{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T6UXLZHDGTWI3HI42B2GH6SFHR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"34a995ca466bd152b5fddf47593e150bdbc6d0c33688a7db1d150676159ce20f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","title_canon_sha256":"f9bf1957689d01899db0b5532d89b6a8531939a112cc8227701236e3ed4228eb"},"schema_version":"1.0","source":{"id":"2310.05657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05657","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05657v1","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05657","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_12","alias_value":"T6UXLZHDGTWI","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_16","alias_value":"T6UXLZHDGTWI3HI4","created_at":"2026-07-05T06:58:48Z"},{"alias_kind":"pith_short_8","alias_value":"T6UXLZHD","created_at":"2026-07-05T06:58:48Z"}],"graph_snapshots":[{"event_id":"sha256:99d605ff35e250e5d369659c9a487e3dd4441384ca9bb349fe696582d79e28a7","target":"graph","created_at":"2026-07-05T06:58:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.05657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Using large language models (LLMs) to evaluate text quality has recently gained popularity. Some prior works explore the idea of using LLMs for evaluation, while they differ in some details of the evaluation process. In this paper, we analyze LLM evaluation (Chiang and Lee, 2023) and G-Eval (Liu et al., 2023), and we discuss how those details in the evaluation process change how well the ratings given by LLMs correlate with human ratings. We find that the auto Chain-of-Thought (CoT) used in G-Eval does not always make G-Eval more aligned with human ratings. We also show that forcing the LLM to","authors_text":"Cheng-Han Chiang, Hung-yi Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","title":"A Closer Look into Automatic Evaluation Using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05657","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3894df23230adc7965f046a2c821e15e9bbe6ea408c66358ac38bbf68b2d19a5","target":"record","created_at":"2026-07-05T06:58:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"34a995ca466bd152b5fddf47593e150bdbc6d0c33688a7db1d150676159ce20f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T12:12:55Z","title_canon_sha256":"f9bf1957689d01899db0b5532d89b6a8531939a112cc8227701236e3ed4228eb"},"schema_version":"1.0","source":{"id":"2310.05657","kind":"arxiv","version":1}},"canonical_sha256":"9fa975e4e334ec8d9d1cd07463fa453c58b2b926d57a3a7f0834963f82c3e02f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fa975e4e334ec8d9d1cd07463fa453c58b2b926d57a3a7f0834963f82c3e02f","first_computed_at":"2026-07-05T06:58:48.164986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:48.164986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HEPKEkIjmLluoHVToa4+iCGgwbxWVvAgsgVZAXmruBtj3euuOa6RM8unCKq9zg9Yt0l0CWcGCBZiqlMuN30rBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:48.165472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3894df23230adc7965f046a2c821e15e9bbe6ea408c66358ac38bbf68b2d19a5","sha256:99d605ff35e250e5d369659c9a487e3dd4441384ca9bb349fe696582d79e28a7"],"state_sha256":"5c144ed56d266368eff2f792a43de5601f76d3c3c9dde4cca96f6a02267e99f6"}