Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges

• URL: http://arxiv.org/abs/2606.09165v1
• Date: Mon, 08 Jun 2026 08:02:57 GMT
• Title: Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges
• Abstract summary: Safety judges are increasingly deployed to evaluate model outputs against evolving criteria.<n>Recent meta-evaluation work shows they remain brittle under prompt and rubric variation.<n>We propose a training strategy that combines instance-conditioned dynamic rubrics and a reliable-to-expressive curriculum.
• Score: 2.8523456804049885
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Safety judges are increasingly deployed to evaluate model outputs against evolving criteria, yet recent meta-evaluation work shows they remain brittle under prompt and rubric variation, with false negative-rate swings of up to 0.24 reported for stylistic perturbations alone. We argue that safety judgment is fundamentally a rubric-following problem: a robust judge must apply the given evaluation criteria consistently across rubric formulations rather than memorize one specific template. We propose a training strategy that combines (i) instance-conditioned dynamic rubrics generated from prompt-response-label triples to expose the judge to the variability of evaluation criteria, and (ii) a reliable-to-expressive curriculum that begins with clean fixed-rubric supervision and progressively introduces noisier dynamic-rubric data. We evaluate on a single human-labeled set under three contrasting rubric prompts (HarmBench-style, ShieldGemma-style, and a domain-specific rubric). Our 12B curriculum judge achieves 94.12-94.88% accuracy across the three rubrics with a cross-rubric range of only 0.76, outperforming general-purpose LLMs, dedicated safety classifiers, and reasoning-oriented judges up to 30B in both peak accuracy and stability. An ablation shows that naively mixing dynamic rubrics into SFT increases cross rubric variance (1.44 -> 3.60); only the curriculum schedule recovers and improves on the fixed rubric baseline (variance 0.76).

Related papers

• 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)
• Cybersecurity Detection Classification with Reasoning-enabled Language Models [50.72675435043546]
  A major issue in Security Operations Centers (SOCs) is alert fatigue.<n>Prior work prompts or fine-tunes large language models (LLMs) to emit a triage label directly, but does not train them to reason about whether a detection is a genuine threat.<n>We train a chain-of-thought (CoT) reasoning-enabled triage classifier on real, human-labeled Windows endpoint detections.
  arXiv  Detail & Related papers  (2026-07-30T16:22:13Z)
• Which Values Do LLMs Confuse? A Schwartz-Based Recognition Study [32.505127447635864]
  We study controlled top-1 recognition over Schwartz's ten basic values.<n>We evaluate 21 instruction-tuned LLM runs under a fixed ranked-response protocol.<n>We find that models often locate the correct motivational region while ranking close alternatives unstably.
  arXiv  Detail & Related papers  (2026-07-22T15:22:14Z)
• 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)
• Evaluation Awareness Is Not One Capability: Evidence from Open Language Models [1.758143872501506]
  Safety benchmarks assume that test-condition behavior predicts deployment behavior, an assumption that fails if models detect evaluation cues and adapt.<n>This opens a gap between benchmark performance and deployment behavior.<n>We characterize this evaluation awareness through eight experiments across 37 open-weight models and seven families.
  arXiv  Detail & Related papers  (2026-06-22T16:48:43Z)
• Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking [22.825786049667602]
  We propose a replication-first paradigm to anchor validity to a single human-rater consensus.<n>We certify the instrument via four properties -- reliability across K runs, cross-instrument replication across architecturally distinct judges, historical-footprint calibration via judges from earlier training cohorts, and pre-registered prediction.<n>We test it on emotional accompaniment by letting the self-evolve data-driven across: the dimensions are not pre-stipulated and the procedure stabilizes to a 9-dimension set.
  arXiv  Detail & Related papers  (2026-05-27T03:41:11Z)
• TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models [76.92890872338235]
  Large-scale pre-trained Vision-Language models (VLMs) exhibit strong zero-shot generalization, yet are highly vulnerable to imperceptible adversarial perturbations.<n>To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense.
  arXiv  Detail & Related papers  (2026-05-17T18:07:08Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses [5.396994583933599]
  We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for evaluation of both prompts and responses.<n>PEEM defines a structured rubric with 9 axes: 3 prompt criteria (clarity/structure, linguistic quality, fairness) and 6 response criteria (accuracy, objectivity, relevance, clarity, conciseness)
  arXiv  Detail & Related papers  (2026-03-11T07:00:59Z)
• Autorubric: A Unified Framework for Rubric-Based LLM Evaluation [34.429649156970015]
  We present a unified framework for evaluating large language models (LLMs)<n>Each identified technique is paired with its realization in Autorubric, an open-source Python framework proposed in this paper.<n>Autorubric supports binary, ordinal, and nominal criteria with weights; single-judge and multi-judge ensemble evaluation with majority, weighted, unanimous, and any-vote aggregation.
  arXiv  Detail & Related papers  (2026-02-13T02:26:30Z)
• Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements [78.87065404966002]
  Existing benchmarks predominantly curate questions at the question level.<n>We propose Encyclo-K, a statement-based benchmark that rethinks benchmark construction from the ground up.
  arXiv  Detail & Related papers  (2025-12-31T13:55:54Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• 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)

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.