{"id":"https://openalex.org/W7166809780","doi":"https://doi.org/10.18653/v1/2026.gem-main.38","title":"MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models","display_name":"MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166809780","doi":"https://doi.org/10.18653/v1/2026.gem-main.38"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.gem-main.38","doi":"https://doi.org/10.18653/v1/2026.gem-main.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.38","pdf_url":"https://aclanthology.org/2026.gem-main.38.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.gem-main.38.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121237668","display_name":"Weixin Liu","orcid":"https://orcid.org/0009-0008-9082-1000","observed_orcids":["https://orcid.org/0009-0008-9082-1000"]},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weixin Liu","raw_affiliation_strings":["Vanderbilt University , Nashville , TN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University , Nashville , TN , USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053675776","display_name":"Congning Ni","orcid":"https://orcid.org/0000-0001-6950-6948","observed_orcids":["https://orcid.org/0000-0001-6950-6948"]},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Congning Ni","raw_affiliation_strings":["Vanderbilt University Medical Center , Nashville , TN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University Medical Center , Nashville , TN , USA","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002150831","display_name":"Shelagh A. Mulvaney","orcid":"https://orcid.org/0000-0003-1622-6744","observed_orcids":["https://orcid.org/0000-0003-1622-6744"]},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shelagh A. Mulvaney","raw_affiliation_strings":["Vanderbilt University , Nashville , TN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University , Nashville , TN , USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136371037","display_name":"Susannah L. Rose","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susannah L. Rose","raw_affiliation_strings":["Vanderbilt University Medical Center , Nashville , TN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University Medical Center , Nashville , TN , USA","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087192873","display_name":"Murat Kantarc\u0131o\u011flu","orcid":"https://orcid.org/0000-0001-9795-9063","observed_orcids":["https://orcid.org/0000-0001-9795-9063"]},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murat Kantarcioglu","raw_affiliation_strings":["Virginia Tech , Blacksburg , VA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech , Blacksburg , VA , USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090647314","display_name":"Bradley Malin","orcid":"https://orcid.org/0000-0003-3040-5175","observed_orcids":["https://orcid.org/0000-0003-3040-5175"]},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bradley A. Malin","raw_affiliation_strings":["Vanderbilt University , Nashville , TN , USA","Vanderbilt University Medical Center , Nashville , TN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University , Nashville , TN , USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University Medical Center , Nashville , TN , USA","institution_ids":["https://openalex.org/I901861585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136474161","display_name":"Zhijun Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]},{"id":"https://openalex.org/I901861585","display_name":"Vanderbilt University Medical Center","ror":"https://ror.org/05dq2gs74","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210162197","https://openalex.org/I901861585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhijun Yin","raw_affiliation_strings":["Vanderbilt University , Nashville , TN , USA","Vanderbilt University Medical Center , Nashville , TN , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vanderbilt University , Nashville , TN , USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Vanderbilt University Medical Center , Nashville , TN , USA","institution_ids":["https://openalex.org/I901861585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.6106,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97164619,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"393","last_page":"409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3991999924182892,"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/T10028","display_name":"Topic Modeling","score":0.3991999924182892,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.23600000143051147,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.20399999618530273,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mental-health-knowledge","display_name":"mental health knowledge","score":0.7369999885559082},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9120000004768372},{"id":"https://openalex.org/keywords/relation-prediction","display_name":"relation prediction","score":0.8610000014305115},{"id":"https://openalex.org/keywords/response-validity","display_name":"response validity","score":0.6169999837875366},{"id":"https://openalex.org/keywords/clinical-safety","display_name":"clinical safety","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5514000058174133},{"id":"https://openalex.org/C134362201","wikidata":"https://www.wikidata.org/wiki/Q317309","display_name":"Mental health","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5076000094413757},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.4521999955177307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38589999079704285},{"id":"https://openalex.org/C2982912361","wikidata":"https://www.wikidata.org/wiki/Q1851867","display_name":"Mental model","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2776291881","wikidata":"https://www.wikidata.org/wiki/Q6423378","display_name":"Knowledge level","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C509550671","wikidata":"https://www.wikidata.org/wiki/Q126945","display_name":"Medical education","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.gem-main.38","doi":"https://doi.org/10.18653/v1/2026.gem-main.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.38","pdf_url":"https://aclanthology.org/2026.gem-main.38.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.gem-main.38","doi":"https://doi.org/10.18653/v1/2026.gem-main.38","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.38","pdf_url":"https://aclanthology.org/2026.gem-main.38.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.428600013256073,"id":"https://metadata.un.org/sdg/3"}],"sustainable_development_goals_aurora":[{"display_name":"Quality education","score":0.6059674024581909,"id":"https://metadata.un.org/sdg/4"}],"study_designs":[],"awards":[],"funders":[{"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/W7166809780.pdf","grobid_xml":"https://content.openalex.org/works/W7166809780.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417291884","https://openalex.org/W7140101052","https://openalex.org/W7204449673","https://openalex.org/W7129067450","https://openalex.org/W4414801979","https://openalex.org/W4405468762","https://openalex.org/W4388748472","https://openalex.org/W7131883710","https://openalex.org/W4414920049","https://openalex.org/W7133183541"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,80,108],"(LLMs)":[3],"are":[4],"increasingly":[5],"used":[6],"in":[7,132],"the":[8,89,126],"mental":[9],"health":[10],"domain,":[11],"yet":[12,93],"it":[13,28],"remains":[14],"unclear":[15],"how":[16,24],"well":[17],"they":[18,26,94],"capture":[19],"related":[20],"biomedical":[21],"knowledge":[22],"and":[23,49,57,65,87,100],"reliably":[25],"apply":[27],"to":[29],"clinically":[30],"salient":[31],"structured":[32],"judgments.Here,":[33],"we":[34],"present":[35],"a":[36,75,143,150,157],"knowledgegraph":[37],"(KG)-grounded":[38],"benchmark":[39,52],"for":[40,112],"assessing":[41],"LLMs":[42,73],"on":[43,84,88],"mental-health":[44],"entity":[45,85],"recognition,":[46],"relation":[47,98],"judgment,":[48],"two-hop":[50,101],"reasoning.The":[51],"is":[53],"derived":[54],"from":[55],"PrimeKG":[56,148],"comprises":[58],"nine":[59],"task":[60],"families":[61],"with":[62,97,142],"KGsupported":[63],"answers":[64],"controlled":[66],"negative":[67],"options.Experiments":[68],"across":[69],"15":[70],"closed-and":[71],"opensource":[72],"reveal":[74],"persistent":[76],"recognitionto-judgment":[77],"gap:":[78],"leading":[79],"achieve":[81],"nearceiling":[82],"performance":[83,111,120],"typing":[86],"small":[90],"relation-typing":[91],"subset,":[92],"still":[95],"struggle":[96],"prediction":[99],"reasoning.Additionally,":[102],"short":[103],"KG-derived":[104],"snippets":[105],"benefit":[106],"some":[107],"but":[109],"degrade":[110],"others.Moreover,":[113],"output-format":[114],"reliability":[115],"can":[116],"substantially":[117],"influence":[118],"measured":[119],"under":[121,149],"constrained":[122,151],"multiple-choice":[123,152],"settings,":[124],"highlighting":[125],"critical":[127],"role":[128],"of":[129,147,160],"response":[130],"validity":[131],"benchmark-based":[133],"evaluation.MH-GraphBench":[134],"should":[135],"therefore":[136],"be":[137],"interpreted":[138],"as":[139,156],"evaluating":[140],"agreement":[141],"curated":[144],"mentalhealth":[145],"slice":[146],"interface,":[153],"rather":[154],"than":[155],"direct":[158],"assessment":[159],"real-world":[161],"clinical":[162],"safety.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-07-02T00:00:00"}
