{"id":"https://openalex.org/W4411113101","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.186","title":"Challenges in Trustworthy Human Evaluation of Chatbots","display_name":"Challenges in Trustworthy Human Evaluation of Chatbots","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411113101","doi":"https://doi.org/10.18653/v1/2025.findings-naacl.186"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-naacl.186","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.186","pdf_url":"https://aclanthology.org/2025.findings-naacl.186.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: NAACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-naacl.186.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114986005","display_name":"Wenting Zhao","orcid":"https://orcid.org/0000-0003-0313-5149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenting Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062546146","display_name":"Alexander M. Rush","orcid":"https://orcid.org/0000-0002-9900-1606"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander M Rush","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020127239","display_name":"Tanya Goyal","orcid":"https://orcid.org/0009-0009-6429-278X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanya Goyal","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":1.4143,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78752235,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3359","last_page":"3365"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.9593999981880188,"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/T12128","display_name":"AI in Service Interactions","score":0.9593999981880188,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9067000150680542,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.7392726540565491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6804236173629761},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3701671361923218},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.22596243023872375}],"concepts":[{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.7392726540565491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804236173629761},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3701671361923218},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22596243023872375}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-naacl.186","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.186","pdf_url":"https://aclanthology.org/2025.findings-naacl.186.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: NAACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-naacl.186","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-naacl.186","pdf_url":"https://aclanthology.org/2025.findings-naacl.186.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: NAACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5988268520","display_name":"CAREER: Data-Driven Document Generation","funder_award_id":"2037519","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411113101.pdf","grobid_xml":"https://content.openalex.org/works/W4411113101.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2022710553"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2076536433","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W90316445","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Open":[0],"community-driven":[1],"platforms":[2],"like":[3],"Chatbot":[4],"Arena":[5],"that":[6,49,70],"collect":[7,40],"user":[8],"preference":[9],"data":[10],"from":[11,43],"site":[12],"visitors":[13,80],"have":[14],"gained":[15],"a":[16,98],"reputation":[17],"as":[18],"one":[19],"of":[20,52,63,73,97],"the":[21,61,95,104],"most":[22],"trustworthy":[23],"publicly":[24],"available":[25],"benchmarks":[26],"for":[27],"LLM":[28],"performance.While":[29],"now":[30],"standard,":[31],"it":[32],"is":[33],"tricky":[34],"to":[35,39,84,93,109],"implement":[36],"effective":[37],"guardrails":[38],"high-quality":[41,117],"annotations":[42],"humans.In":[44],"this":[45],"paper,":[46],"we":[47,68],"demonstrate":[48],"three":[50],"sources":[51],"bad":[53],"annotations,":[54],"both":[55],"malicious":[56],"and":[57],"otherwise,":[58],"can":[59,102],"corrupt":[60],"reliability":[62],"open":[64,113],"leaderboard":[65],"rankings.In":[66],"particular,":[67],"show":[69],"only":[71],"10%":[72],"poor":[74],"quality":[75],"votes":[76],"by":[77,107],"apathetic":[78],"(site":[79],"not":[81],"appropriately":[82],"incentivized":[83],"give":[85],"correct":[86],"votes)":[87],"or":[88],"adversarial":[89],"(bad":[90],"actors":[91],"seeking":[92],"inflate":[94],"ranking":[96],"target":[99],"model)":[100],"users":[101],"change":[103],"models'":[105],"rankings":[106],"up":[108],"5":[110],"places.We":[111],"discuss":[112],"challenges":[114],"in":[115],"ensuring":[116],"human":[118],"annotations.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}