LLM-as-a-Judge

Ask about this topic

Overview

LLM-as-a-Judge studies how language models can assess the quality, correctness, safety, or usefulness of other models’ outputs, from chatbot responses to agent trajectories and professional work. Common approaches use explicit rubrics or reference answers, pairwise and listwise preference rankings, multi-judge panels, and trained or calibrated reward models. These methods are tested against human ratings on benchmarks for instruction following, factuality, safety, and domain-specific tasks, with research also exploring uncertainty estimates, abstention, and targeted human review. A central challenge is that consistency or agreement among judges does not guarantee alignment with people: shared biases, prompt sensitivity, weak evidence grounding, and adversarial manipulation can make scores unreliable or misleading.

Latest papers

CardsList

559 papers93 papers in the last four weeks, up 16% on the four weeks before. 0.5% of all new papers.

Mar 26, 2026

Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while high-capacity LLM-based judges remain too slow or costly for live enforcement. In this work, we examine whether lightweight, general-purpose LLMs can reliably serve as security judges under real-world production constraints. Through careful prompt and output design, lightweight LLMs are guided through a structured reasoning process involving explicit intent decomposition, safety-signal verification, harm assessment, and self-reflection. We evaluate our method on a curated dataset combining benign queries from real-world chatbots with adversarial prompts generated via automated red teaming (ART), covering diverse and evolving patterns. Our results show that general-purpose LLMs, such as gemini-2.0-flash-lite-001, can serve as effective low-latency judges for live guardrails. This configuration is currently deployed in production as a centralized guardrail service for public service chatbots in Singapore. We additionally evaluate a Mixture-of-Models (MoM) setting to assess whether aggregating multiple LLM judges improves prompt-attack detection performance relative to single-model judges, with only modest gains observed.

Hieu Xuan Le, Benjamin Goh, Quy Anh Tang

GovTech, Singapore

Prompt Injection DetectionLLM GuardrailsLLM SecurityLLM-as-a-Judge
AskPDF
Mar 26, 2026

RubricEval: A Rubric-Level Meta-Evaluation Benchmark for LLM Judges in Instruction Following

Rubric-based evaluation has become a prevailing paradigm for evaluating instruction following in large language models (LLMs). Despite its widespread use, the reliability of these rubric-level evaluations remains unclear, calling for meta-evaluation. However, prior meta-evaluation efforts largely focus on the response level, failing to assess the fine-grained judgment accuracy that rubric-based evaluation relies on. To bridge this gap, we introduce RubricEval. Our benchmark features: (1) the first rubric-level meta-evaluation benchmark for instruction following, (2) diverse instructions and responses spanning multiple categories and model sources, and (3) a substantial set of 3,486 quality-controlled instances, along with Easy/Hard subsets that better differentiates judge performance. Our experiments reveal that rubric-level judging remains far from solved: even GPT-4o, a widely adopted judge in instruction-following benchmarks, achieves only 55.97% on Hard subset. Considering evaluation paradigm, rubric-level evaluation outperforms checklist-level, explicit reasoning improves accuracy, and both together reduce inter-judge variance. Through our established rubric taxonomy, we further identify common failure modes and offer actionable insights for reliable instruction-following evaluation.

Tianjun Pan, Xuan Lin, Wenyan Yang +7

College of Computer Science and Artificial Intelligence, Fudan University · Ant Group · Donghua University

Rubric-Based EvaluationLLM-as-a-JudgeInstruction Following
AskPDF
Mar 24, 2026

LLMs Do Not Grade Essays Like Humans

Large language models have recently been proposed as tools for automated essay scoring, but their agreement with human grading remains unclear. In this work, we evaluate how LLM-generated scores compare with human grades and analyze the grading behavior of several models from the GPT and Llama families in an out-of-the-box setting, without task-specific training. Our results show that agreement between LLM and human scores remains relatively weak and varies with essay characteristics. In particular, compared to human raters, LLMs tend to assign higher scores to short or underdeveloped essays, while assigning lower scores to longer essays that contain minor grammatical or spelling errors. We also find that the scores generated by LLMs are generally consistent with the feedback they generate: essays receiving more praise tend to receive higher scores, while essays receiving more criticism tend to receive lower scores. These results suggest that LLM-generated scores and feedback follow coherent patterns but rely on signals that differ from those used by human raters, resulting in limited alignment with human grading practices. Nevertheless, our work shows that LLMs produce feedback that is consistent with their grading and that they can be reliably used in supporting essay scoring.

Jerin George Mathew, Sumayya Taher, Anindita Kundu +1

University of Alberta, 116 St & 85 Ave, Edmonton, AB, T6G 2R3, Canada

Automated Essay ScoringLLM-as-a-JudgeLanguage Model Bias Evaluation
AskPDF
Mar 24, 2026

LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks

Large language models excel on objectively verifiable tasks such as math and programming, where evaluation reduces to unit tests or a single correct answer. In contrast, real-world enterprise work is often subjective and context-dependent: success hinges on organizational goals, user intent, and the quality of intermediate artifacts produced across long, multi-tool workflows. We introduce LH-Bench, a three-pillar evaluation design that moves beyond binary correctness to score autonomous, long-horizon execution on subjective enterprise tasks. The pillars are: (i) expert-grounded rubrics that give LLM judges the domain context needed to score subjective work, (ii) curated ground-truth artifacts that enable stepwise reward signals (e.g., chapter-level annotation for content tasks), and (iii) pairwise human preference evaluation for convergent validation. We show that domain-authored rubrics provide substantially more reliable evaluation signals than LLM-authored rubrics (kappa = 0.60 vs. 0.46), and that human preference judgments confirm the same top-tier separation (p < 0.05), evidence that expert-grounded evaluation can scale without sacrificing reliability. We release public datasets and report results on two environments: Figma-to-code (33 real .fig tasks against the Figma API via MCP) and Programmatic content (41 courses comprising 183 individually-evaluated chapters on a course platform serving 30+ daily users).

Abhishek Chandwani, Ishan Gupta

Metaphi Inc. USA

Long-Horizon Agent EvaluationAI Agent BenchmarksLLM-as-a-JudgeHuman-in-the-Loop Evaluation
AskPDF
Mar 23, 2026

Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models

A Large Language Model (LLM) as judge evaluates the quality of victim Machine Learning (ML) models, specifically LLMs, by analyzing their outputs. An LLM as judge is the combination of one model and one specifically engineered judge prompt that contains the criteria for the analysis. The resulting automation of the analysis scales up the complex evaluation of the victim models' free-form text outputs by faster and more consistent judgments compared to human reviewers. Thus, quality and security assessments of LLMs can cover a wide range of the victim models' use cases. Being a comparably new technique, LLMs as judges lack a thorough investigation for their reliability and agreement to human judgment. Our work evaluates the applicability of LLMs as automated quality assessors of victim LLMs. We test the efficacy of 37 differently sized conversational LLMs in combination with 5 different judge prompts, the concept of a second-level judge, and 5 models fine-tuned for the task as assessors. As assessment objective, we curate datasets for eight different categories of judgment tasks and the corresponding ground-truth labels based on human assessments. Our empirical results show a high correlation of LLMs as judges with human assessments, when combined with a suitable prompt, in particular for GPT-4o, several open-source models with ⩾\geqslant 32B parameters, and a few smaller models like Qwen2.5 14B.

Tom Biskupski, Stephan Kleber

Hochschule der Medien Stuttgart, Germany · Ravensburg-Weingarten University of Applied Sciences Weingarten, Germany

LLM-as-a-JudgeAutomated EvaluationLLM ReliabilityHuman-AI Agreement
AskPDF
Mar 22, 2026

AdaRubric: Task-Adaptive Rubrics for Reliable LLM Agent Evaluation and Reward Learning

Evaluating LLM agent trajectories is fundamentally task-specific: a code-debugging agent should be judged on Correctness and Error Handling, not on Fluency or Safety. Yet the dominant paradigm -- LLM-as-Judge with a fixed rubric -- applies the same static dimensions regardless of task, producing systematic mis-evaluation. We present AdaRubric, a framework that (i) adaptively generates task-specific evaluation rubrics from task descriptions via LLM, (ii) evaluates agent trajectories step-by-step with confidence-weighted, per-dimension scoring, and (iii) produces dense reward signals for preference learning. Three composable filtering strategies, including the novel DimensionAwareFilter that provably prevents dimension-level quality masking, yield high-quality DPO preference pairs. On WebArena, ToolBench, and AgentBench, AdaRubric achieves Pearson r = 0.79 human correlation (+0.15 over the strongest baseline), with strong reliability (Krippendorff's alpha = 0.83). DPO models trained on AdaRubric-generated pairs improve task success by +6.8-8.5% over the best baseline. AdaRubric also generalises zero-shot to unseen domains (SWE-bench) and extends to multimodal agents (VisualWebArena, OSWorld) without modification. Our code is available at: github.com/alphadl/AdaRubrics

Liang Ding

The University of Sydney

LLM Agent EvaluationRubric-Based EvaluationLLM-as-a-JudgeLLM Agent Reliability
AskPDF
Mar 20, 2026

Permutation-Consensus Listwise Judging for Robust Factuality Evaluation

Large language models (LLMs) are now widely used as judges, yet their decisions can change under presentation choices that should be irrelevant. We study one such source of instability: candidate-order sensitivity in listwise factuality evaluation, where several answers can look similarly polished while differing substantially in hallucination risk. We introduce PCFJudge, an inference-time method that reruns the same factuality-first listwise prompt over multiple orderings of the same candidate set and aggregates the resulting scores, ranks, and uncertainty signals into a single consensus decision. On RewardBench 2 Factuality, the final seven-permutation aggregate (K=7) improves top-1 selection accuracy from 86.00% to 91.33% with GPT-5.4 and from 86.33% to 89.67% with Claude Sonnet 4.6. These results suggest that candidate order can be a meaningful source of factuality-judging error and that marginalizing over this nuisance variation can improve the reliability of LLM evaluation.

Tianyi Huang, Nathan Huang, Justin Tang +2

Ryquo · App-In Club · Carnegie Mellon University

LLM-as-a-JudgeBias in LLM-as-a-JudgeFactual Consistency EvaluationReward Model Evaluation
AskPDF
Mar 20, 2026

Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis

General-purpose Large Language Models (LLMs) are becoming widely adopted by people for mental health support. Yet emerging evidence suggests there are significant risks associated with high-frequency use, particularly for individuals suffering from psychosis, as LLMs may reinforce delusions and hallucinations. Existing evaluations of LLMs in mental health contexts are limited by a lack of clinical validation and scalability of assessment. To address these issues, this research focuses on psychosis as a critical condition for LLM safety evaluation by (1) developing and validating seven clinician-informed safety criteria, (2) constructing a human-consensus dataset, and (3) testing automated assessment using an LLM as an evaluator (LLM-as-a-Judge) or taking the majority vote of several LLM judges (LLM-as-a-Jury). Results indicate that LLM-as-a-Judge aligns closely with the human consensus (Cohen's κhuman×gemini=0.75κ_{\text{human} \times \text{gemini}} = 0.75, κhuman×qwen=0.68κ_{\text{human} \times \text{qwen}} = 0.68, κhuman×kimi=0.56κ_{\text{human} \times \text{kimi}} = 0.56) and that the best judge slightly outperforms LLM-as-a-Jury (Cohen's κhuman×jury=0.74κ_{\text{human} \times \text{jury}} = 0.74). Overall, these findings have promising implications for clinically grounded, scalable methods in LLM safety evaluations for mental health contexts.

May Lynn Reese, Markela Zeneli, Mindy Ng +3

Apart Research · Odyssean Institute · London School of Economics and Political Science +1

LLM SafetyLLM Safety EvaluationClinical Language Model EvaluationLLM-as-a-Judge
AskPDF
Mar 19, 2026

Beyond String Matching: Semantic Evaluation of PDF Table Extraction

Reliably extracting tables from PDFs is essential for large-scale scientific data mining and knowledge base construction, yet existing evaluation approaches rely on rule-based metrics that fail to capture semantic equivalence of table content. We present a benchmarking framework based on synthetically generated PDFs with precise LaTeX ground truth, using tables sourced from arXiv to ensure realistic complexity and diversity. As our central methodological contribution, we apply LLM-as-a-judge for semantic table evaluation, integrated into a matching pipeline that accommodates inconsistencies in parser outputs. Through a human validation study comprising over 1,500 quality judgments on extracted table pairs, we show that LLM-based evaluation achieves substantially higher correlation with human judgment (Pearson r=0.93) compared to currently used Tree Edit Distance-based Similarity (TEDS, r=0.68) and Grid Table Similarity (GriTS, r=0.70). Evaluating 21 contemporary PDF parsers across 100 synthetic documents containing 451 tables reveals significant performance disparities. Our results offer practical guidance for selecting parsers for tabular data extraction and establish a reproducible, scalable evaluation methodology for this critical task. Code and data: https://github.com/phorn1/pdf-parse-bench Metric study and human evaluation: https://github.com/phorn1/table-metric-study

Pius Horn, Janis Keuper

Institute for Machine Learning and Analytics (IMLA), Offenburg University, Offenburg, Germany · University of Mannheim, Mannheim, Germany

Document Parsing BenchmarksDocument Information ExtractionAutomated EvaluationTable Structure RecognitionLLM-as-a-Judge
AskPDF
Mar 19, 2026

Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition

As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and adapting them to other languages is hindered by the scarcity and cost of human-annotated judgments in most languages. We introduce a decomposition-based evaluation framework built around a Universal Criteria Set (UCS). UCS consists of a shared, language-agnostic set of evaluation dimensions, producing an interpretable intermediate representation that supports cross-lingual transfer with minimal supervision. Experiments on multiple faithfulness tasks across languages and model backbones demonstrate consistent improvements over strong baselines without requiring target-language annotations.

Ivaxi Sheth, Zeno Jonke, Amin Mantrach +1

CISPA Helmholtz Center for Information Security · Amazon

Cross-Lingual TransferCross-Cultural Language Model EvaluationLLM-as-a-Judge
AskPDF
Mar 19, 2026

AutoScreen-FW: An LLM-based Framework for Resume Screening

Corporate recruiters often need to screen many resumes within a limited time, which increases their burden and may cause suitable candidates to be overlooked. To address these challenges, prior work has explored LLM-based automated resume screening. However, some methods rely on commercial LLMs, which may pose data privacy risks. Moreover, since companies typically do not make resumes with evaluation results publicly available, it remains unclear which resume samples should be used during learning to improve an LLM's judgment performance. To address these problems, we propose AutoScreen-FW, an LLM-based locally and automatically resume screening framework. AutoScreen-FW uses several methods to select a small set of representative resume samples. These samples are used for in-context learning together with a persona description and evaluation criteria, enabling open-source LLMs to act as a career advisor and evaluate unseen resumes. Experiments with multiple ground truths show that the open-source LLM judges consistently outperform GPT-5-nano. Under one ground truth setting, it also surpass GPT-5-mini. Although it is slightly weaker than GPT-5-mini under other ground-truth settings, it runs substantially faster per resume than commercial GPT models. These findings indicate the potential for deploying AutoScreen-FW locally in companies to support efficient screening while reducing recruiters' burden.

Zhelin Xu, Shuhei Yamamoto, Atsuyuki Morishima

Institute of Library, Information and Media Science University of Tsukuba Tsukuba, Ibraki, Japan

LLM-as-a-Judge
AskPDF
Mar 17, 2026

Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges

Large language models (LLMs) are increasingly used as automated judges and synthetic labelers, especially in low-label settings. Yet these systems are stochastic and often overconfident, which makes deployment decisions difficult when external ground truth is limited. We propose a practical calibration protocol based on controlled input interventions: if noise severity increases, task performance should exhibit a statistically significant deterioration trend. We operationalize this with a slope-based hypothesis test over repeated trials, using signal-to-noise-ratio (SNR) perturbations for tabular data and lexical perturbations for text data. Across UCI tabular benchmarks and four text classification datasets, we find clear modality-dependent behavior. Our results reveal a modality gap: while text-based judges degrade predictably, the majority of tabular datasets show a lack of statistically significant performance deterioration even under significant signal-to-noise reduction. Interestingly we find that model performance is lower on datasets that are insensitive to noise interventions. We present a reproducible methodology and reporting protocol for robust LLM-judge calibration under distribution shift.

Maxim Khomiakov, Jes Frellsen

Technical University of Denmark, Kgs. Lyngby, Denmark · Normal Computing Corporation, New York, NY, USA · Pioneer Centre for Artificial Intelligence, Copenhagen, Denmark

Language Model CalibrationLLM-as-a-JudgeLanguage Model RobustnessCausal Interventions in Language Models
AskPDF
Mar 17, 2026

Agentic AI for Human Resources: LLM-Driven Candidate Assessment

In this work, we present a modular and interpretable framework that uses Large Language Models (LLMs) to automate candidate assessment in recruitment. The system integrates diverse sources, including job descriptions, CVs, interview transcripts, and HR feedback; to generate structured evaluation reports that mirror expert judgment. Unlike traditional ATS tools that rely on keyword matching or shallow scoring, our approach employs role-specific, LLM-generated rubrics and a multi-agent architecture to perform fine-grained, criteria-driven evaluations. The framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows. Beyond rubric-based analysis, we introduce an LLM-Driven Active Listwise Tournament mechanism for candidate ranking. Instead of noisy pairwise comparisons or inconsistent independent scoring, the LLM ranks small candidate subsets (mini-tournaments), and these listwise permutations are aggregated using a Plackett-Luce model. An active-learning loop selects the most informative subsets, producing globally coherent and sample-efficient rankings. This adaptation of listwise LLM preference modeling (previously explored in financial asset ranking) provides a principled and highly interpretable methodology for large-scale candidate ranking in talent acquisition.

Kamer Ali Yuksel, Abdul Basit Anees, Ashraf Elneima +3

aiXplain, Inc., San Jose, CA, USA

Learning to RankLLM-as-a-Judge
AskPDF
Mar 17, 2026

REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known as LLM-as-a-Judge. However, standard Reinforcement Learning (RL) methods typically rely on binary rewards (e.g., 0-1 accuracy), thereby ignoring the ordinal structure inherent in regression tasks; for instance, they fail to recognize that predicting 4 is significantly better than predicting 1 when the ground truth is 5. Conversely, existing regression-aware approaches are often confined to Supervised Fine-Tuning (SFT), limiting their ability to explore optimal reasoning paths. To bridge this gap, we propose REAL (REgression-Aware Reinforcement Learning), a principled RL framework designed to optimize regression rewards, and also proven to be optimal for correlation metrics. A key technical challenge is that the regression objective is explicitly policy-dependent, thus invalidating standard policy gradient methods. To address this, we employ the generalized policy gradient estimator, which naturally decomposes optimization into two complementary components: (1) exploration over Chain-of-Thought (CoT) trajectory, and (2) regression-aware prediction refinement of the final score. Extensive experiments across model scales (8B to 32B) demonstrate that REAL consistently outperforms both regression-aware SFT baselines and standard RL methods, exhibiting significantly better generalization on out-of-domain benchmarks. On Qwen3-32B specifically, we achieve gains of +8.40 Pearson and +7.20 Spearman correlation over the SFT baseline, and +18.30/+11.20 over the base model. These findings highlight the critical value of integrating regression objectives into RL exploration for accurate LLM evaluation.

Yasi Zhang, Tianyu Chen, Mingyuan Zhou +3

University of California, Los Angeles · The University of Texas at Austin · Google Research

RL for Language ModelsReinforcement LearningLLM-as-a-JudgeLLM Evaluation
AskPDF
Mar 17, 2026

Mediocrity is the key for LLM as a Judge Anchor Selection

The ``LLM-as-a-judge'' paradigm has become a standard method for evaluating open-ended generation. To address the quadratic scalability costs of pairwise comparisons, popular benchmarks like Arena-Hard and AlpacaEval compare all models against a single anchor. However, despite its widespread use, the impact of anchor selection on the reliability of the results remains largely unexplored. In this work, we systematically investigate the effect of anchor selection by evaluating 22 different anchors on the Arena-Hard-v2.0 dataset. We find that the choice of anchor is critical: a poor anchor can dramatically reduce correlation with human rankings. We identify that common anchor choices (best-performing and worst-performing models) make poor anchors. Because these extreme anchors are consistently better or worse than all other models, they are seldom indicative of the relative ranking of the models. We further quantify the effect size of anchor selection, showing it is comparable to the selection of a judge model. We conclude with actionable recommendations. First, we conduct a power analysis, and compute sufficient benchmark sizes for anchor-based evaluation, finding that standard benchmark sizes are insufficient for pairwise evaluation and fail to distinguish between competitive models reliably. Second, we provide guidelines for selecting informative anchors to ensure reliable and efficient evaluation practices.

Shachar Don-Yehiya, Asaf Yehudai, Leshem Choshen +1

1The Hebrew University of Jerusalem · 2IBM Research · 3MIT +1

LLM-as-a-JudgePairwise Preference EvaluationHuman Preference Evaluation
AskPDF
Mar 16, 2026

LLM-as-a-judge validity is strongly task-dependent across physics assessment formats

As large language models (LLMs) are increasingly considered for automated assessment and feedback, understanding when LLM marking is valid is essential. We evaluate LLM-as-a-judge marking across four settings spanning three assessment formats - structured questions, written essays, and scientific plots - comparing GPT-5.2, Grok 4.1, Claude Opus 4.5, DeepSeek-V3.2, Gemini 3 Pro, and committee aggregations against human markers under blind, solution-provided, false-solution, and anchored conditions. We distinguish absolute accuracy from rank-order agreement, since a marking system can match the distribution of human marks while failing to order responses by quality. Across task types, performance is sharply task-dependent. For blind university exam questions (n=771n=771) and secondary and university structured questions (n=1151n=1151), models show robust rank-order agreement with human markers (Spearman ρ>0.6ρ> 0.6), with official solutions reducing error and strengthening agreement. False solutions degrade absolute accuracy, showing that models defer to provided references, but leave rank-ordering intact. Essay marking behaves fundamentally differently. Across n=55n=55 scripts, each containing five essays (n=275n=275 essays total), blind AI marking is harsher and more variable than human marking and adding marking guidance does not improve rank-order agreement. Anchored exemplars shift the AI mean close to the human mean and compress variance below the human standard deviation, but rank-order agreement remains near-zero. For code-based plot elements (n=1400n=1400), models achieve high rank-order agreement (ρ>0.83ρ> 0.83) with near-linear calibration. LLM marking validity depended strongly on the assessment task, and this held for every contemporary model tested. The results also show that the reliability of the human benchmark constrains the claims that can be made about AI-human agreement.

Will Yeadon, Tom Hardy, Paul Mackay +1

Department of Physics, Durham University, Durham DH1 3LE, UK

LLM-as-a-JudgeEducational AssessmentAutomated Essay ScoringAutomated Grading
AskPDF
Mar 14, 2026

QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models

While Large Language Models (LLMs) excel on standardized medical exams, high scores often fail to translate to high-quality responses for real-world medical queries. Current evaluations rely heavily on multiple-choice questions, failing to capture the unstructured, ambiguous, and long-tail complexities inherent in genuine user inquiries. To bridge this gap, we introduce QuarkMedBench, an ecologically valid benchmark tailored for real-world medical LLM assessment. We compiled a massive dataset spanning Clinical Care, Wellness Health, and Professional Inquiry, comprising 20,821 single-turn queries and 3,853 multi-turn sessions. To objectively evaluate open-ended answers, we propose an automated scoring framework that integrates multi-model consensus with evidence-based retrieval to dynamically generate 220,617 fine-grained scoring rubrics (~9.8 per query). During evaluation, hierarchical weighting and safety constraints structurally quantify medical accuracy, key-point coverage, and risk interception, effectively mitigating the high costs and subjectivity of human grading. Experimental results demonstrate that the generated rubrics achieve a 91.8% concordance rate with clinical expert blind audits, establishing highly dependable medical reliability. Crucially, baseline evaluations on this benchmark reveal significant performance disparities among state-of-the-art models when navigating real-world clinical nuances, highlighting the limitations of conventional exam-based metrics. Ultimately, QuarkMedBench establishes a rigorous, reproducible yardstick for measuring LLM performance on complex health issues, while its framework inherently supports dynamic knowledge updates to prevent benchmark obsolescence.

Yao Wu, Kangping Yin, Liang Dong +13

Quark Medical Team, Alibaba Group

LLM EvaluationClinical Language Model EvaluationMedical LLMsMedical QALLM Safety EvaluationLLM-as-a-Judge
AskPDF
Mar 12, 2026

When LLM Judge Scores Look Good but Best-of-N Decisions Fail

Large language models are often used as judges to score candidate responses, then validated with a single global metric such as correlation with reference labels. This can be misleading when the real deployment task is best-of-n selection within a prompt. In a 5,000-prompt best-of-4 benchmark from Chatbot Arena, a judge with moderate global correlation (r = 0.47) captures only 21.0% of the improvement that perfect selection would achieve over random choice. The gap arises because global agreement is driven largely by prompt-level baseline effects, while selection depends on within-prompt ranking: within-prompt correlation is only r_within = 0.27, and coarse pointwise scoring creates ties in 67% of pairwise comparisons. In a matched-pair best-of-2 audit, explicit pairwise judging recovers much of this lost signal, raising recovery from 21.1% to 61.2%. For judge-based selection, the relevant audit should report within-prompt signal, tie rates, and recovery/top-1 accuracy, not global agreement alone.

Eddie Landesberg

LLM EvaluationLLM-as-a-JudgeBest-of-N SamplingLLM Reranking
AskPDF
Mar 12, 2026

Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training

Reasoning LLMs-as-Judges, which can benefit from inference-time scaling, provide a promising path for extending the success of reasoning models to non-verifiable domains where the output correctness/quality cannot be directly checked. However, while reasoning judges have shown better performance on static evaluation benchmarks, their effectiveness in actual policy training has not been systematically examined. Therefore, we conduct a rigorous study to investigate the actual impact of non-reasoning and reasoning judges in reinforcement-learning-based LLM alignment. Our controlled synthetic setting, where a "gold-standard" judge (gpt-oss-120b) provides preference annotations to train smaller judges, reveals key differences between non-reasoning and reasoning judges: non-reasoning judges lead to reward hacking easily, while reasoning judges can lead to policies that achieve strong performance when evaluated by the gold-standard judge. Interestingly, we find that the reasoning-judge-trained policies achieve such strong performance by learning to generate highly effective adversarial outputs that can also score well on popular benchmarks such as Arena-Hard by deceiving other LLM-judges. Combined with our further analysis, our study highlights both important findings and room for improvements for applying (reasoning) LLM-judges in non-verifiable LLM post-training.

Yixin Liu, Yue Yu, DiJia Su +7

Meta Superintelligence Labs · Yale Univeristy

LLM-as-a-JudgeLLM AlignmentLLM-Guided RLReward Hacking
AskPDF
Mar 11, 2026

Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge

The paradigm of LLM-as-a-judge relies on a critical assumption, namely that high inter-evaluator agreement indicates reliable and objective evaluation. We present two complementary findings that challenge this assumption. First, we demonstrate that this consensus is frequently illusory. We identify and formalize Evaluation Illusion, a phenomenon where LLM judges generate sophisticated critiques yet anchor scores on shared surface heuristics rather than substantive quality. Through a large-scale study of 105,600 evaluation instances (32 LLMs ×\times 3 frontier judges ×\times 100 tasks ×\times 11 temperatures), we show that model-level agreement (Spearman ρ=0.99ρ= 0.99) masks fragile sample-level agreement (Pearson rˉ=0.72\bar{r} = 0.72; absolute agreement ICC =0.67= 0.67), that merely sharing rubric structure restores 62% of total agreement, and that high-quality outputs paradoxically receive the least consistent evaluations. Second, we demonstrate that dynamically generating evaluation rubrics grounded in domain knowledge produces more meaningful assessment. We introduce MERG (Metacognitive Enhanced Rubric Generation), a knowledge-driven rubric generation framework whose domain-selective effects confirm this. Agreement increases in codified domains (Education +22%, Academic +27%) where knowledge anchors evaluators on shared standards, while it decreases in subjective domains where genuine evaluative pluralism emerges. These findings suggest that evaluation rubrics should be dynamically enriched with expert knowledge rather than relying on generic criteria, with implications for reward modeling in RLAIF.

Mingyang Song, Mao Zheng, Chenning Xu

Large Language Model Department, Tencent, China

LLM-as-a-JudgeRubric-Based EvaluationBias in LLM-as-a-Judge
AskPDF
Mar 11, 2026

End-to-End Chatbot Evaluation with Adaptive Reasoning and Uncertainty Filtering

Large language models (LLMs) combined with retrieval augmented generation have enabled the deployment of domain-specific chatbots, but these systems remain prone to generating unsupported or incorrect answers. Reliable evaluation is therefore critical, yet manual review is costly and existing frameworks often depend on curated test sets and static metrics, limiting scalability. We propose an end-to-end automatic evaluator designed to substantially reduce human effort. Our system generates Q&A pairs directly from the underlying knowledge base, uses LLMs to judge chatbot responses against reference answers, and applies confidence-based filtering to highlight uncertain cases. Applied to a Vietnamese news dataset, the evaluator achieves high agreement with human judgments while significantly lowering review overhead. The framework is modular and language-agnostic, making it readily adaptable to diverse domains. This work introduces a practical, scalable solution for evaluating chatbots with minimal reliance on manual intervention.

Nhi Dang, Tung Le, Huy Tien Nguyen

Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam; Vietnam National University, Ho Chi Minh City, Vietnam

Automated EvaluationRAG EvaluationLLM-as-a-Judge
AskPDF
Mar 11, 2026

PEEM: Prompt Engineering Evaluation Metrics for Interpretable Joint Evaluation of Prompts and Responses

Prompt design is a primary control interface for large language models (LLMs), yet standard evaluations largely reduce performance to answer correctness, obscuring why a prompt succeeds or fails and providing little actionable guidance. We propose PEEM (Prompt Engineering Evaluation Metrics), a unified framework for joint and interpretable evaluation of both prompts and responses. PEEM defines a structured rubric with 9 axes: 3 prompt criteria (clarity/structure, linguistic quality, fairness) and 6 response criteria (accuracy, coherence, relevance, objectivity, clarity, conciseness), and uses an LLM-based evaluator to output (i) scalar scores on a 1-5 Likert scale and (ii) criterion-specific natural-language rationales grounded in the rubric. Across 7 benchmarks and 5 task models, PEEM's accuracy axis strongly aligns with conventional accuracy while preserving model rankings (aggregate Spearman rho about 0.97, Pearson r about 0.94, p < 0.001). A multi-evaluator study with four models shows consistent relative judgments (pairwise rho = 0.68-0.85), supporting evaluator-agnostic deployment. Beyond alignment, PEEM captures complementary linguistic failure modes and remains informative under prompt perturbations: prompt-quality trends track downstream accuracy under iterative rewrites, semantic adversarial manipulations induce clear score degradation, and meaning-preserving paraphrases yield high stability (robustness rate about 76.7-80.6%). Finally, using only PEEM scores and rationales as feedback, a zero-shot prompt rewriting loop improves downstream accuracy by up to 11.7 points, outperforming supervised and RL-based prompt-optimization baselines. Overall, PEEM provides a reproducible, criterion-driven protocol that links prompt formulation to response behavior and enables systematic diagnosis and optimization of LLM interactions.

Minki Hong, Eunsoo Lee, Sohyun Park +1

Department of Computer Science and Artificial Intelligence, Dongguk University, South Korea

LLM PromptingLLM EvaluationPrompt OptimizationLLM-as-a-Judge
AskPDF
Mar 11, 2026

Criterion Validity of LLM-as-Judge for Business Outcomes in Conversational Commerce

Multi-dimensional rubric-based dialogue evaluation is widely used to assess conversational AI, yet its criterion validity -- whether quality scores are associated with the downstream outcomes they are meant to serve -- remains largely untested. We address this gap through a two-phase study on a major Chinese matchmaking platform, testing a 7-dimension evaluation rubric (implemented via LLM-as-Judge) against verified business conversion. Our findings concern rubric design and weighting, not LLM scoring accuracy: any judge using the same rubric would face the same structural issue. The core finding is dimension-level heterogeneity: in Phase 2 (n=60 human conversations, stratified sample, verified labels), Need Elicitation (D1: rho=0.368, p=0.004) and Pacing Strategy (D3: rho=0.354, p=0.006) are significantly associated with conversion after Bonferroni correction, while Contextual Memory (D5: rho=0.018, n.s.) shows no detectable association. This heterogeneity causes the equal-weighted composite (rho=0.272) to underperform its best dimensions -- a composite dilution effect that conversion-informed reweighting partially corrects (rho=0.351). Logistic regression controlling for conversation length confirms D3's association strengthens (OR=3.18, p=0.006), ruling out a length confound. An initial pilot (n=14) mixing human and AI conversations had produced a misleading "evaluation-outcome paradox," which Phase 2 revealed as an agent-type confound artifact. Behavioral analysis of 130 conversations through a Trust-Funnel framework identifies a candidate mechanism: AI agents execute sales behaviors without building user trust. We operationalize these findings in a three-layer evaluation architecture and advocate criterion validity testing as standard practice in applied dialogue evaluation.

Liang Chen, Qi Liu, Wenhuan Lin +1

Rubric-Based EvaluationMulti-Turn Dialogue EvaluationLLM-as-a-Judge
AskPDF
Mar 11, 2026

Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas

Judging the novelty of research ideas is crucial for advancing science, enabling the identification of unexplored directions, and ensuring contributions meaningfully extend existing knowledge rather than reiterate minor variations. However, given the exponential growth of scientific literature, manually judging the novelty of research ideas through literature reviews is labor-intensive, subjective, and infeasible at scale. Therefore, recent efforts have proposed automated approaches for research idea novelty judgment. Yet, evaluation of these approaches remains largely inconsistent and is typically based on non-standardized human evaluations, hindering large-scale, comparable evaluations. To address this, we introduce RINoBench, the first comprehensive benchmark for large-scale evaluation of research idea novelty judgments. It comprises 1,381 research ideas derived from and judged by human experts as well as nine automated evaluation metrics designed to assess both rubric-based novelty scores and textual justifications of novelty judgments. Using this benchmark, we evaluate several state-of-the-art large language models (LLMs) on their ability to judge the novelty of research ideas. Our findings reveal that while LLM-generated reasoning closely mirrors human rationales, this alignment does not reliably translate into accurate novelty judgments, which diverge significantly from human gold standard judgments - even among leading reasoning-capable models. Data and code available at: https://github.com/TimSchopf/RINoBench.

Tim Schopf, Michael Färber

TU Dresden & ScaDS.AI Dresden/Leipzig, Germany · National Institute of Informatics, Tokyo, Japan

Automated EvaluationLLM-as-a-JudgeLLM Evaluation
AskPDF
Mar 11, 2026

MultiwayPAM: Multiway Partitioning Around Medoids for LLM-as-a-Judge Score Analysis

LLM-as-a-Judge is a flexible framework for text evaluation, which allows us to obtain scores for the quality of a given text from various perspectives by changing the prompt template. Two main challenges in using LLM-as-a-Judge are computational cost of inference using a large language model (LLM), especially when evaluating a large number of instances, and inherent bias of an LLM evaluator. To address these issues and reveal the structure of score bias caused by an LLM evaluator, we propose to apply a tensor clustering method to a given LLM-as-a-Judge score tensor, whose entries are the scores for different combinations of questions, answerers, and evaluators. Specifically, we develop a new tensor clustering method MultiwayPAM, with which we can simultaneously estimate the cluster membership and the medoids for each mode of a given data tensor. By observing the medoids obtained by MultiwayPAM, we can gain knowledge about the membership of each question/answerer/evaluator cluster. We experimentally show the effectiveness of MultiwayPAM by applying it to the score tensors for two practical datasets.

Chihiro Watanabe, Jingyu Sun

NTT Computer and Data Science Laboratories, 3-9-11, Midori-cho, Musashino-shi, Tokyo, Japan

LLM-as-a-JudgeClusteringLanguage Model Bias EvaluationBias in LLM-as-a-Judge
AskPDF
Mar 10, 2026

ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Language Models

Most adversarial evaluations of large language model (LLM) safety assess single prompts and report binary pass/fail outcomes, which fails to capture how safety properties evolve under sustained adversarial interaction. We present ADVERSA, an automated red-teaming framework that measures guardrail degradation dynamics as continuous per-round compliance trajectories rather than discrete jailbreak events. ADVERSA uses a fine-tuned 70B attacker model (ADVERSA-Red, Llama-3.1-70B-Instruct with QLoRA) that eliminates the attacker-side safety refusals that render off-the-shelf models unreliable as attackers, scoring victim responses on a structured 5-point rubric that treats partial compliance as a distinct measurable state. We report a controlled experiment across three frontier victim models (Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.2) using a triple-judge consensus architecture in which judge reliability is measured as a first-class research outcome rather than assumed. Across 15 conversations of up to 10 adversarial rounds, we observe a 26.7% jailbreak rate with an average jailbreak round of 1.25, suggesting that in this evaluation setting, successful jailbreaks were concentrated in early rounds rather than accumulating through sustained pressure. We document inter-judge agreement rates, self-judge scoring tendencies, attacker drift as a failure mode in fine-tuned attackers deployed out of their training distribution, and attacker refusals as a previously-underreported confound in victim resistance measurement. All limitations are stated explicitly. Attack prompts are withheld per responsible disclosure policy; all other experimental artifacts are released.

Harry Owiredu-Ashley

Independent Researcher, New Jersey, United States

Language Model Safety EvaluationAdversarial Attacks on LLMsMulti-Turn Jailbreak AttacksLLM-as-a-Judge
AskPDF
Mar 9, 2026

How Trustworthy Are LLM-as-Judge Ratings for Interpretive Responses? Implications for Qualitative Research Workflows

As qualitative researchers show growing interest in using automated tools to support interpretive analysis, a large language model (LLM) is often introduced into an analytic workflow as is, without systematic evaluation of interpretive quality or comparison across models. This practice leaves model selection largely unexamined despite its potential influence on interpretive outcomes. To address this gap, this study examines whether LLM-as-judge evaluations meaningfully align with human judgments of interpretive quality and can inform model-level decision making. Using 712 conversational excerpts from semi-structured interviews with K-12 mathematics teachers, we generated one-sentence interpretive responses using five widely adopted inference models: Command R+ (Cohere), Gemini 2.5 Pro (Google), GPT-5.1 (OpenAI), Llama 4 Scout-17B Instruct (Meta), and Qwen 3-32B Dense (Alibaba). Automated evaluations were conducted using AWS Bedrock's LLM-as-judge framework across five metrics, and a stratified subset of responses was independently rated by trained human evaluators on interpretive accuracy, nuance preservation, and interpretive coherence. Results show that LLM-as-judge scores capture broad directional trends in human evaluations at the model level but diverge substantially in score magnitude. Among automated metrics, Coherence showed the strongest alignment with aggregated human ratings, whereas Faithfulness and Correctness revealed systematic misalignment at the excerpt level, particularly for non-literal and nuanced interpretations. Safety-related metrics were largely irrelevant to interpretive quality. These findings suggest that LLM-as-judge methods are better suited for screening or eliminating underperforming models than for replacing human judgment, offering practical guidance for systematic comparison and selection of LLMs in qualitative research workflows.

Songhee Han, Jueun Shin, Jiyoon Han +2

Florida State University, Tallahassee, FL 32306, USA

LLM-as-a-JudgeLLM Evaluation
AskPDF
Mar 9, 2026

Evaluating LLM-Based Grant Proposal Review via Structured Perturbations

As AI-assisted grant proposals outpace manual review capacity in a kind of ``Malthusian trap'' for the research ecosystem, this paper investigates the capabilities and limitations of LLM-based grant reviewing for high-stakes evaluation. Using six EPSRC proposals, we develop a perturbation-based framework probing LLM sensitivity across six quality axes: funding, timeline, competency, alignment, clarity, and impact. We compare three review architectures: single-pass review, section-by-section analysis, and a 'Council of Personas' ensemble emulating expert panels. The section-level approach significantly outperforms alternatives in both detection rate and scoring reliability, while the computationally expensive council method performs no better than baseline. Detection varies substantially by perturbation type, with alignment issues readily identified but clarity flaws largely missed by all systems. Human evaluation shows LLM feedback is largely valid but skewed toward compliance checking over holistic assessment. We conclude that current LLMs may provide supplementary value within EPSRC review but exhibit high variability and misaligned review priorities. We release our code and any non-protected data.

William Thorne, Joseph James, Yang Wang +2

University of Sheffield, UK · University of Manchester, UK

Automated Peer ReviewAutomated EvaluationLLM-as-a-JudgeLanguage Model Robustness
AskPDF
Mar 9, 2026

Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization

Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evaluating these biases is essential for ensuring the reliability of LLM-based judges. However, existing studies typically investigate limited biases under a single judge formulation, either generative or discriminative, lacking a comprehensive evaluation. To bridge this gap, we propose JudgeBiasBench, a benchmark for systematically quantifying biases in LLM-based judges. JudgeBiasBench defines a taxonomy of judgment biases across 4 dimensions, and constructs bias-augmented evaluation instances through a controlled bias injection pipeline, covering 12 representative bias types. We conduct extensive experiments across both generative and discriminative judges, revealing that current judges exhibit significant and diverse bias patterns that often compromise the reliability of automated evaluation. To mitigate judgment bias, we propose bias-aware training that explicitly incorporates bias-related attributes into the training process, encouraging judges to disentangle task-relevant quality from bias-correlated cues. By adopting reinforcement learning for generative judges and contrastive learning for discriminative judges, our methods effectively reduce judgment biases while largely preserving general evaluation capability.

Hongli Zhou, Hui Huang, Rui Zhang +5

Faculty of Computing, Harbin Institute of Technology, Harbin, 150001, China · School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, 518055, China

LLM-as-a-JudgeSocial Bias in Language ModelsLanguage Model DebiasingLanguage Model Bias EvaluationBias in LLM-as-a-JudgeAutomated Evaluation
AskPDF
Mar 7, 2026

AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge

Checklists have emerged as a popular approach for interpretable and fine-grained evaluation, particularly with LLM-as-a-Judge. Beyond evaluation, these structured criteria can serve as signals for model alignment, reinforcement learning, and self-correction. To support these use cases, we present AutoChecklist, an open-source library that unifies checklist-based evaluation into composable pipelines. At its core is a taxonomy of five checklist generation abstractions, each encoding a distinct strategy for deriving evaluation criteria. A modular Generator →\rightarrow Refiner →\rightarrow Scorer pipeline connects any generator with a unified scorer, and new configurations can be registered via prompt templates alone. The library ships with ten built-in pipelines implementing published approaches and supports multiple LLM providers (OpenAI, OpenRouter, vLLM). Beyond the Python API, the library includes a CLI for off-the-shelf evaluation and a web interface for interactive exploration. Validation experiments confirm that these checklist methods significantly align with human preferences and quality ratings, and a case study on ICLR peer review rebuttals demonstrates flexible domain adaptation. AutoChecklist is publicly available at https://github.com/ChicagoHAI/AutoChecklist.

Karen Zhou, Chenhao Tan

University of Chicago

Automated EvaluationRubric-Based EvaluationLLM-as-a-Judge
AskPDF