{"id":"https://openalex.org/W4414455665","doi":"https://doi.org/10.18653/v1/2026.findings-acl.586","title":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","display_name":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414455665","doi":"https://doi.org/10.18653/v1/2026.findings-acl.586"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.586","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.586","pdf_url":"https://aclanthology.org/2026.findings-acl.586.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.586.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101721790","display_name":"Yizhuo Zhang","orcid":"https://orcid.org/0009-0002-9496-1007"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizhuo Zhang","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111050761","display_name":"Heng Wang","orcid":"https://orcid.org/0009-0008-1395-976X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heng Wang","raw_affiliation_strings":["University of Illinois Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039166924","display_name":"Shangbin Feng","orcid":"https://orcid.org/0000-0002-4133-1987"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shangbin Feng","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047674498","display_name":"Zhaoxuan Tan","orcid":"https://orcid.org/0000-0001-8230-6238"},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaoxuan Tan","raw_affiliation_strings":["University of Notre Dame"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101612101","display_name":"Xinyun Liu","orcid":"https://orcid.org/0000-0002-4275-7197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyun Liu","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062910836","display_name":"Yulia Tsvetkov","orcid":"https://orcid.org/0000-0002-4634-7128"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulia Tsvetkov","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.00674549,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12070","last_page":"12091"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.982699990272522,"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":0.982699990272522,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9282000064849854,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9103999733924866,"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/synthetic-data","display_name":"Synthetic data","score":0.6582000255584717},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6086999773979187},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.3686999976634979},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.2976999878883362},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.28139999508857727}],"concepts":[{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6582000255584717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6134999990463257},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6086999773979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4984999895095825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4584999978542328},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.586","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.586","pdf_url":"https://aclanthology.org/2026.findings-acl.586.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"},{"id":"pmh:oai:arXiv.org:2506.00845","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00845","pdf_url":"https://arxiv.org/pdf/2506.00845","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,"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.2506.00845","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.00845","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.586","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.586","pdf_url":"https://aclanthology.org/2026.findings-acl.586.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":[{"id":"https://openalex.org/G6430229357","display_name":null,"funder_award_id":"HR00112520300","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414455665.pdf","grobid_xml":"https://content.openalex.org/works/W4414455665.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Previous":[0],"research":[1],"has":[2],"sought":[3],"to":[4,21,44,55,161],"enhance":[5],"the":[6,95],"graph":[7,17,27,42,49,60,75,98,124,143],"reasoning":[8,99],"capabilities":[9],"of":[10,59,78,172],"LLMs":[11,23,33,93,118,120],"by":[12],"supervised":[13],"fine-tuning":[14],"on":[15,103,122,132,165,186,191],"synthetic":[16,41,65,74,104,123,135,187],"data.While":[18],"these":[19],"led":[20],"specialized":[22],"better":[24],"at":[25],"solving":[26],"algorithm":[28],"problems,":[29],"we":[30,37,53,86],"don't":[31],"need":[32,38],"for":[34,73],"shortest":[35],"path:":[36],"generalization":[39],"from":[40],"data":[43,188],"realworld":[45],"tasks":[46,136,140],"with":[47,61,64,141,168],"implicit":[48,142],"structures.In":[50],"this":[51],"work,":[52],"propose":[54],"unlock":[56],"generalizable":[57],"learning":[58],"post-training":[62,89,107,157,206],"alignment":[63,90,108,158],"data.We":[66,105,125],"first":[67],"design":[68],"solutionbased":[69],"and":[70,100,113,119,137,151,194,196],"process-based":[71,180],"rewards":[72,181,185],"problems:":[76],"instead":[77],"rigid":[79],"memorizing":[80],"response":[81],"patterns":[82],"in":[83],"direct":[84],"fine-tuning,":[85],"posit":[87],"that":[88,155,179],"would":[91],"help":[92],"grasp":[94],"essentials":[96],"underlying":[97],"alleviate":[101],"overfitting":[102],"employ":[106],"algorithms":[109],"such":[110,145],"as":[111,146],"GRPO":[112],"DPO,":[114],"aligning":[115],"both":[116,133],"off-theshelf":[117],"fine-tuned":[121],"then":[126],"compare":[127],"them":[128],"against":[129],"existing":[130],"settings":[131],"in-domain":[134],"out-of-domain":[138],"real-world":[139,192],"structures":[144],"multi-hop":[147],"QA,":[148],"structured":[149],"planning,":[150],"more.Extensive":[152],"experiments":[153],"demonstrate":[154],"our":[156],"recipe":[159],"leads":[160],"statistically":[162],"significant":[163],"improvement":[164],"5":[166],"datasets,":[167],"an":[169],"average":[170],"gain":[171],"12.9%":[173],"over":[174],"baseline":[175],"settings.Further":[176],"analysis":[177],"reveals":[178],"consistently":[182],"outperform":[183],"solution-based":[184],"but":[189],"not":[190],"tasks,":[193],"compositionality":[195],"explainable":[197],"intermediate":[198],"steps":[199],"remains":[200],"a":[201],"critical":[202],"challenge":[203],"even":[204],"after":[205],"alignment.":[207],"1and":[208],"Bryan":[209],"Hooi.2024b.G-retriever:":[210]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}