{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EACVKCNYYVHWGARNL5JQHLZOUN","short_pith_number":"pith:EACVKCNY","schema_version":"1.0","canonical_sha256":"20055509b8c54f63022d5f5303af2ea3770b548d3237d55a79f2d7d4e115ff97","source":{"kind":"arxiv","id":"2305.13711","version":1},"attestation_state":"computed","paper":{"title":"LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yen-Ting Lin, Yun-Nung Chen","submitted_at":"2023-05-23T05:57:09Z","abstract_excerpt":"We propose LLM-Eval, a unified multi-dimensional automatic evaluation method for open-domain conversations with large language models (LLMs). Existing evaluation methods often rely on human annotations, ground-truth responses, or multiple LLM prompts, which can be expensive and time-consuming. To address these issues, we design a single prompt-based evaluation method that leverages a unified evaluation schema to cover multiple dimensions of conversation quality in a single model call. We extensively evaluate the performance of LLM-Eval on various benchmark datasets, demonstrating its effective"},"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":"2305.13711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T05:57:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"87bb23a1c2d723e05960498bfc7494099654e91dcaf01790d335e4108fc8065e","abstract_canon_sha256":"555c5a3f933fa0e268011c817409d47a2f2b47637a4c338ac3dd965d8b16e4bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:56.518679Z","signature_b64":"Vw1Xsgd9mSTezp5fQW7s6LWmIe+lHyc8NOhPg1q+uQbQRiNmVnZDvr9v36vSiJlGERU3irSUNu/rFokbYiveBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20055509b8c54f63022d5f5303af2ea3770b548d3237d55a79f2d7d4e115ff97","last_reissued_at":"2026-07-05T06:12:56.518253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:56.518253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yen-Ting Lin, Yun-Nung Chen","submitted_at":"2023-05-23T05:57:09Z","abstract_excerpt":"We propose LLM-Eval, a unified multi-dimensional automatic evaluation method for open-domain conversations with large language models (LLMs). Existing evaluation methods often rely on human annotations, ground-truth responses, or multiple LLM prompts, which can be expensive and time-consuming. To address these issues, we design a single prompt-based evaluation method that leverages a unified evaluation schema to cover multiple dimensions of conversation quality in a single model call. We extensively evaluate the performance of LLM-Eval on various benchmark datasets, demonstrating its effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13711","kind":"arxiv","version":1},"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/2305.13711/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":"2305.13711","created_at":"2026-07-05T06:12:56.518308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13711v1","created_at":"2026-07-05T06:12:56.518308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13711","created_at":"2026-07-05T06:12:56.518308+00:00"},{"alias_kind":"pith_short_12","alias_value":"EACVKCNYYVHW","created_at":"2026-07-05T06:12:56.518308+00:00"},{"alias_kind":"pith_short_16","alias_value":"EACVKCNYYVHWGARN","created_at":"2026-07-05T06:12:56.518308+00:00"},{"alias_kind":"pith_short_8","alias_value":"EACVKCNY","created_at":"2026-07-05T06:12:56.518308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30556","citing_title":"Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00093","citing_title":"Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2511.10287","citing_title":"OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06608","citing_title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19773","citing_title":"PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":128,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07892","citing_title":"Data Selection for Multi-turn Dialogue Instruction Tuning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN","json":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN.json","graph_json":"https://pith.science/api/pith-number/EACVKCNYYVHWGARNL5JQHLZOUN/graph.json","events_json":"https://pith.science/api/pith-number/EACVKCNYYVHWGARNL5JQHLZOUN/events.json","paper":"https://pith.science/paper/EACVKCNY"},"agent_actions":{"view_html":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN","download_json":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN.json","view_paper":"https://pith.science/paper/EACVKCNY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13711&json=true","fetch_graph":"https://pith.science/api/pith-number/EACVKCNYYVHWGARNL5JQHLZOUN/graph.json","fetch_events":"https://pith.science/api/pith-number/EACVKCNYYVHWGARNL5JQHLZOUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN/action/storage_attestation","attest_author":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN/action/author_attestation","sign_citation":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN/action/citation_signature","submit_replication":"https://pith.science/pith/EACVKCNYYVHWGARNL5JQHLZOUN/action/replication_record"}},"created_at":"2026-07-05T06:12:56.518308+00:00","updated_at":"2026-07-05T06:12:56.518308+00:00"}