JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment

• URL: http://arxiv.org/abs/2605.25240v2
• Date: Tue, 02 Jun 2026 02:06:08 GMT
• Title: JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment
• Abstract summary: We release JudgmentBench, a benchmark of 30 real-world legal tasks paired with 1,539 rubric scores and 1,530 pairwise preference judgments.<n>The annotations constitute the first publicly available dataset in a high-expertise domain in which both supervision signals are elicited from the same experts.
• Score: 2.961401607740788
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Two methodologies dominate current practices of benchmarking: rubric-based scoring evaluates items against predefined criteria, whereas comparative judgment elicits pairwise preferences between outputs. Although both methodologies are widely used, the choice between them is rarely justified. We release JudgmentBench, a benchmark of 30 real-world legal tasks, paired with 1,539 rubric scores and 1,530 pairwise preference judgments collected from practicing attorneys--including at major U.S. law firms--with substantial experience. The annotations constitute the first publicly available dataset in a high-expertise domain in which both supervision signals are elicited from the same experts on the same items. Using LLM-generated outputs at three constructed quality levels, we provide an initial empirical comparison: comparative judgments recover the intended quality ordering substantially better than rubrics (mean Spearman's rank correlation of 0.908 vs. 0.150, estimated difference = 0.758 [0.494, 1.021]) while requiring less than half the annotation time. The patterns hold for human annotators and LLM autograders. Beyond this initial comparison, the paired structure of the dataset supports a broader research agenda on how expert judgment should be elicited, aggregated, and used as supervision in domains without verifiable ground truth.

Related papers

• The Double Measurement Confound in Agent Benchmarks: De-Scaffolding, Ground-Truth Scoring, and Reliability Beyond the Mean [2.822987192839875]
  Agent benchmarks are increasingly used to compare large language models (LLMs) and guide deployment decisions.<n>We identify a double measurement confound: execution-critical decisions are performed by a fixed scaffold instead of the model, while the scorer evaluates outputs using criteria that may not reflect task correctness.<n>We unify these issues within a measurement-theoretic framework that characterizes when benchmark scores can be interpreted as evidence of model capability.
  arXiv  Detail & Related papers  (2026-09-06T21:23:11Z)
• Small Language Models as Judges for Rubric-Based Reinforcement Learning [57.707881387886516]
  We study whether smaller language models can serve as efficient and reliable rubric-based judges.<n>We compare three ways of extracting criterion-level judgments from small models: Generative verdicts, Yes/No Logprob margins, and Probe judges.<n>Across both datasets, the Qwen3-1.7B Probe judge achieves the strongest criterion-level agreement among these methods.
  arXiv  Detail & Related papers  (2026-08-30T20:00:17Z)
• PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception [75.70273182182397]
  PerceptionRubrics is a rubric-based evaluation framework.<n>It addresses the gap between saturated benchmark scores and real-world brittleness.<n>It pairs 1,038 information-dense images with over 10,000 instance-specific rubrics.
  arXiv  Detail & Related papers  (2026-06-26T17:59:15Z)
• To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias [61.40435736418359]
  We introduce a unified framework that standardizes heterogeneous benchmarks to contrast isolated demographic assessments with forced-choice comparative settings.<n>We show that comparative settings act as aggressive catalysts for latent discrimination, a shift primarily driven by underspecified contexts.<n>Finally, we demonstrate that this comparative prejudice is a generalized phenomenon that scales positively with model size.
  arXiv  Detail & Related papers  (2026-06-23T13:53:50Z)
• CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging [95.02210956333374]
  We propose a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation.<n>On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy.
  arXiv  Detail & Related papers  (2026-05-19T10:59:19Z)
• Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement [4.814048071575166]
  Analyses show substantial expert disagreement on fine-grained ordinal scores, while agreement is higher under coarse selection.<n>We then compare three judge configurations: a zero-shot judge, an aggregate judge conditioned on mixed evaluator histories, and a personalized judge conditioned on the target evaluator's scoring history.<n>Across dimensions and model sizes, personalized judges align more closely with the corresponding evaluator than aggregate judges, and evaluator agreement correlates with similarity of judge-generated reasoning only under personalized conditioning.
  arXiv  Detail & Related papers  (2026-04-24T12:56:54Z)
• Re-Rankers as Relevance Judges [65.37611299805856]
  We reproduce re-rankers in a re-ranker-as-relevance-judge setup.<n>We perform experiments on TREC-DL 2019 to 2023 with 8 re-rankers from 3 families, ranging from 220M to 32B, and analyse the evaluation bias exhibited by re-ranker-based judges.
  arXiv  Detail & Related papers  (2026-01-08T00:02:59Z)
• Retrieving Semantically Similar Decisions under Noisy Institutional Labels: Robust Comparison of Embedding Methods [0.0]
  General-purpose embedder (OpenAI) outperforms domain-specific BERT-trained from scratch on 30,000 decisions.<n>Our framework is robust enough to be used for evaluation under a noisy gold dataset.
  arXiv  Detail & Related papers  (2025-12-05T12:54:26Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• The Comparative Trap: Pairwise Comparisons Amplifies Biased Preferences of LLM Evaluators [31.520403357740317]
  Large language models (LLMs) are increasingly used as evaluators for natural language generation tasks.<n>LLMs display biased preferences, such as favoring verbosity and authoritative tones.<n>We introduce PRePair, which integrates pointwise reasoning within a pairwise framework.
  arXiv  Detail & Related papers  (2024-06-18T06:43:04Z)
• LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models [55.60306377044225]
  Large language models (LLMs) have enabled impressive zero-shot capabilities across various natural language tasks. This paper explores two options for exploiting the emergent abilities of LLMs for zero-shot NLG assessment. For moderate-sized open-source LLMs, such as FlanT5 and Llama2-chat, comparative assessment is superior to prompt scoring.
  arXiv  Detail & Related papers  (2023-07-15T22:02:12Z)
• Rater Equivalence: Evaluating Classifiers in Human Judgment Settings [11.529701822081394]
  We introduce a framework for evaluating automated classifiers based solely on human judgments.<n>Our framework uses human-generated labels both to construct benchmark panels and to evaluate performance.<n>Using case studies and formal analysis, we demonstrate how this framework can inform the evaluation and deployment of AI systems.
  arXiv  Detail & Related papers  (2021-06-02T16:07:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.