{"id":"https://openalex.org/W7128683711","doi":"https://doi.org/10.48550/arxiv.2602.10386","title":"Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models","display_name":"Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128683711","doi":"https://doi.org/10.48550/arxiv.2602.10386"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.10386","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","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":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125735746","display_name":"Angelo Zangari","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zangari, Angelo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046492119","display_name":"Peyman Baghershahi","orcid":"https://orcid.org/0000-0001-9792-1807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baghershahi, Peyman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125709122","display_name":"Sourav Medya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Medya, Sourav","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5125735746"],"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.5473999977111816,"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":0.5473999977111816,"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":0.16459999978542328,"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":0.16060000658035278,"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/graph","display_name":"Graph","score":0.5827000141143799},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3237000107765198},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3118000030517578},{"id":"https://openalex.org/keywords/graph-property","display_name":"Graph property","score":0.3086000084877014},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.296999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258999943733215},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5827000141143799},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4943999946117401},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C64339825","wikidata":"https://www.wikidata.org/wiki/Q722659","display_name":"Graph property","level":5,"score":0.3086000084877014},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C146380142","wikidata":"https://www.wikidata.org/wiki/Q1137726","display_name":"Directed graph","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2590000033378601}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.10386","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.10386","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.10386","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":"pmh:doi:10.48550/arxiv.2602.10386","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7278211116790771,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Graph":[0],"problems":[1,50],"are":[2],"fundamentally":[3],"challenging":[4],"for":[5,61],"large":[6],"language":[7,71],"models":[8],"(LLMs).":[9],"While":[10],"LLMs":[11,43,111],"excel":[12],"at":[13],"processing":[14],"unstructured":[15],"text,":[16],"graph":[17,49,66,123,152,159],"tasks":[18,124,153],"require":[19,155],"reasoning":[20,156],"over":[21,157],"explicit":[22],"structure,":[23],"permutation":[24],"invariance,":[25],"and":[26,84,102,121,135,142],"computationally":[27],"complex":[28],"relationships,":[29],"creating":[30],"a":[31,56,77],"mismatch":[32],"with":[33],"the":[34,126],"representations":[35],"of":[36,79],"text-based":[37],"models.":[38],"Our":[39,73],"work":[40],"investigates":[41],"how":[42],"can":[44],"be":[45,106],"effectively":[46,108],"applied":[47],"to":[48,87],"despite":[51],"these":[52],"barriers.":[53],"We":[54],"introduce":[55],"human-interpretable":[57,103],"structural":[58],"encoding":[59],"strategy":[60],"graph-to-text":[62],"translation":[63],"that":[64,99,154],"injects":[65],"structure":[67],"directly":[68],"into":[69],"natural":[70],"prompts.":[72],"method":[74,131,146],"involves":[75],"computing":[76],"variant":[78],"Weisfeiler-Lehman":[80],"(WL)":[81],"similarity":[82],"classes":[83],"maps":[85],"them":[86],"human-like":[88],"color":[89],"tokens":[90],"rather":[91],"than":[92,112],"numeric":[93],"labels.":[94],"The":[95],"key":[96],"insight":[97],"is":[98],"semantically":[100],"meaningful":[101],"cues":[104],"may":[105],"more":[107],"processed":[109],"by":[110,129],"opaque":[113],"symbolic":[114],"encoding.":[115],"Experimental":[116],"results":[117],"on":[118,132,151],"multiple":[119],"algorithmic":[120],"predictive":[122],"show":[125],"considerable":[127],"improvements":[128],"our":[130,145],"both":[133,140],"synthetic":[134],"real-world":[136],"datasets.":[137],"By":[138],"capturing":[139],"local":[141],"global-range":[143],"dependencies,":[144],"enhances":[147],"LLM":[148],"performance":[149],"especially":[150],"global":[158],"structure.":[160]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-13T00:00:00"}