{"id":"https://openalex.org/W7203684710","doi":"https://doi.org/10.48550/arxiv.2608.14622","title":"A Human-Centred Approach to Benchmarking LLMs for Parenting Advice","display_name":"A Human-Centred Approach to Benchmarking LLMs for Parenting Advice","publication_year":2026,"publication_date":"2026-07-14","ids":{"openalex":"https://openalex.org/W7203684710","doi":"https://doi.org/10.48550/arxiv.2608.14622"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.14622","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14622","pdf_url":"https://arxiv.org/pdf/2608.14622","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14622","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110691197","display_name":"Yunke Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhao, Yunke","raw_affiliation_strings":["Department of Computer Science , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013752087","display_name":"Isobel Voysey","orcid":"https://orcid.org/0000-0002-5399-0824","observed_orcids":["https://orcid.org/0000-0002-5399-0824"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Voysey, Isobel","raw_affiliation_strings":["Department of Computer Science , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005065579","display_name":"Alastair C. van Heerden","orcid":"https://orcid.org/0000-0003-2530-6885","observed_orcids":["https://orcid.org/0000-0003-2530-6885"]},"institutions":[{"id":"https://openalex.org/I4405269462","display_name":"Morrison Trust","ror":"https://ror.org/048czwg46","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4405269462"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"van Heerden, Alastair","raw_affiliation_strings":["Tandem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tandem","institution_ids":["https://openalex.org/I4405269462"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147386495","display_name":"Rob Hughes","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405269462","display_name":"Morrison Trust","ror":"https://ror.org/048czwg46","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4405269462"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hughes, Rob","raw_affiliation_strings":["Tandem"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tandem","institution_ids":["https://openalex.org/I4405269462"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100744623","display_name":"Jun Zhao","orcid":"https://orcid.org/0000-0001-6935-9028","observed_orcids":["https://orcid.org/0000-0001-6935-9028","https://orcid.org/0000-0002-3539-2249","https://orcid.org/0000-0001-9954-9471"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhao, Jun","raw_affiliation_strings":["Department of Computer Science , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.44119998812675476,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.44119998812675476,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.14249999821186066,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.050700001418590546,"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/large-language-models","display_name":"large language models","score":0.9779999852180481},{"id":"https://openalex.org/keywords/parenting-advice","display_name":"parenting advice","score":0.8629999756813049},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.7820000052452087},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.9570000171661377},{"id":"https://openalex.org/keywords/parenting-styles","display_name":"parenting styles","score":0.5440000295639038}],"concepts":[{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.9013000130653381},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.618399977684021},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.541100025177002},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4632999897003174},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.414900004863739},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.4066999852657318},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.35370001196861267},{"id":"https://openalex.org/C75630572","wikidata":"https://www.wikidata.org/wiki/Q538904","display_name":"Applied psychology","level":1,"score":0.3248000144958496},{"id":"https://openalex.org/C2781029818","wikidata":"https://www.wikidata.org/wiki/Q2368856","display_name":"Curry","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C166735990","wikidata":"https://www.wikidata.org/wiki/Q1750812","display_name":"Human factors and ergonomics","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14622","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14622","pdf_url":"https://arxiv.org/pdf/2608.14622","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.14622","doi":"https://doi.org/10.48550/arxiv.2608.14622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14622","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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.14622","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14622","pdf_url":"https://arxiv.org/pdf/2608.14622","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,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203684710.pdf","grobid_xml":"https://content.openalex.org/works/W7203684710.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4409363989","https://openalex.org/W7203980511","https://openalex.org/W4403826361","https://openalex.org/W7128528452","https://openalex.org/W7151776206","https://openalex.org/W4415456690","https://openalex.org/W6930876559","https://openalex.org/W4385571232","https://openalex.org/W4396570275","https://openalex.org/W7202185450"],"abstract_inverted_index":{"People":[0],"are":[1],"increasingly":[2],"using":[3,67],"large":[4],"language":[5,88],"models":[6,81],"(LLMs)":[7],"to":[8,35],"seek":[9],"advice,":[10],"including":[11],"for":[12,115,118],"parenting.":[13,109],"Parenting":[14],"is":[15],"a":[16,45],"critical":[17],"and":[18,38,65,87,99,122],"socially":[19],"sensitive":[20],"domain.":[21],"Thus,":[22],"evaluating":[23,103],"advice":[24,105,128],"provided":[25],"by":[26,49],"LLMs":[27,56,117],"requires":[28],"indicators":[29],"beyond":[30],"aggregated":[31],"information":[32],"quality":[33],"benchmarks":[34],"consider":[36],"relational":[37],"behavioural":[39],"elements":[40],"of":[41,95,125],"the":[42,93,123],"responses.":[43,90],"With":[44],"multi-dimensional":[46],"rubric":[47,78],"created":[48],"parenting":[50,59,85,127],"experts,":[51],"this":[52],"paper":[53],"evaluates":[54],"15":[55],"across":[57],"100":[58],"scenarios":[60],"in":[61,102,106],"2":[62],"languages":[63],"(English":[64],"Chinese),":[66],"an":[68],"LLM-as-a-judge":[69],"method.":[70],"Results":[71],"show":[72],"that":[73],"aggregate":[74],"scores":[75],"can":[76],"hide":[77],"item-specific":[79],"weaknesses,":[80],"implicitly":[82],"encourage":[83],"different":[84],"styles,":[86],"influences":[89],"We":[91],"highlight":[92],"importance":[94],"evaluation":[96],"output":[97],"auditability":[98],"challenges":[100],"involved":[101],"LLM-generated":[104],"domains":[107],"like":[108],"Our":[110],"findings":[111],"provide":[112],"important":[113],"insights":[114],"selecting":[116],"direct":[119],"user":[120],"engagement":[121],"development":[124],"user-facing":[126],"applications.":[129]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-08-19T00:00:00"}
