Reference-Free Rating of LLM Responses via Latent Information

• URL: http://arxiv.org/abs/2509.24678v1
• Date: Mon, 29 Sep 2025 12:15:52 GMT
• Title: Reference-Free Rating of LLM Responses via Latent Information
• Authors: Leander Girrbach, Chi-Ping Su, Tankred Saanum, Richard Socher, Eric Schulz, Zeynep Akata,
• Abstract summary: 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.
• Score: 53.463883683503106
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: How reliable are single-response LLM-as-a-judge ratings without references, and can we obtain fine-grained, deterministic scores in this setting? We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses and show two systematic issues: scores are unstable under sampling and poorly calibrated, leading to compression near the top of the scale and frequent ties. We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals: (i) probability-weighted scores over integer ratings, (ii) verifier-style probabilities of "yes", and (iii) linear probes trained on model activations at the rating position. Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting, with consistent gains on pairwise accuracy and listwise ranking relevant to Best-of-N selection. Probability-weighted scores achieve the strongest single-rating correlations, while probes recover useful signals when output logits are miscalibrated. These results indicate that latent information provides deterministic and more discriminative signals for reference-free evaluation, and can improve selection and training approaches like Best-of-$N$, multi-teacher distillation, and routing.

Related papers

• Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems [32.83708359216193]
  Large Language Models (LLMs) are increasingly being used to autonomously evaluate the quality of content in communication systems.<n>This paper systematically investigates judgment biases in two LLM-as-a-judge models under the point-wise scoring setting.<n>We propose four potential mitigation strategies to ensure fair and reliable AI judging in practical communication scenarios.
  arXiv  Detail & Related papers  (2025-10-14T12:52:29Z)
• 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)
• On the Reliability of Sampling Strategies in Offline Recommender Evaluation [3.4956406636452626]
  offline evaluation plays a central role in benchmarking recommender systems when online testing is impractical or risky.<n>It is susceptible to two key sources of bias: exposure bias, where users only interact with items they are shown, and sampling bias, introduced when evaluation is performed on a subset of logged items rather than the full catalog.
  arXiv  Detail & Related papers  (2025-08-07T13:50:05Z)
• SCOPE: Stochastic and Counterbiased Option Placement for Evaluating Large Language Models [0.27309692684728604]
  Large Language Models (LLMs) can achieve inflated scores on multiple-choice tasks by exploiting inherent biases in option positions or labels.<n>This study introduces SCOPE, an evaluation framework designed to measure and mitigate such selection bias in a dataset-independent manner.
  arXiv  Detail & Related papers  (2025-07-24T08:28:17Z)
• Pairwise or Pointwise? Evaluating Feedback Protocols for Bias in LLM-Based Evaluation [57.380464382910375]
  We show that the choice of feedback protocol for evaluation can significantly affect evaluation reliability and induce systematic biases.<n>We find that generator models can flip preferences by embedding distractor features.<n>We offer recommendations for choosing feedback protocols based on dataset characteristics and evaluation objectives.
  arXiv  Detail & Related papers  (2025-04-20T19:05:59Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Unbiased Learning to Rank with Biased Continuous Feedback [5.561943356123711]
  Unbiased learning-to-rank(LTR) algorithms are verified to model the relative relevance accurately based on noisy feedback. To provide personalized high-quality recommendation results, recommender systems need model both categorical and continuous biased feedback. We introduce the pairwise trust bias to separate the position bias, trust bias, and user relevance explicitly. Experiment results on public benchmark datasets and internal live traffic of a large-scale recommender system at Tencent News show superior results for continuous labels.
  arXiv  Detail & Related papers  (2023-03-08T02:14:08Z)
• Unbiased Pairwise Learning to Rank in Recommender Systems [4.058828240864671]
  Unbiased learning to rank algorithms are appealing candidates and have already been applied in many applications with single categorical labels. We propose a novel unbiased LTR algorithm to tackle the challenges, which innovatively models position bias in the pairwise fashion. Experiment results on public benchmark datasets and internal live traffic show the superior results of the proposed method for both categorical and continuous labels.
  arXiv  Detail & Related papers  (2021-11-25T06:04:59Z)
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility [54.179859639868646]
  Bipartite ranking aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data. There have been rising concerns on whether the learned scoring function can cause systematic disparity across different protected groups. We propose a model post-processing framework for balancing them in the bipartite ranking scenario.
  arXiv  Detail & Related papers  (2020-06-15T10:08:39Z)

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.