{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AWGGH2D4NG3B6I2RCZ5MDLU535","short_pith_number":"pith:AWGGH2D4","schema_version":"1.0","canonical_sha256":"058c63e87c69b61f2351167ac1ae9ddf6bd0db3118300fbbfbddc82c4a84b427","source":{"kind":"arxiv","id":"2601.03630","version":2},"attestation_state":"computed","paper":{"title":"Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Large reasoning models outperform standard LLMs as judges on accuracy and robustness but still carry strong evaluation biases that an explicit planning step can reduce.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Huang, Muyun Yang, Xuanxin Wu, Yuki Arase","submitted_at":"2026-01-07T06:19:26Z","abstract_excerpt":"This paper presents the first systematic comparison investigating whether Large Reasoning Models (LRMs) are superior judges to non-reasoning LLMs. Our empirical analysis yields four key findings: 1) LRMs outperform non-reasoning LLMs in terms of judgment accuracy, particularly on reasoning-intensive tasks; 2) LRMs demonstrate superior evaluation instruction-following capabilities; 3) LRMs exhibit enhanced robustness against adversarial attacks targeting judgment tasks; 4) However, LRMs still exhibit strong evaluation biases. To mitigate this bias vulnerability, we propose PlanJudge, a lightwei"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.03630","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-07T06:19:26Z","cross_cats_sorted":[],"title_canon_sha256":"815ace6fd9ed995b8703dba2203cf04166011cfe3041c0dda4ee93706a84ff21","abstract_canon_sha256":"07229dbd403bf02fe1ca97dd890d85b09906bc427ad26ba8a4cb77eca547b26a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.710763Z","signature_b64":"/8IxzJUAPdmqADdP8ES0DoMZEU6P1KCI0ucPW4frRrjs+RiepkqW1Bav9Z6hBd5gzNaUzjArBoYQXpb0qd2kAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058c63e87c69b61f2351167ac1ae9ddf6bd0db3118300fbbfbddc82c4a84b427","last_reissued_at":"2026-05-17T23:39:16.710192Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.710192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Large reasoning models outperform standard LLMs as judges on accuracy and robustness but still carry strong evaluation biases that an explicit planning step can reduce.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Huang, Muyun Yang, Xuanxin Wu, Yuki Arase","submitted_at":"2026-01-07T06:19:26Z","abstract_excerpt":"This paper presents the first systematic comparison investigating whether Large Reasoning Models (LRMs) are superior judges to non-reasoning LLMs. Our empirical analysis yields four key findings: 1) LRMs outperform non-reasoning LLMs in terms of judgment accuracy, particularly on reasoning-intensive tasks; 2) LRMs demonstrate superior evaluation instruction-following capabilities; 3) LRMs exhibit enhanced robustness against adversarial attacks targeting judgment tasks; 4) However, LRMs still exhibit strong evaluation biases. To mitigate this bias vulnerability, we propose PlanJudge, a lightwei"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"LRMs outperform non-reasoning LLMs in judgment accuracy, particularly on reasoning-intensive tasks, demonstrate superior instruction-following and robustness, yet still exhibit strong evaluation biases that PlanJudge mitigates while preserving accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen tasks, adversarial attacks, and bias metrics comprehensively capture real-world judgment scenarios and that observed improvements generalize beyond the tested models and datasets.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Reasoning models judge better than non-reasoning LLMs yet retain biases; generating an evaluation plan first mitigates bias without losing accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large reasoning models outperform standard LLMs as judges on accuracy and robustness but still carry strong evaluation biases that an explicit planning step can reduce.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3de6081e860dd93d181654d98c34111e51e81d105489df81c37d07e5720d9adf"},"source":{"id":"2601.03630","kind":"arxiv","version":2},"verdict":{"id":"d134c7ab-42ab-4aec-9c54-d29387a47ef1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T17:14:40.009656Z","strongest_claim":"LRMs outperform non-reasoning LLMs in judgment accuracy, particularly on reasoning-intensive tasks, demonstrate superior instruction-following and robustness, yet still exhibit strong evaluation biases that PlanJudge mitigates while preserving accuracy.","one_line_summary":"Reasoning models judge better than non-reasoning LLMs yet retain biases; generating an evaluation plan first mitigates bias without losing accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen tasks, adversarial attacks, and bias metrics comprehensively capture real-world judgment scenarios and that observed improvements generalize beyond the tested models and datasets.","pith_extraction_headline":"Large reasoning models outperform standard LLMs as judges on accuracy and robustness but still carry strong evaluation biases that an explicit planning step can reduce."},"references":{"count":12,"sample":[{"doi":"","year":2025,"title":"InFindings of the Association for Computational Linguistics: ACL 2025, pages 5880–5895","work_id":"61bb32c1-ce49-4dfa-a311-d0ba4eeb1709","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Zhang, Makesh Narsimhan Sreedhar, and Oleksii Kuchaiev","work_id":"a48d5ada-8623-467d-baf4-93bd47703121","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Are reasoning models more prone to hallucination?","work_id":"cbb24d0e-0a95-46cb-a43e-115b3c4115d7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Planning: A detailed evaluation plan is specified based on the current evaluation task","work_id":"1630ead5-cdf4-4899-ae6d-c35802dd91ed","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"We investigate three distinct strategies for the first step of plan generation:","work_id":"903f762c-74ef-4a5e-a50c-0e26882caa22","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":12,"snapshot_sha256":"1860e2cff397bae7d9f78cbc8e77b854d9560dad92b597496023dcfbcf3fe2ac","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":"2601.03630","created_at":"2026-05-17T23:39:16.710287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.03630v2","created_at":"2026-05-17T23:39:16.710287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.03630","created_at":"2026-05-17T23:39:16.710287+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWGGH2D4NG3B","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWGGH2D4NG3B6I2R","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWGGH2D4","created_at":"2026-05-18T12:33:37.589309+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/AWGGH2D4NG3B6I2RCZ5MDLU535","json":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535.json","graph_json":"https://pith.science/api/pith-number/AWGGH2D4NG3B6I2RCZ5MDLU535/graph.json","events_json":"https://pith.science/api/pith-number/AWGGH2D4NG3B6I2RCZ5MDLU535/events.json","paper":"https://pith.science/paper/AWGGH2D4"},"agent_actions":{"view_html":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535","download_json":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535.json","view_paper":"https://pith.science/paper/AWGGH2D4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.03630&json=true","fetch_graph":"https://pith.science/api/pith-number/AWGGH2D4NG3B6I2RCZ5MDLU535/graph.json","fetch_events":"https://pith.science/api/pith-number/AWGGH2D4NG3B6I2RCZ5MDLU535/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535/action/storage_attestation","attest_author":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535/action/author_attestation","sign_citation":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535/action/citation_signature","submit_replication":"https://pith.science/pith/AWGGH2D4NG3B6I2RCZ5MDLU535/action/replication_record"}},"created_at":"2026-05-17T23:39:16.710287+00:00","updated_at":"2026-05-17T23:39:16.710287+00:00"}