{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4TR6JJARK2RBIOZOHSNT7VBIZ2","short_pith_number":"pith:4TR6JJAR","schema_version":"1.0","canonical_sha256":"e4e3e4a41156a2143b2e3c9b3fd428cea3c0e5ff4983b14878e936988085db7b","source":{"kind":"arxiv","id":"2309.13308","version":1},"attestation_state":"computed","paper":{"title":"Calibrating LLM-Based Evaluator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feng Sun, Furu Wei, Haizhen Huang, Qi Zhang, Shaohan Huang, Tianchi Yang, Weiwei Deng, Yuxuan Liu, Zihan Zhang","submitted_at":"2023-09-23T08:46:11Z","abstract_excerpt":"Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation. However, hindered by the closed-source or high computational demand to host and tune, there is a lack of practice to further calibrate an off-the-shelf LLM-based evaluator towards better human alignment. In this work, we propose AutoCalibrate, a multi-stage, gradient-free approach to automatically calibrate and align an LLM-based evaluator toward human preference"},"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":"2309.13308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T08:46:11Z","cross_cats_sorted":[],"title_canon_sha256":"1e41e3ea3459fcc779208f7888612d6b1c8f637677689fa60ce4b2b10f1c6ce1","abstract_canon_sha256":"33d76f133bfbf492b2da063b035a1e84a5d33e8eb2b2c816cb37ca8cf18747c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:50.084156Z","signature_b64":"2sm+NP3iv/B4TJy7u7B9TUXukpXIYxE0KpepIKMRI8OuF+37Ld4qTEIE0zAGnsiZhQ8gedgM4sKbQtPxuWB+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4e3e4a41156a2143b2e3c9b3fd428cea3c0e5ff4983b14878e936988085db7b","last_reissued_at":"2026-07-05T06:53:50.083645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:50.083645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibrating LLM-Based Evaluator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feng Sun, Furu Wei, Haizhen Huang, Qi Zhang, Shaohan Huang, Tianchi Yang, Weiwei Deng, Yuxuan Liu, Zihan Zhang","submitted_at":"2023-09-23T08:46:11Z","abstract_excerpt":"Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation. However, hindered by the closed-source or high computational demand to host and tune, there is a lack of practice to further calibrate an off-the-shelf LLM-based evaluator towards better human alignment. In this work, we propose AutoCalibrate, a multi-stage, gradient-free approach to automatically calibrate and align an LLM-based evaluator toward human preference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13308","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/2309.13308/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":"2309.13308","created_at":"2026-07-05T06:53:50.083702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13308v1","created_at":"2026-07-05T06:53:50.083702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13308","created_at":"2026-07-05T06:53:50.083702+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TR6JJARK2RB","created_at":"2026-07-05T06:53:50.083702+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TR6JJARK2RBIOZO","created_at":"2026-07-05T06:53:50.083702+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TR6JJAR","created_at":"2026-07-05T06:53:50.083702+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22329","citing_title":"BabelJudge: Measuring LLM-as-a-Judge Reliability Across Languages and Agent Trajectories","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2506.21582","citing_title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2410.09024","citing_title":"AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17200","citing_title":"Calibrating Model-Based Evaluation Metrics for Summarization","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2","json":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2.json","graph_json":"https://pith.science/api/pith-number/4TR6JJARK2RBIOZOHSNT7VBIZ2/graph.json","events_json":"https://pith.science/api/pith-number/4TR6JJARK2RBIOZOHSNT7VBIZ2/events.json","paper":"https://pith.science/paper/4TR6JJAR"},"agent_actions":{"view_html":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2","download_json":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2.json","view_paper":"https://pith.science/paper/4TR6JJAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13308&json=true","fetch_graph":"https://pith.science/api/pith-number/4TR6JJARK2RBIOZOHSNT7VBIZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/4TR6JJARK2RBIOZOHSNT7VBIZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2/action/storage_attestation","attest_author":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2/action/author_attestation","sign_citation":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2/action/citation_signature","submit_replication":"https://pith.science/pith/4TR6JJARK2RBIOZOHSNT7VBIZ2/action/replication_record"}},"created_at":"2026-07-05T06:53:50.083702+00:00","updated_at":"2026-07-05T06:53:50.083702+00:00"}