Pith. sign in

REVIEW 5 cited by

OffsetBias: Leveraging Debiased Data for Tuning Evaluators

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.06551 v2 pith:K6TJGRV6 submitted 2024-07-09 cs.CL

Junsoo Park , Seungyeon Jwa , Meiying Ren , Daeyoung Kim , Sanghyuk Choi This is my paper · ORCID
classification cs.CL
keywords modelsbiasesjudgedatasetevaluationevaluatorsfine-tuningoffsetbias
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Employing Large Language Models (LLMs) to assess the quality of generated responses, such as prompting instruct-tuned models or fine-tuning judge models, has become a widely adopted evaluation method. It is also known that such evaluators are vulnerable to biases, such as favoring longer responses. While it is important to overcome this problem, the specifics of these biases remain under-explored. In this work, we qualitatively identify six types of biases inherent in various judge models. We propose EvalBiasBench as a meta-evaluation collection of hand-crafted test cases for each bias type. Additionally, we present de-biasing dataset construction methods and the associated preference dataset OffsetBias. Experimental results demonstrate that fine-tuning on our dataset significantly enhances the robustness of judge models against biases and improves performance across most evaluation scenarios. We release our datasets and the fine-tuned judge model to public.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RewardAnything: Generalizable Principle-Following Reward Models

    cs.CL 2025-06 conditional novelty 6.0 of 10

    RewardAnything follows natural-language reward principles at inference time and, with the new RABench benchmark, demonstrates that principle-conditioned listwise training beats fixed-preference reward models on held-o...

  2. Helpful Agent Meets Deceptive Judge: Understanding Vulnerabilities in Agentic Workflows

    cs.AI 2025-06 conditional novelty 6.0 of 10

    LLM agents frequently switch correct answers after one round of misleading feedback, and the new WAFER-QA benchmark measures this with web-backed critiques.

  3. An Empirical Study of LLM-as-a-Judge: How Design Choices Impact Evaluation Reliability

    cs.CL 2025-06 conditional novelty 5.0 of 10

    The reliability of LLM-as-a-Judge depends strongly on scoring rubrics and reference answers; sampling with averaging outperforms greedy decoding, and chain-of-thought reasoning adds little when rubrics are clear.

  4. A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A unified taxonomy and comparative meta-evaluation of automatic evaluation methods across text, vision, and speech generation, concluding that LLM-based evaluators dominate current practice.

  5. Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

    cs.LG 2026-02 conditional novelty 4.0 of 10

    A taxonomy-driven survey arguing that reward design is the central mechanism shaping reliable LLM reasoning, with maps of reward paradigms, reward-hacking failure modes, and benchmark pitfalls.

Pith tools