{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HVQWMY2T6YUQLSEUGNRGXOWAHQ","short_pith_number":"pith:HVQWMY2T","schema_version":"1.0","canonical_sha256":"3d61666353f62905c89433626bbac03c1b14b32127b1ae30c1cb186e3157b2f9","source":{"kind":"arxiv","id":"2406.14952","version":3},"attestation_state":"computed","paper":{"title":"ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Liang, Haiquan Zhao, Jiaan Wang, Kexin Huang, Lingyu Li, Shisong Chen, Shuqi Kong, Tianle Gu, Wang Jian, Yanghua Xiao, Yan Teng, Yingchun Wang, Yixu Wang, Zhixu Li","submitted_at":"2024-06-21T08:03:33Z","abstract_excerpt":"Emotion Support Conversation (ESC) is a crucial application, which aims to reduce human stress, offer emotional guidance, and ultimately enhance human mental and physical well-being. With the advancement of Large Language Models (LLMs), many researchers have employed LLMs as the ESC models. However, the evaluation of these LLM-based ESCs remains uncertain. Inspired by the awesome development of role-playing agents, we propose an ESC Evaluation framework (ESC-Eval), which uses a role-playing agent to interact with ESC models, followed by a manual evaluation of the interactive dialogues. In deta"},"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":"2406.14952","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-21T08:03:33Z","cross_cats_sorted":[],"title_canon_sha256":"f1d41956e4dce8ce8e4ae0e5cf7d043dae77e004262022fd3c5992539769dc2b","abstract_canon_sha256":"d55fe3e958ff51ab014f8ff240c7db5dea167e2658e1fe551572b6ab7f2a22d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:02.404169Z","signature_b64":"U88uUD/rnkt6BFp/cG10vNP9TPboh0/C+OoNvDzS+mkzDcz4uT6FnAXTvrUmdi+m1/OovM3m+OXOdSJHr1ZJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d61666353f62905c89433626bbac03c1b14b32127b1ae30c1cb186e3157b2f9","last_reissued_at":"2026-07-05T09:27:02.403675Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:02.403675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dandan Liang, Haiquan Zhao, Jiaan Wang, Kexin Huang, Lingyu Li, Shisong Chen, Shuqi Kong, Tianle Gu, Wang Jian, Yanghua Xiao, Yan Teng, Yingchun Wang, Yixu Wang, Zhixu Li","submitted_at":"2024-06-21T08:03:33Z","abstract_excerpt":"Emotion Support Conversation (ESC) is a crucial application, which aims to reduce human stress, offer emotional guidance, and ultimately enhance human mental and physical well-being. With the advancement of Large Language Models (LLMs), many researchers have employed LLMs as the ESC models. However, the evaluation of these LLM-based ESCs remains uncertain. Inspired by the awesome development of role-playing agents, we propose an ESC Evaluation framework (ESC-Eval), which uses a role-playing agent to interact with ESC models, followed by a manual evaluation of the interactive dialogues. In deta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14952","kind":"arxiv","version":3},"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/2406.14952/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":"2406.14952","created_at":"2026-07-05T09:27:02.403734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14952v3","created_at":"2026-07-05T09:27:02.403734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14952","created_at":"2026-07-05T09:27:02.403734+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVQWMY2T6YUQ","created_at":"2026-07-05T09:27:02.403734+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVQWMY2T6YUQLSEU","created_at":"2026-07-05T09:27:02.403734+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVQWMY2T","created_at":"2026-07-05T09:27:02.403734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ","json":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ.json","graph_json":"https://pith.science/api/pith-number/HVQWMY2T6YUQLSEUGNRGXOWAHQ/graph.json","events_json":"https://pith.science/api/pith-number/HVQWMY2T6YUQLSEUGNRGXOWAHQ/events.json","paper":"https://pith.science/paper/HVQWMY2T"},"agent_actions":{"view_html":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ","download_json":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ.json","view_paper":"https://pith.science/paper/HVQWMY2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14952&json=true","fetch_graph":"https://pith.science/api/pith-number/HVQWMY2T6YUQLSEUGNRGXOWAHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/HVQWMY2T6YUQLSEUGNRGXOWAHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ/action/storage_attestation","attest_author":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ/action/author_attestation","sign_citation":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ/action/citation_signature","submit_replication":"https://pith.science/pith/HVQWMY2T6YUQLSEUGNRGXOWAHQ/action/replication_record"}},"created_at":"2026-07-05T09:27:02.403734+00:00","updated_at":"2026-07-05T09:27:02.403734+00:00"}