Mitigating Preference Leakage via Strict Estimator Separation for Normative Generative Ranking

• URL: http://arxiv.org/abs/2602.20800v2
• Date: Wed, 25 Feb 2026 10:31:56 GMT
• Title: Mitigating Preference Leakage via Strict Estimator Separation for Normative Generative Ranking
• Abstract summary: Current evaluations suffer from circularity and preference leakage.<n>We introduce a leakage-free two-judge framework that strictly separates supervision (Judge B) from evaluation (Judge A)<n>Our results prove that subtle cultural preferences can be distilled into efficient rankers without leakage.
• Score: 16.186456141688645
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In Generative Information Retrieval (GenIR), the bottleneck has shifted from generation to the selection of candidates, particularly for normative criteria such as cultural relevance. Current LLM-as-a-Judge evaluations often suffer from circularity and preference leakage, where overlapping supervision and evaluation models inflate performance. We address this by formalising cultural relevance as a within-query ranking task and introducing a leakage-free two-judge framework that strictly separates supervision (Judge B) from evaluation (Judge A). On a new benchmark of 33,052 (NGR-33k) culturally grounded stories, we find that while classical baselines yield only modest gains, a dense bi-encoder distilled from a Judge-B-supervised Cross-Encoder is highly effective. Although the Cross-Encoder provides a strong supervision signal for distillation, the distilled BGE-M3 model substantially outperforms it under leakage-free Judge~A evaluation. We validate our framework on the human-curated Moral Stories dataset, showing strong alignment with human norms. Our results demonstrate that rigorous evaluator separation is a prerequisite for credible GenIR evaluation, proving that subtle cultural preferences can be distilled into efficient rankers without leakage.

Related papers

• 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)
• Rethinking Reward Supervision: Rubric-Conditioned Self-Distillation [60.55792673956761]
  We propose textbfRubric-Conditioned Self-Distillation, a framework that incorporates rubrics as structured, fine-grained feedback for on-policy self-distillation.<n>We evaluate on a diverse suite of science reasoning benchmarks and results show that rubric-conditioned self-distillation effectively converts rubric-level criteria into token-level guidance.
  arXiv  Detail & Related papers  (2026-06-17T17:54:04Z)
• 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)
• BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation [11.37493959290663]
  We introduce BERT-as-a-Judge, an encoder-driven approach for assessing answer correctness in reference-based generative settings.<n>We show that it consistently outperforms the lexical baseline while matching the performance of much larger LLM judges.
  arXiv  Detail & Related papers  (2026-04-10T17:08:40Z)
• CDRRM: Contrast-Driven Rubric Generation for Reliable and Interpretable Reward Modeling [61.75914342638658]
  CDRRM (Contrast-Driven Reward Model) is a framework for high-quality rubric generation and guided preference judgment.<n>This work offers a scalable, interpretable, and data-efficient path for reward modeling.
  arXiv  Detail & Related papers  (2026-03-09T07:15:23Z)
• Pixels Don't Lie (But Your Detector Might): Bootstrapping MLLM-as-a-Judge for Trustworthy Deepfake Detection and Reasoning Supervision [25.382800247901827]
  DeepfakeJudge is a framework for scalable reasoning supervision and evaluation.<n>It integrates an out-of-distribution benchmark containing recent generative and editing forgeries, a human-annotated subset with visual reasoning labels, and a suite of evaluation models.
  arXiv  Detail & Related papers  (2026-02-23T11:08:46Z)
• R-Align: Enhancing Generative Reward Models through Rationale-Centric Meta-Judging [69.96389360650072]
  We show that reasoning fidelity is highly predictive of downstream RLHF outcomes, beyond standard label accuracy.<n>We propose Rationale-Centric Alignment, R-Align, which augments training with gold judgments and explicitly supervises rationale alignment.
  arXiv  Detail & Related papers  (2026-02-06T15:17:11Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• RULERS: Locked Rubrics and Evidence-Anchored Scoring for Robust LLM Evaluation [15.787947727055611]
  We introduce RULERS, a compiler-executor framework that transforms natural language rubrics into executable specifications.<n>RULERS operates by compiling criteria into versioned immutable bundles, enforcing structured decoding with deterministic evidence verification, and applying lightweight Wasserstein-based post-hoc calibration.
  arXiv  Detail & Related papers  (2026-01-13T15:31:42Z)
• LLM-as-a-Judge: Rapid Evaluation of Legal Document Recommendation for Retrieval-Augmented Generation [40.06592175227558]
  This paper investigates a principled approach to evaluating Retrieval-Augmented Generation systems in legal contexts.<n>We find that traditional agreement metrics like Krippendorff's alpha can be misleading in the skewed distributions typical of AI system evaluations.<n>Our findings suggest a path toward scalable, cost-effective evaluation that maintains the precision demanded by legal applications.
  arXiv  Detail & Related papers  (2025-09-15T19:20:21Z)
• UDA: Unsupervised Debiasing Alignment for Pair-wise LLM-as-a-Judge [23.497453639857852]
  We propose UDA, a framework that reduces inter-judge disagreement by dynamically adjusting the Elo rating system.<n>UDA operates in a fully unsupervised manner, guided solely by the objective of minimizing the dispersion among the Elo trajectories of all judges.<n>Experiments show that UDA significantly reduces the inter-judge rating standard deviation by up to 63.4% and improves the average correlation with human judgments by 24.7%.
  arXiv  Detail & Related papers  (2025-08-13T11:41:01Z)
• CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards [72.44810390478229]
  CompassJudger-2 is a novel generalist judge model that overcomes limitations via a task-driven, multi-domain data curation strategy.<n> CompassJudger-2 achieves superior results across multiple judge and reward benchmarks.
  arXiv  Detail & Related papers  (2025-07-12T01:34:24Z)
• J4R: Learning to Judge with Equivalent Initial State Group Relative Policy Optimization [69.23273504123941]
  We train judges to be robust to positional biases that arise in more complex evaluation settings.<n>We introduce ReasoningJudgeBench, a benchmark that evaluates judges in diverse reasoning settings not covered by prior work.<n>We train Judge for Reasoning (J4R), a 7B judge trained with EIS-GRPO that outperforms GPT-4o and the next best small judge by 6.7% and 9%.
  arXiv  Detail & Related papers  (2025-05-19T16:50:35Z)
• Language Model Preference Evaluation with Multiple Weak Evaluators [89.90733463933431]
  We introduce PGED, a novel approach that leverages multiple model-based evaluators to construct preference graphs, and then ensembles and denoises these graphs for acyclic, non-contradictory evaluation results.<n>We demonstrate PGED's superiority in three applications: 1) model ranking for evaluation, 2) response selection for test-time scaling, and 3) data selection for model fine-tuning.
  arXiv  Detail & Related papers  (2024-10-14T01:57:25Z)
• Direct Judgement Preference Optimization [79.54459973726405]
  We train large language models (LLMs) as generative judges to evaluate and critique other models' outputs.<n>We employ three approaches to collect the preference pairs for different use cases, each aimed at improving our generative judge from a different perspective.<n>Our model robustly counters inherent biases such as position and length bias, flexibly adapts to any evaluation protocol specified by practitioners, and provides helpful language feedback for improving downstream generator models.
  arXiv  Detail & Related papers  (2024-09-23T02:08:20Z)
• Unsupervised Learning of Debiased Representations with Pseudo-Attributes [85.5691102676175]
  We propose a simple but effective debiasing technique in an unsupervised manner. We perform clustering on the feature embedding space and identify pseudoattributes by taking advantage of the clustering results. We then employ a novel cluster-based reweighting scheme for learning debiased representation.
  arXiv  Detail & Related papers  (2021-08-06T05:20:46Z)

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.