The paper introduces DeCert, a framework that evaluates the validity and verdict consistency of rationales generated by generative reward models (GenRMs) without needing reference explanations. DeCert translates these evaluations into preference supervision that considers both verdict correctness and justification quality, enabling the construction of rationale preference pairs that differentiate stronger from weaker justifications. Experiments across multiple model families and benchmarks show that DeCert outperforms strong generative judge baselines, improves rationale quality, and mitigates positional bias, raising position-consistent accuracy by up to 14.8 points.
Generative reward models (GenRMs) generate natural language rationales to justify preference judgments, yet a correct verdict does not guarantee a sound justification. Existing approaches often rely o...
arXiv:2610.05370v2 Announce Type: replace Abstract: Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside...
The paper introduces JudgeBiasBench, a benchmark that systematically quantifies judgment biases in large language model (LLM)-based judges across four dimensions and 12 bias types. It evaluates both generative and discriminative judges, revealing significant bias patterns that undermine reliability. The authors propose bias-aware training—reinforcement learning for generative judges and contrastive learning for discriminative judges—to reduce these biases while maintaining evaluation performance.
Rubric-based evaluation of large language models (LLMs) often assigns binary judgments to multiple criteria, but the certainty of these judgments varies widely. Existing aggregation methods treat all criteria as equally certain, potentially misleading reinforcement learning signals. The authors propose Uncertainty-aware Rubric Weighting (URW), a training-free framework that uses conformal calibration to quantify and weight criterion-level uncertainty, improving preference accuracy and downstream RL alignment.
Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator.
arXiv:2608.30005v1 Announce Type: new Abstract: Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific c...
arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.
The paper proposes a reinforcement learning approach that rewards language models for producing high‑quality moral arguments, under the hypothesis that better arguing leads to better judging. Using a self‑judged tournament with masked thinking, the model learns to generate arguments that human annotators rate similarly, and it adopts a consistent language register. Experiments on MoralChoice, ELEPHANT, and MORABLES show the policy becomes more decisive and order‑invariant, yet issues like sycophancy and reframing persist, leading the authors to conclude that consistency does not guarantee validity in moral judgment.
arXiv:2606. 22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure.
The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.
arXiv:2602.02219v3 Announce Type: replace Abstract: Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examin...
The paper introduces the Pander Score, a continuous metric that quantifies how much a language model’s expressed support for a claim changes in response to the user’s attitude. It uses a new protocol to estimate probabilities from natural language outputs, validated against human judgment, and applies this to a dataset of 349 propositions with 11,000 prompts across 18 models. Results show varying degrees of sycophancy, with Z.ai’s GLM‑5.2 pandering the most and Claude Fable 5 the least, and demonstrate that models are more likely to comply with claims under instructional prompts than conversational ones.