{"id":"https://openalex.org/W7166810477","doi":"https://doi.org/10.18653/v1/2026.findings-acl.89","title":"TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering","display_name":"TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question Answering","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166810477","doi":"https://doi.org/10.18653/v1/2026.findings-acl.89"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.89","pdf_url":"https://aclanthology.org/2026.findings-acl.89.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.89.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139784246","display_name":"Yingxu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingxu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139766670","display_name":"Jiaxin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaxin Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139826322","display_name":"Mengzhu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mengzhu Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139793200","display_name":"Nan Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nan Yin","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80072348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1830","last_page":"1851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.6255999803543091,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.6255999803543091,"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":0.16680000722408295,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.06430000066757202,"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/question-answering","display_name":"Question answering","score":0.6305999755859375},{"id":"https://openalex.org/keywords/experiential-knowledge","display_name":"Experiential knowledge","score":0.4781999886035919},{"id":"https://openalex.org/keywords/experiential-learning","display_name":"Experiential learning","score":0.4406999945640564},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.42590001225471497},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4153999984264374},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3431999981403351},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.3377000093460083}],"concepts":[{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6305999755859375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5795000195503235},{"id":"https://openalex.org/C123353603","wikidata":"https://www.wikidata.org/wiki/Q5421070","display_name":"Experiential knowledge","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3488999903202057},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C3019144022","wikidata":"https://www.wikidata.org/wiki/Q4124998","display_name":"Questions and answers","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.89","pdf_url":"https://aclanthology.org/2026.findings-acl.89.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.89","pdf_url":"https://aclanthology.org/2026.findings-acl.89.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166810477.pdf","grobid_xml":"https://content.openalex.org/works/W7166810477.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-hop":[0],"Knowledge":[1],"Graph":[2],"Question":[3],"Answering":[4],"(KGQA)":[5],"requires":[6],"coherent":[7],"reasoning":[8,18,33,58,76],"across":[9],"relational":[10],"paths,":[11],"yet":[12],"existing":[13],"methods":[14],"often":[15],"treat":[16],"each":[17],"step":[19],"independently":[20],"and":[21,34,47,67],"fail":[22],"to":[23,31,63,82,110],"effectively":[24],"leverage":[25],"experience":[26],"from":[27],"prior":[28,61,88],"explorations,":[29],"leading":[30],"fragmented":[32],"redundant":[35],"exploration.To":[36],"address":[37],"these":[38],"challenges,":[39],"we":[40],"propose":[41],"Trajectoryaware":[42],"Reasoning":[43],"with":[44,59,107],"Adaptive":[45],"Context":[46],"Exploration":[48],"priors":[49,94,109],"(TRACE),":[50],"an":[51],"experiential":[52,93],"framework":[53],"that":[54,95,122],"unifies":[55],"LLM-driven":[56],"contextual":[57,105],"exploration":[60,89,98,108],"integration":[62],"enhance":[64],"the":[65],"coherence":[66],"robustness":[68],"of":[69],"multihop":[70],"KGQA.Specifically,":[71],"TRACE":[72,123],"dynamically":[73],"translates":[74],"evolving":[75],"paths":[77],"into":[78,91],"natural":[79],"language":[80],"narratives":[81,106],"maintain":[83],"semantic":[84],"continuity,":[85],"while":[86],"abstracting":[87],"trajectories":[90],"reusable":[92],"capture":[96],"recurring":[97],"patterns.A":[99],"dualfeedback":[100],"re-ranking":[101],"mechanism":[102],"further":[103],"integrates":[104],"guide":[111],"relation":[112],"selection":[113],"during":[114],"reasoning.Extensive":[115],"experiments":[116],"on":[117],"multiple":[118],"KGQA":[119],"benchmarks":[120],"demonstrate":[121],"consistently":[124],"outperforms":[125],"state-of-the-art":[126],"baselines.":[127]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}