paper-with-me

홈 › Papers

RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following

2026-03-26 · Tianjun Pan, Xuan Lin, Wenyan Yang, Qianyu He, Shisong Chen, Licai Qi, Wanqing Xu, Hongwei Feng, Bo Xu, Yanghua Xiao arxiv

Rubric-based evaluation has become a prevailing paradigm for evaluating instruction following in large language models (LLMs). Despite its widespread use, the reliability of these rubric-level evaluations remains unclear, calling for meta-evaluation. However, prior meta-evaluation efforts largely focus on the response level, failing to assess the fine-grained judgment accuracy that rubric-based evaluation relies on. To bridge this gap, we introduce RubricEval. Our benchmark features: (1) the first rubric-level meta-evaluation benchmark for instruction following, (2) diverse instructions and responses spanning multiple categories and model sources, and (3) a substantial set of 3,486 quality-controlled instances, along with Easy/Hard subsets that better differentiates judge performance. Our experiments reveal that rubric-level judging remains far from solved: even GPT-4o, a widely adopted judge in instruction-following benchmarks, achieves only 55.97% on Hard subset. Considering evaluation paradigm, rubric-level evaluation outperforms checklist-level, explicit reasoning improves accuracy, and both together reduce inter-judge variance. Through our established rubric taxonomy, we further identify common failure modes and offer actionable insights for reliable instruction-following evaluation.

📄 PDF Abstract BibTeX arXiv:2603.25133

Code (0)

등록된 구현이 없습니다.

Tasks

Instruction Following

Similar Papers 제목 키워드 기반

Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction

2026-07-14 · Hanhua Hong, Yizhi Li, Jiaoyan Chen, Luu Gia Huy 외 arxiv

Rubric-based evaluation is a promising approach for assessing open-ended outputs from LLM-based research agents, particularly in paper reproduction, where direct paper-to-repository comparison is prone to hallucination. …

Semantic Similarity

Generating and Refining Dynamic Evaluation Rubrics for LLM-as-a-Judge

2026-05-28 · Zijie Wang, Eduardo Blanco arxiv

LLM-as-a-Judge is a scalable alternative to human evaluation, yet existing rubric-based methods rely on human-annotated data such as reference answers or expert-crafted rubrics. We propose to automatically generate fine-…

Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

2026-07-21 · Xilun Chen, Zhaleh Feizollahi, Ross Goodwin, Seungwhan Moon 외 hf

Evaluating the factuality of long-form generations has focused predominantly on precision, measuring whether the claims a model makes are correct. The dominant decompose-search-verify pipeline catches incorrect claims we…

FinResearchBench II: A Deep Research Benchmark with Consensus-Derived Gold Rubrics for Distinguishing Financial Report Quality

2026-07-14 · Beidi Luan, Rui Sun, Sinuo Wang, Yan Gu 외 arxiv

Deep research agents are increasingly used to produce long-form financial reports, yet large-scale evaluation remains bottlenecked by the need for human experts to define and execute high-quality rubrics. We address this…

Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals

2026-05-22 · Sirui Chen, Lei Xu, Yuying Zhao, Yutian Chen 외 arxiv

Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewards (RLVR) derives outcome signals from e…

Reinforcement Learning