The Necessity of Setting Temperature in LLM-as-a-Judge

• URL: http://arxiv.org/abs/2603.28304v1
• Date: Mon, 30 Mar 2026 11:31:29 GMT
• Title: The Necessity of Setting Temperature in LLM-as-a-Judge
• Abstract summary: We investigate the relationship between temperature and judge performance through a series of controlled experiments.<n>We also adopt a causal inference framework within our empirical statistical analysis to rigorously examine the direct causal effect of temperature on judge behavior.
• Score: 10.631912729138152
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: LLM-as-a-Judge has emerged as an effective and low-cost paradigm for evaluating text quality and factual correctness. Prior studies have shown substantial agreement between LLM judges and human experts, even on tasks that are difficult to assess automatically. In practice, researchers commonly employ fixed temperature configurations during the evaluation process-with values of 0.1 and 1.0 being the most prevalent choices-a convention that is largely empirical rather than principled. However, recent researches suggest that LLM performance exhibits non-trivial sensitivity to temperature settings, that lower temperatures do not universally yield optimal outcomes, and that such effects are highly task-dependent. This raises a critical research question: does temperature influence judge performance in LLM centric evaluation? To address this, we systematically investigate the relationship between temperature and judge performance through a series of controlled experiments, and further adopt a causal inference framework within our empirical statistical analysis to rigorously examine the direct causal effect of temperature on judge behavior, offering actionable engineering insights for the design of LLM-centric evaluation pipelines.

Related papers

• Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? [61.49434544687523]
  We introduce REFLECT, a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments.<n> REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions.<n>Our experiments show that even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures.
  arXiv  Detail & Related papers  (2026-05-18T23:55:08Z)
• Adaptive Rigor in AI System Evaluation using Temperature-Controlled Verdict Aggregation via Generalized Power Mean [51.56484100374058]
  This paper presents a method that combines a five-level verdict-scoring system with generalized power-mean aggregation and an intuitive temperature parameter T [0.1, 1.0] to control evaluation rigor.<n>Low temperatures yield pessimistic scores suited for safety-critical domains; high temperatures produce lenient scores appropriate for conversational AI.
  arXiv  Detail & Related papers  (2026-04-04T09:04:38Z)
• Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training [75.98427023288052]
  Reasoning LLMs-as-Judges provide a promising path for extending the success of reasoning models to non-verifiable domains.<n>This study investigates the actual impact of non-reasoning and reasoning judges in reinforcement-learning-based LLM alignment.<n>We find that reasoning-judge-trained policies achieve such strong performance by learning to generate highly effective adversarial outputs.
  arXiv  Detail & Related papers  (2026-03-12T17:57:06Z)
• TempPerturb-Eval: On the Joint Effects of Internal Temperature and External Perturbations in RAG Robustness [3.796841688047966]
  This work presents a systematic investigation of how text perturbations interact with temperature settings across multiple LLM runs.<n>We propose a comprehensive RAG Perturbation-Temperature Analysis Framework that subjects retrieved documents to three distinct perturbation types across varying temperature settings.<n>Our work yields three key contributions: (1) a diagnostic benchmark for assessing RAG robustness, (2) an analytical framework for quantifying perturbation-temperature interactions, and (3) practical guidelines for model selection and parameter tuning under noisy retrieval conditions.
  arXiv  Detail & Related papers  (2025-12-01T01:46:36Z)
• Optimal Attention Temperature Enhances In-Context Learning under Distribution Shift [8.135786025034626]
  This paper provides the first theoretical and empirical study of attention temperature for ICL under distribution shift.<n>We prove that shifts in input covariance or label noise substantially impair ICL, but that an optimal attention temperature exists which minimizes this error.<n>Our results establish attention temperature as a principled and powerful mechanism for improving the robustness of ICL in pretrained Transformers.
  arXiv  Detail & Related papers  (2025-11-03T07:18:27Z)
• MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback [136.27567671480156]
  We introduce experiment-guided ranking, which prioritizes hypotheses based on feedback from prior tests.<n>We frame experiment-guided ranking as a sequential decision-making problem.<n>Our approach significantly outperforms pre-experiment baselines and strong ablations.
  arXiv  Detail & Related papers  (2025-05-23T13:24:50Z)
• 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)
• Exploring the Impact of Temperature Scaling in Softmax for Classification and Adversarial Robustness [8.934328206473456]
  This study delves into the often-overlooked parameter within the softmax function, known as "temperature"<n>Our empirical studies, adopting convolutional neural networks and transformers, reveal that moderate temperatures generally introduce better overall performance.<n>For the first time, we discover a surprising benefit of elevated temperatures: enhanced model robustness against common corruption, natural perturbation, and non-targeted adversarial attacks like Projected Gradient Descent.
  arXiv  Detail & Related papers  (2025-02-28T00:07:45Z)
• An Empirical Analysis of Uncertainty in Large Language Model Evaluations [28.297464655099034]
  We conduct experiments involving 9 widely used LLM evaluators across 2 different evaluation settings.<n>We pinpoint that LLM evaluators exhibit varying uncertainty based on model families and sizes.<n>We find that employing special prompting strategies, whether during inference or post-training, can alleviate evaluation uncertainty to some extent.
  arXiv  Detail & Related papers  (2025-02-15T07:45:20Z)
• Comprehensive Reassessment of Large-Scale Evaluation Outcomes in LLMs: A Multifaceted Statistical Approach [64.42462708687921]
  Evaluations have revealed that factors such as scaling, training types, architectures and other factors profoundly impact the performance of LLMs. Our study embarks on a thorough re-examination of these LLMs, targeting the inadequacies in current evaluation methods. This includes the application of ANOVA, Tukey HSD tests, GAMM, and clustering technique.
  arXiv  Detail & Related papers  (2024-03-22T14:47:35Z)
• KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models [53.84677081899392]
  KIEval is a Knowledge-grounded Interactive Evaluation framework for large language models. It incorporates an LLM-powered "interactor" role for the first time to accomplish a dynamic contamination-resilient evaluation. Extensive experiments on seven leading LLMs across five datasets validate KIEval's effectiveness and generalization.
  arXiv  Detail & Related papers  (2024-02-23T01:30:39Z)
• Dynamically Scaled Temperature in Self-Supervised Contrastive Learning [11.133502139934437]
  We focus on improving the performance of InfoNCE loss in self-supervised learning by proposing a novel cosine similarity dependent temperature scaling function. Experimental evidence shows that the proposed framework outperforms the contrastive loss-based SSL algorithms.
  arXiv  Detail & Related papers  (2023-08-02T13:31:41Z)

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.