{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5ERVCTCIVZNIMHQOLJJV7XLDZT","short_pith_number":"pith:5ERVCTCI","schema_version":"1.0","canonical_sha256":"e923514c48ae5a861e0e5a535fdd63cce8d6c812674f2b18d50654aa2160029f","source":{"kind":"arxiv","id":"2410.19317","version":2},"attestation_state":"computed","paper":{"title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruizhe Chen, Tianxiang Hu, Zhiting Fan, Zuozhu Liu","submitted_at":"2024-10-25T06:06:31Z","abstract_excerpt":"The growing use of large language model (LLM)-based chatbots has raised concerns about fairness. Fairness issues in LLMs can lead to severe consequences, such as bias amplification, discrimination, and harm to marginalized communities. While existing fairness benchmarks mainly focus on single-turn dialogues, multi-turn scenarios, which in fact better reflect real-world conversations, present greater challenges due to conversational complexity and potential bias accumulation. In this paper, we propose a comprehensive fairness benchmark for LLMs in multi-turn dialogue scenarios, \\textbf{FairMT-B"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.19317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-25T06:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"dac2568ef9ed85d56dce814ccd959060d17fd7c87ecba8801eff772ad15abe24","abstract_canon_sha256":"8781d6e7e0218508f80beb8d8d3fc8885e573bde22255e3381f0823f02951752"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:39.995754Z","signature_b64":"CxS0PgHxxH+mUwopQfyp1i2hE+jLpEinx6ryTAeX/wLxOfQhMvdXk5C15qb/jKnhiRWb5VaIATRPmiIkHSSZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e923514c48ae5a861e0e5a535fdd63cce8d6c812674f2b18d50654aa2160029f","last_reissued_at":"2026-07-05T11:18:39.995243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:39.995243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruizhe Chen, Tianxiang Hu, Zhiting Fan, Zuozhu Liu","submitted_at":"2024-10-25T06:06:31Z","abstract_excerpt":"The growing use of large language model (LLM)-based chatbots has raised concerns about fairness. Fairness issues in LLMs can lead to severe consequences, such as bias amplification, discrimination, and harm to marginalized communities. While existing fairness benchmarks mainly focus on single-turn dialogues, multi-turn scenarios, which in fact better reflect real-world conversations, present greater challenges due to conversational complexity and potential bias accumulation. In this paper, we propose a comprehensive fairness benchmark for LLMs in multi-turn dialogue scenarios, \\textbf{FairMT-B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19317","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.19317/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.19317","created_at":"2026-07-05T11:18:39.995311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19317v2","created_at":"2026-07-05T11:18:39.995311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19317","created_at":"2026-07-05T11:18:39.995311+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ERVCTCIVZNI","created_at":"2026-07-05T11:18:39.995311+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ERVCTCIVZNIMHQO","created_at":"2026-07-05T11:18:39.995311+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ERVCTCI","created_at":"2026-07-05T11:18:39.995311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.06120","citing_title":"LLMs Get Lost In Multi-Turn Conversation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT","json":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT.json","graph_json":"https://pith.science/api/pith-number/5ERVCTCIVZNIMHQOLJJV7XLDZT/graph.json","events_json":"https://pith.science/api/pith-number/5ERVCTCIVZNIMHQOLJJV7XLDZT/events.json","paper":"https://pith.science/paper/5ERVCTCI"},"agent_actions":{"view_html":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT","download_json":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT.json","view_paper":"https://pith.science/paper/5ERVCTCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19317&json=true","fetch_graph":"https://pith.science/api/pith-number/5ERVCTCIVZNIMHQOLJJV7XLDZT/graph.json","fetch_events":"https://pith.science/api/pith-number/5ERVCTCIVZNIMHQOLJJV7XLDZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT/action/storage_attestation","attest_author":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT/action/author_attestation","sign_citation":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT/action/citation_signature","submit_replication":"https://pith.science/pith/5ERVCTCIVZNIMHQOLJJV7XLDZT/action/replication_record"}},"created_at":"2026-07-05T11:18:39.995311+00:00","updated_at":"2026-07-05T11:18:39.995311+00:00"}