{"id":"https://openalex.org/W7160196824","doi":"https://doi.org/10.48550/arxiv.2605.00434","title":"LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations","display_name":"LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160196824","doi":"https://doi.org/10.48550/arxiv.2605.00434"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.00434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00434","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.00434","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054409996","display_name":"Huangbiao Xu","orcid":"https://orcid.org/0000-0002-3717-8713"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xu, Huangbiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101551771","display_name":"Huanqi Wu","orcid":"https://orcid.org/0009-0008-4518-3273"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Huanqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025474158","display_name":"Xiao Ke","orcid":"https://orcid.org/0000-0001-5895-2766"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135216683","display_name":"Yuxin Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054409996"],"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":0.7437999844551086,"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":0.7437999844551086,"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":0.08900000154972076,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.03519999980926514,"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/inference","display_name":"Inference","score":0.6190000176429749},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5278000235557556},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.3882000148296356},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.38580000400543213},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.37790000438690186},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.353300005197525},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3513999879360199},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3499000072479248},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.34290000796318054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809000015258789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6854000091552734},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6190000176429749},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.544700026512146},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.3882000148296356},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35920000076293945},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.353300005197525},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.25529998540878296},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.00434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00434","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.00434","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.00434","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-world":[0],"multimodal":[1,151],"learning":[2],"is":[3,154],"often":[4],"hindered":[5],"by":[6],"missing":[7],"modalities.":[8],"While":[9],"Incomplete":[10,65],"Multimodal":[11,66],"Learning":[12],"(IML)":[13],"has":[14],"gained":[15],"traction,":[16],"existing":[17],"methods":[18],"typically":[19],"rely":[20],"on":[21,53,126,141],"the":[22,40,83],"unrealistic":[23],"assumption":[24],"of":[25,44,58,87],"full-modal":[26],"availability":[27],"during":[28],"training":[29,143],"to":[30,100,119],"provide":[31],"reconstruction":[32],"supervision":[33],"or":[34],"cross-modal":[35],"priors.":[36],"This":[37],"paper":[38],"tackles":[39],"more":[41],"challenging":[42],"setting":[43],"IML":[45],"under":[46],"training-time":[47],"incomplete":[48],"observations,":[49],"which":[50],"precludes":[51],"reliance":[52],"a":[54,69,76,115,146],"``God's":[55],"eye":[56],"view''":[57],"complete":[59,142],"data.":[60],"We":[61],"propose":[62],"LIMSSR":[63,81,134],"(LLM-Driven":[64],"Sequence-to-Score":[67],"Reasoning),":[68],"framework":[70],"that":[71,133],"reformulates":[72],"this":[73],"challenge":[74],"as":[75],"conditional":[77],"sequence":[78],"reasoning":[79,85],"task.":[80],"leverages":[82],"semantic":[84],"capabilities":[86],"Large":[88],"Language":[89],"Models":[90],"via":[91],"Prompt-Guided":[92],"Context-Aware":[93],"Modality":[94],"Imputation":[95],"and":[96],"Multidimensional":[97],"Representation":[98],"Fusion":[99],"infer":[101],"latent":[102],"semantics":[103],"from":[104],"available":[105,155],"contexts":[106],"without":[107,139],"direct":[108],"reconstruction.":[109],"To":[110],"mitigate":[111],"hallucinations,":[112],"we":[113],"introduce":[114],"Mask-Aware":[116],"Dual-Path":[117],"Aggregation":[118],"dynamically":[120],"calibrate":[121],"inference":[122],"uncertainty.":[123],"Extensive":[124],"experiments":[125],"three":[127],"Action":[128],"Quality":[129],"Assessment":[130],"datasets":[131],"demonstrate":[132],"significantly":[135],"outperforms":[136],"state-of-the-art":[137],"baselines":[138],"relying":[140],"data,":[144],"establishing":[145],"new":[147],"paradigm":[148],"for":[149],"data-efficient":[150],"learning.":[152],"Code":[153],"at":[156],"https://github.com/XuHuangbiao/LIMSSR.":[157]},"counts_by_year":[],"updated_date":"2026-05-05T06:12:25.323381","created_date":"2026-05-05T00:00:00"}