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164843783","doi":"https://doi.org/10.1145/3805622.3810776"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810776","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810776","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124115583","display_name":"Yijie Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yijie Hong","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-6817-5586","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138655788","display_name":"Xiaofei Yin","orcid":"https://orcid.org/0009-0000-7292-2184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofei Yin","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-7292-2184","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102835896","display_name":"Xinzhong Wang","orcid":"https://orcid.org/0009-0003-2082-375X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhong Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-2082-375X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750284","display_name":"Ya Guo","orcid":"https://orcid.org/0000-0002-9242-493X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya Guo","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9242-493X","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101572850","display_name":"Huijia Zhu","orcid":"https://orcid.org/0009-0008-5784-7225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huijia Zhu","raw_affiliation_strings":["Ant Group, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-5784-7225","affiliations":[{"raw_affiliation_string":"Ant Group, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074561776","display_name":"Sufeng Duan","orcid":"https://orcid.org/0000-0002-1210-8954"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sufeng Duan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1210-8954","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"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":0.93837365,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"515","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8806999921798706,"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":0.8806999921798706,"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/T10028","display_name":"Topic Modeling","score":0.05040000006556511,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.021199999377131462,"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/closed-captioning","display_name":"Closed captioning","score":0.7857000231742859},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7120000123977661},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5199000239372253},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.49559998512268066},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.4011000096797943},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.3321000039577484}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7857000231742859},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7120000123977661},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6782000064849854},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5199000239372253},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4260999858379364},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37529999017715454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3391999900341034},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810776","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810776","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810776","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2560647685","https://openalex.org/W4366563389","https://openalex.org/W4382998416","https://openalex.org/W4401023434","https://openalex.org/W4403771073","https://openalex.org/W4405595839","https://openalex.org/W4405669265","https://openalex.org/W4407361604"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Vision-Language":[1],"Models":[2],"(LVLMs)":[3],"demonstrate":[4],"impressive":[5],"general-purpose":[6],"capabilities":[7],"but":[8],"often":[9],"suffer":[10],"from":[11,41],"catastrophic":[12],"forgetting":[13],"when":[14],"incorporating":[15],"specialized":[16,77,111],"knowledge.":[17],"To":[18],"address":[19],"this":[20],"plasticity-stability":[21],"dilemma,":[22],"we":[23],"introduce":[24],"Structured":[25],"Dialogue":[26],"Fine-Tuning":[27],"(SDFT),":[28],"a":[29,48],"data-centric":[30],"approach":[31],"that":[32,94],"injects":[33],"domain-specific":[34],"concepts":[35],"while":[36],"preserving":[37],"foundational":[38],"abilities.":[39],"Distinct":[40],"parameter-constrained":[42],"continual":[43],"learning":[44],"methods,":[45],"SDFT":[46,95],"leverages":[47],"three-phase":[49],"dialogue":[50],"structure:":[51],"Foundation":[52],"Preservation":[53],"reinforces":[54],"pre-trained":[55],"visual-linguistic":[56],"alignment":[57],"through":[58],"captioning":[59],"tasks;":[60],"Contrastive":[61],"Disambiguation":[62],"uses":[63],"carefully":[64],"designed":[65],"counterfactual":[66],"examples":[67],"to":[68],"establish":[69],"precise":[70],"semantic":[71],"boundaries;":[72],"and":[73,90,102,114],"Knowledge":[74],"Specialization":[75],"embeds":[76],"information":[78],"via":[79],"chain-of-thought":[80],"reasoning.":[81],"Evaluations":[82],"across":[83],"personalized":[84],"entity":[85],"recognition,":[86],"abstract":[87],"concept":[88],"understanding,":[89],"biomedical":[91],"domains":[92],"show":[93],"significantly":[96],"outperforms":[97],"state-of-the-art":[98],"baselines,":[99],"including":[100],"EWC-LoRA":[101],"O-LoRA.":[103],"The":[104],"results":[105],"confirm":[106],"SDFT\u2019s":[107],"effectiveness":[108],"in":[109],"balancing":[110],"knowledge":[112],"acquisition":[113],"general":[115],"capability":[116],"retention.":[117]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}