{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QCZECMJGYQY4RRNAO2FZ6UUCBA","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":"fbec2543d23bf6fcb561e60235dcfd1f5ace7de94c8e82d5d015a4711249c0f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T09:52:44Z","title_canon_sha256":"52e2c1b07cb407f9fb603e40bc7cf8a837672ba9e66e8eb525b3dcc2b2130648"},"schema_version":"1.0","source":{"id":"2409.16788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16788","created_at":"2026-07-05T09:11:39Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16788v1","created_at":"2026-07-05T09:11:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16788","created_at":"2026-07-05T09:11:39Z"},{"alias_kind":"pith_short_12","alias_value":"QCZECMJGYQY4","created_at":"2026-07-05T09:11:39Z"},{"alias_kind":"pith_short_16","alias_value":"QCZECMJGYQY4RRNA","created_at":"2026-07-05T09:11:39Z"},{"alias_kind":"pith_short_8","alias_value":"QCZECMJG","created_at":"2026-07-05T09:11:39Z"}],"graph_snapshots":[{"event_id":"sha256:955a7941f1a9dd6c486b702567941d572e94ebbd9e02a9c3aa1530fb2dde22de","target":"graph","created_at":"2026-07-05T09:11:39Z","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/2409.16788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been a trend of evaluating the Large Language Model (LLM) quality in the flavor of LLM-as-a-Judge, namely leveraging another LLM to evaluate the current output quality. However, existing judges are proven to be biased, namely they would favor answers which present better superficial quality (such as verbosity, fluency) while ignoring the instruction following ability. In this work, we propose systematic research about the bias of LLM-as-a-Judge. Specifically, for closed-source judge models, we apply calibration to mitigate the significance of superficial quality, both on pr","authors_text":"Bing Xu, Conghui Zhu, Hailong Cao, Hongli Zhou, Hui Huang, Muyun Yang, Tiejun Zhao, Yunfei Long","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T09:52:44Z","title":"Mitigating the Bias of Large Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16788","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":"sha256:4ca6094a940c17263cf266de592b495ed7f616abdbaec07fa44d678ebc7d177a","target":"record","created_at":"2026-07-05T09:11:39Z","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":"fbec2543d23bf6fcb561e60235dcfd1f5ace7de94c8e82d5d015a4711249c0f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T09:52:44Z","title_canon_sha256":"52e2c1b07cb407f9fb603e40bc7cf8a837672ba9e66e8eb525b3dcc2b2130648"},"schema_version":"1.0","source":{"id":"2409.16788","kind":"arxiv","version":1}},"canonical_sha256":"80b2413126c431c8c5a0768b9f5282081247e82c5bd1a431436aabe45b08373a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80b2413126c431c8c5a0768b9f5282081247e82c5bd1a431436aabe45b08373a","first_computed_at":"2026-07-05T09:11:39.365797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:11:39.365797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dt34VFL2wS+NAZypIxpVMHHxwy3+emogHgVN0B9pTNlbObWs2LHj7OOCMBLoV8uJA4NDVKk7c88nj27m6QcADg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:11:39.366327Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ca6094a940c17263cf266de592b495ed7f616abdbaec07fa44d678ebc7d177a","sha256:955a7941f1a9dd6c486b702567941d572e94ebbd9e02a9c3aa1530fb2dde22de"],"state_sha256":"20a593b90db728adacfdef8a0e58c5bf23ace4a906a6a24c55563e488519daf4"}