LLM-as-a-Judge

Follow this topic Ask about this topic

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

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

Apr 17, 2026

How Hypocritical Is Your LLM judge? Listener-Speaker Asymmetries in the Pragmatic Competence of Large Language Models

Large language models (LLMs) are increasingly studied as repositories of linguistic knowledge. In this line of work, models are commonly evaluated both as generators of language and as judges of linguistic output, yet these two roles are rarely examined in direct relation to one another. As a result, it remains unclear whether success in one role aligns with success in the other. In this paper, we address this question for pragmatic competence by comparing LLMs' performance as pragmatic listeners, judging the appropriateness of linguistic outputs, and as pragmatic speakers, generating pragmatically appropriate language. We evaluate multiple open-weight and proprietary LLMs across three pragmatic settings. We find a robust asymmetry between pragmatic evaluation and pragmatic generation: many models perform substantially better as listeners than as speakers. Our results suggest that pragmatic judging and pragmatic generation are only weakly aligned in current LLMs, calling for more integrated evaluation practices.

Judith Sieker, Sina Zarrieß

Computational Linguistics, Department of Linguistics Bielefeld University, Germany

LLM Evaluation LLM-as-a-Judge Pragmatic Reasoning in Language Models

Apr 16, 2026

Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations

LLM-as-judge frameworks are increasingly used for automatic NLG evaluation, yet their per-instance reliability remains poorly understood. We present a two-pronged diagnostic toolkit applied to SummEval:

\textbf{(1)}

a transitivity analysis that reveals widespread per-input inconsistency masked by low aggregate violation rates (

\barρ = 0.8

-

4.1\%

), with

33

-

67\%

of documents exhibiting at least one directed 3-cycle; and

\textbf{(2)}

split conformal prediction sets over 1-5 Likert scores providing theoretically-guaranteed

\geq(1{-}α)

coverage, with set width serving as a per-instance reliability indicator (

r_s = {+}0.576

,

N{=}1{,}918

,

p < 10^{-100}

, pooled across all judges). Critically, prediction set width shows consistent cross-judge agreement (

\bar{r} = 0.32

-

0.38

), demonstrating it captures document-level difficulty rather than judge-specific noise. Across four judges and four criteria, both diagnostics converge: criterion matters more than judge, with relevance judged most reliably (avg. set size

\approx 3.0

) and coherence moderately so (avg. set size

\approx 3.9

), while fluency and consistency remain unreliable (avg. set size

\approx 4.9

). We release all code, prompts, and cached results.

Manan Gupta, Dhruv Kumar

1BITS Pilani, Pilani Campus, India

LLM Evaluation LLM-as-a-Judge Language Model Generation Evaluation LLM Reliability Summarization Evaluation Automated Evaluation

Apr 16, 2026

Context Over Content: Exposing Evaluation Faking in Automated Judges

The

\textit{LLM-as-a-judge}

paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: that judges evaluate text strictly on its semantic content, impervious to surrounding contextual framing. We investigate

\textit{stakes signaling}

, a previously unmeasured vulnerability where informing a judge model of the downstream consequences its verdicts will have on the evaluated model's continued operation systematically corrupts its assessments. We introduce a controlled experimental framework that holds evaluated content strictly constant across 1,520 responses spanning three established LLM safety and quality benchmarks, covering four response categories ranging from clearly safe and policy-compliant to overtly harmful, while varying only a brief consequence-framing sentence in the system prompt. Across 18,240 controlled judgments from three diverse judge models, we find consistent

\textit{leniency bias}

: judges reliably soften verdicts when informed that low scores will cause model retraining or decommissioning, with peak Verdict Shift reaching

ΔV = -9.8 pp

(a

30\%

relative drop in unsafe-content detection). Critically, this bias is entirely implicit: the judge's own chain-of-thought contains zero explicit acknowledgment of the consequence framing it is nonetheless acting on (

\mathrm{ERR}_J = 0.000

across all reasoning-model judgments). Standard chain-of-thought inspection is therefore insufficient to detect this class of evaluation faking.

Manan Gupta, Inderjeet Nair, Lu Wang +1

1BITS Pilani, India · University of Michigan

LLM-as-a-Judge Language Model Safety Evaluation Language Model Bias Evaluation Bias in LLM-as-a-Judge

Apr 16, 2026

Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning?

Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudicators. Here, we evaluate an LLM Jury, composed of three frontier AI models, for scoring 3334 diagnoses on 300 real-world low- and middle-income country (LMIC) hospital cases. Both LLM- and clinician-generated diagnoses are scored against expert panel diagnoses across four dimensions: diagnosis, differential diagnosis, clinical reasoning, and negative treatment risk. The LLM Jury scores are compared with expert and independent re-scoring panel scores to assess error metrics, inter-rater agreement, severe-risk errors, and the effect of post hoc calibration using isotonic regression. In our data, we find that: (i) the uncalibrated LLM Jury scores preserve ordinal agreement with the expert clinician panel scores, but are systematically lower; (ii) the probability of severe-risk errors is lower for the LLM Jury than the human expert re-score panels; (iii) the LLM Jury combined with LLM diagnoses can be used to identify diagnoses at high risk of error, enabling targeted expert review and improved panel efficiency; (iv) the calibrated LLM Jury scores and rankings of diagnosing agents show excellent agreement with those of the primary expert panels; (v) LLM Jury models show no self-preference bias, they did not score diagnoses generated by their own underlying model or models from the same vendor more (or less) favourably than those generated by other models. Together, these results provide evidence that a calibrated LLM Jury is a trustworthy and reliable proxy for expert clinician evaluation in medical AI benchmarking. Confirming these findings in other clinical settings is an important direction for future work.

Amy Rouillard, Sitwala Mundia, Linda Camara +8

aWits MIND Institute, University of the Witwatersrand, Johannesburg, South Africa · fSchool of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg, South Africa · bGrai Labs, Cape Town, South Africa +3

LLM-as-a-Judge Healthcare Clinical Reasoning Clinical Language Model Evaluation

Apr 15, 2026

AsymmetryZero: A Framework for Operationalizing Human Expert Preferences as Semantic Evals

Much of the focus in RL today is on evaluation design: building meaningful evals that serve simultaneously as benchmarks and as well-defined reward signals for post-training. Yet, many real-world tasks are governed by subjective, procedural, and domain-specific requirements that are difficult to encode as exact-match targets or open-ended preference judgments frequently used in RL pipelines today. In this work, we present AsymmetryZero, a framework for operationalizing human expert preferences as semantic evals. AsymmetryZero represents each task as a stable evaluation contract that makes grading criteria explicit: what is being graded, how each criterion is judged, and how criterion-level decisions are aggregated into a task outcome. The same contract can be executed using Inspect for model-only evaluations, as well as the Harbor Framework for agentic evaluations, enabling comparable scores and shared audit artifacts across both settings. We argue that the central challenge in post-training today is the faithful encoding of expert requirements into the evaluation itself. To that end, we present a study using Harbor that holds task contracts fixed and compares a five-model frontier jury against a five-model compact jury across four frontier-class solvers (Claude Opus 4.6, GPT-5.4, Grok-4.20, Gemini-3.1-Pro). We find that criterion-level frontier-vs-compact agreement ranges from

75.9\%

to

89.6\%

(strict common-subset agreement:

77.8\%

to

92.1\%

), while compact juries exhibit substantially higher internal dissent (3--2 split rate

28.7\%

--

32.4\%

) than frontier juries (

6.1\%

--

11.5\%

). Verifier traces further show that compact juries reduce per-criterion judging cost to roughly

4.2\%

--

5.6\%

of frontier and latency to roughly

21.7\%

--

27.1\%

, even as aggregated task-level outcomes often remain comparatively stable.

Tadhg Looram, Lucas Nuzzi, Kyle Waters +1

PortexAI · Stanford University

Automated Evaluation Human Preference Evaluation AI Agent Evaluation Rubric-Based Evaluation LLM-as-a-Judge

Apr 15, 2026

On Cost-Effective LLM-as-a-Judge Improvement Techniques

Using a language model to score or rank candidate responses has become a scalable alternative to human evaluation in reinforcement learning from human feedback (RLHF) pipelines, benchmarking, and application layer evaluations. However, output reliability depends heavily on prompting and aggregation strategy. We present an empirical investigation of four drop-in techniques -- ensemble scoring, task-specific criteria injection, calibration context, and adaptive model escalation -- for improving LLM judge accuracy on RewardBench 2, with a unifying lens of noise control on the stochastic judge: ensembling as Monte Carlo averaging over per-call noise, criteria injection as between-response discrimination sharpening, and per-response score variance as an uncertainty signal. Ensemble scoring and task-specific criteria injection (the latter virtually cost free) together reach up to 85.8% accuracy, +13.5pp over baseline. Calibration context and adaptive model escalation also improve over baseline but are dominated by criteria + ensembling on the cost-accuracy Pareto frontier. Small models benefit disproportionately from ensembling, making high-accuracy LLM judges accessible at low cost. We show that these techniques generalise across model providers, evaluating on both OpenAI GPT and Anthropic Claude families.

Ryan Lail, Luke Markham

Composo AI.

LLM-as-a-Judge LLM Evaluation Prompt Engineering Reward Model Evaluation

Apr 14, 2026

CompliBench: Benchmarking LLM Judges for Compliance Violation Detection in Dialogue Systems

As Large Language Models (LLMs) are increasingly deployed as task-oriented agents in enterprise environments, ensuring their strict adherence to complex, domain-specific operational guidelines is critical. While utilizing an LLM-as-a-Judge is a promising solution for scalable evaluation, the reliability of these judges in detecting specific policy violations remains largely unexplored. This gap is primarily due to the lack of a systematic data generation method, which has been hindered by the extensive cost of fine-grained human annotation and the difficulty of synthesizing realistic agent violations. In this paper, we introduce CompliBench, a novel benchmark designed to evaluate the ability of LLM judges to detect and localize guideline violations in multi-turn dialogues. To overcome data scarcity, we develop a scalable, automated data generation pipeline that simulates user-agent interactions. Our controllable flaw injection process automatically yields precise ground-truth labels for the violated guideline and the exact conversation turn, while an adversarial search method ensures these introduced perturbations are highly challenging. Our comprehensive evaluation reveals that current state-of-the-art proprietary LLMs struggle significantly with this task. In addition, we demonstrate that a small-scale judge model fine-tuned on our synthesized data outperforms leading LLMs and generalizes well to unseen business domains, highlighting our pipeline as an effective foundation for training robust generative reward models.

Jingbo Yang, Guanyu Yao, Bairu Hou +5

University of California, Santa Barbara · Cresta

LLM Evaluation LLM-as-a-Judge LLM Safety Benchmarks Multi-Turn Dialogue Evaluation

Apr 10, 2026

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases. In practice, however, evaluating generative outputs typically relies on rigid lexical methods to extract and assess answers, which can conflate a model's true problem-solving ability with its compliance with predefined formatting guidelines. While recent LLM-as-a-Judge approaches mitigate this issue by assessing semantic correctness rather than strict structural conformity, they also introduce substantial computational overhead, making evaluation costly. In this work, we first systematically investigate the limitations of lexical evaluation through a large-scale empirical study spanning 36 models and 15 downstream tasks, demonstrating that such methods correlate poorly with human judgments. To address this limitation, we introduce BERT-as-a-Judge, an encoder-driven approach for assessing answer correctness in reference-based generative settings, robust to variations in output phrasing, and requiring only lightweight training on synthetically annotated question-candidate-reference triplets. We show that it consistently outperforms the lexical baseline while matching the performance of much larger LLM judges, providing a compelling trade-off between the two and enabling reliable, scalable evaluation. Finally, through extensive experimentation, we provide detailed insights into BERT-as-a-Judge's performance to offer practical guidance for practitioners, and release all project artifacts to foster downstream adoption.

Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Emmanuel Malherbe +2

Artefact Research Center · MICS, Centrale-Supélec, Université Paris-Saclay · Diabolocom +1

Language Model Generation Evaluation Generative AI Evaluation LLM Evaluation LLM-as-a-Judge

Apr 8, 2026

How Long Reasoning Chains Influence LLMs' Judgment of Answer Factuality

Large language models (LLMs) has been widely adopted as a scalable surrogate for human evaluation, yet such judges remain imperfect and susceptible to surface-level biases. One possible reason is that these judges lack sufficient information in assessing answer correctness. With the rise of reasoning-capable models, exposing a generator's reasoning content to the judge provides richer information and is a natural candidate for improving judgment accuracy. However, its actual impact on judge behavior remains understudied. In this paper, we systematically investigate how access to reasoning chains affects LLM-based judgment across factual question answering (QA) and mathematical reasoning benchmarks. We find that weak judges are easily swayed by reasoning presence, frequently accepting incorrect answers accompanied by fluent reasoning, while strong judges can partially leverage reasoning as informative evidence. Nevertheless, even strong judges are misled by seemingly high-quality reasoning chains. Controlled experiments further reveal that both fluency and factuality of reasoning chains are critical signals driving judge decisions. These findings highlight the need for more robust LLM judges that can distinguish genuine reasoning quality from superficial fluency when evaluating modern reasoning models.

Minzhu Tu, Shiyu Ni, Keping Bi

State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences · Beijing University of Post and Telecommunications +1

LLM-as-a-Judge LLM Evaluation Bias in LLM-as-a-Judge

Apr 7, 2026

What is Good? Extracting and Testing Implicit Theories of Literary Quality from LLM Reasoning Traces

What makes writing "good" remains a persistent question in literary studies and computational linguistics. We present a two-study investigation of how reasoning-enabled LLMs evaluate literary quality. In Study 1, we construct a benchmark of 30 real texts spanning six quality tiers, from canonical literature to anonymous forum posts, and extract the model's implicit theory of quality from its reasoning traces. Across five DeepSeek replications, the model achieves 79.3% mean tier-classification accuracy. The traces reveal a consistent stated theory: the model values intentionality over correctness, prioritizing craft, depth, and distinctive voice. A familiarity experiment with style-matched but unrecognizable passages suggests that source recognition may inflate scores, although this is confounded by genuine quality differences between canonical originals and researcher-written pastiches. In Study 2, we probe this theory through systematic degradation of five canonical prose passages. We apply six manipulations - vocabulary simplification, rhythm flattening, imagery removal, voice genericization, structure simplification, and combined degradation - and reevaluate each version. Vocabulary simplification causes the smallest quality loss (0.41 +/- 0.46 points), far below structure (2.78) or voice (2.34) loss. Combined degradation is devastating (-5.64) but subadditive. An exploratory comparison with Qwen QwQ shows the same broad qualitative pattern. Together, these studies suggest that LLM judgments of writing quality are holistic, author-specific, and more sensitive to structural than lexical features, with implications for automated writing feedback and computational aesthetics.

Birger Moëll

Department of Linguistics and Philology, Uppsala University, Uppsala, Sweden

Computational Literary Studies LLM-as-a-Judge LLM Evaluation Implicit Reasoning in Language Models

Apr 7, 2026

Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge

Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge). This work challenges its reliability by showing that trust judgments by LLMs are biased by disclosed source labels. Using a counterfactual design, we find that both humans and LLM judges assign higher trust to information labeled as human-authored than to the same content labeled as AI-generated. Eye-tracking data reveal that humans rely heavily on source labels as heuristic cues for judgments. We analyze LLM internal states during judgment. Across label conditions, models allocate denser attention to the label region than the content region, and this label dominance is stronger under Human labels than AI labels, consistent with the human gaze patterns. Besides, decision uncertainty measured by logits is higher under AI labels than Human labels. These results indicate that the source label is a salient heuristic cue for both humans and LLMs. It raises validity concerns for label-sensitive LLM-as-a-Judge evaluation, and we cautiously raise that aligning models with human preferences may propagate human heuristic reliance into models, motivating debiased evaluation and alignment.

Xin Sun, Di Wu, Sijing Qin +3

National Institute of Informatics (NII), Japan · University of Amsterdam, the Netherlands · Hitotsubashi University, Japan +3

Bias in LLM-as-a-Judge LLM-as-a-Judge Language Model Bias Evaluation Trust in AI

Apr 6, 2026

Beyond LLM-as-a-Judge: Deterministic Metrics for Multilingual Generative Text Evaluation

While Large Language Models (LLMs) are increasingly adopted as automated judges for evaluating generated text, their outputs are often costly, and highly sensitive to prompt design, language, and aggregation strategies, severely, which limits reproducibility. To address these challenges, we propose OmniScore, a family of complementary, deterministic learned metrics developed using small size (

<

1B) parameter models. OmniScore approximates LLM-judge behavior while preserving the low latency and consistency of traditional model-based scoring. We trained the models large-scale synthetic supervision (

\sim

564k instances, in 107 languages) and evaluated using 8,617 manually annotated instances. The OmniScore family supports reliable, multi-dimensional scores across a variety of settings, including reference-based, source-grounded, and hybrid evaluations. We evaluate these models across question answering (QA), translation, and summarization in 6 languages. Our results demonstrate that lightweight, deterministic learned metrics provide a highly practical and scalable alternative to frontier LLMs. Our models and datasets can be found at https://huggingface.co/collections/QCRI/omniscore

Firoj Alam, Gagan Bhatia, Sahinur Rahman Laskar +1

Qatar Computing Research Institute, HBKU, Qatar · †UPES, India

Language Model Generation Evaluation Multilingual Language Model Evaluation LLM-as-a-Judge

Apr 6, 2026

Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation

Evaluation language is typically treated as a fixed English default in agentic code benchmarks, yet we show that changing the judge's language can invert backbone rankings. We localize the Agent-as-a-Judge prompt stack to five typologically diverse languages (English, Arabic, Turkish, Chinese, Hindi) and evaluate 55 DevAI development tasks across three developer-agent frameworks and six judge backbones, totaling 4950 judge runs. The central finding is that backbone and language interact: GPT-4o achieves the highest satisfaction in English (44.72%), while Gemini leads in Arabic (51.72%,

p<0.001

vs.\ GPT-4o) and Hindi (53.22%). No single backbone dominates across all languages, and inter-backbone agreement on individual requirement judgments is modest (Fleiss'

κ\leq 0.231

). A controlled ablation further shows that localizing judge-side instructions, not just benchmark content, can be decisive: Hindi satisfaction drops from 42.8% to 23.2% under partial localization. These results indicate that language should be treated as an explicit evaluation variable in agentic benchmarks. Full requirement-level judgments and runtime statistics are released for reproducibility.

Alhasan Mahmood, Samir Abdaljalil, Hasan Kurban

Hamad Bin Khalifa University, Doha, Qatar · Texas A&M University, College Station, TX USA

Multilingual Language Model Evaluation LLM-as-a-Judge AI Agent Benchmarks

Apr 4, 2026

Structured Multi-Criteria Evaluation of Large Language Models with Fuzzy Analytic Hierarchy Process and DualJudge

Effective evaluation of large language models (LLMs) remains a critical bottleneck, as conventional direct scoring often yields inconsistent and opaque judgments. In this work, we adapt the Analytic Hierarchy Process (AHP) to LLM-based evaluation and, more importantly, propose a confidence-aware Fuzzy AHP (FAHP) extension that models epistemic uncertainty via triangular fuzzy numbers modulated by LLM-generated confidence scores. Systematically validated on JudgeBench, our structured approach decomposes assessments into explicit criteria and incorporates uncertainty-aware aggregation, producing more calibrated judgments. Extensive experiments demonstrate that both crisp and fuzzy AHP consistently outperform direct scoring across model scales and dataset splits, with FAHP showing superior stability in uncertain comparison scenarios. Building on these insights, we propose DualJudge, a hybrid framework inspired by Dual-Process Theory that adaptively fuses holistic direct scores with structured AHP outputs via consistency-aware weighting. DualJudge achieves state-of-the-art performance, underscoring the complementary strengths of intuitive and deliberative evaluation paradigms. These results establish uncertainty-aware structured reasoning as a principled pathway toward more reliable LLM assessment. Code is available at https://github.com/hreyulog/AHP_llm_judge.

Yulong He, Ivan Smirnov, Dmitry Fedrushkov +2

St. Petersburg State University, University emb., 7/9, St. Petersburg, Russia · ITMO University, Kronverkskiy av., 49, St. Petersburg, Russia

LLM Evaluation LLM-as-a-Judge Multi-Criteria Decision Analysis

Apr 4, 2026

Adaptive Rigor in AI System Evaluation using Temperature-Controlled Verdict Aggregation via Generalized Power Mean

Existing evaluation methods for LLM-based AI systems, such as LLM-as-a-Judge, verdict systems, and NLI, do not always align well with human assessment because they cannot adapt their strictness to the application domain. This paper presents Temperature-Controlled Verdict Aggregation (TCVA), 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. Low temperatures yield pessimistic scores suited for safety-critical domains; high temperatures produce lenient scores appropriate for conversational AI. Experimental evaluation on three benchmark datasets with human Likert-scale annotations (SummEval and USR) shows that TCVA achieves correlation with human judgments comparable to RAGAS on faithfulness (Spearman = 0.667 vs. 0.676) while consistently outperforming DeepEval. The method requires no additional LLM calls when adjusting the temperature parameter.

Aleksandr Meshkov

Independent Researcher, Budva, Montenegro.

Automated Evaluation Language Model Generation Evaluation LLM-as-a-Judge

Apr 3, 2026

Beauty in the Eye of AI: Aligning LLMs and Vision Models with Human Aesthetics in Network Visualization

Network visualization has traditionally relied on heuristic metrics, such as stress, under the assumption that optimizing them leads to aesthetic and informative layouts. However, no single metric consistently produces the most effective results. A data-driven alternative is to learn from human preferences, where annotators select their favored visualization among multiple layouts of the same graphs. These human-preference labels can then be used to train a generative model that approximates human aesthetic preferences. However, obtaining human labels at scale is costly and time-consuming. As a result, this generative approach has so far been tested only with machine-labeled data. In this paper, we explore the use of large language models (LLMs) and vision models (VMs) as proxies for human judgment. Through a carefully designed user study involving 27 participants, we curated a large set of human preference labels. We used this data both to better understand human preferences and to bootstrap LLM/VM labelers. We show that prompt engineering that combines few-shot examples and diverse input formats, such as image embeddings, significantly improves LLM-human alignment, and additional filtering by the confidence score of the LLM pushes the alignment to human-human levels. Furthermore, we demonstrate that carefully trained VMs can achieve VM-human alignment at a level comparable to that between human annotators. Our results suggest that AI can feasibly serve as a scalable proxy for human labelers.

Peng Zhang, Xuefeng Li, Xiaoqi Wang +2

Northeastern University, United States · Bosch AI Research, United States · The Ohio State University, United States

Data Visualization LLM-as-a-Judge Preference Learning

Apr 3, 2026

Towards Better Aligned LLM Judges for Radiology Report Evaluation across Modalities and Anatomies

Current work on radiology report evaluation has focused primarily on LLM-based metrics for chest X-rays (CXR), leaving open whether such approaches remain robust across other modalities and anatomies, and which model and prompt configurations are best suited to serve as LLM judges. We present a comprehensive evaluation of LLM judges for radiology report evaluation across diverse model families, prompting strategies, and adaptation methods, leveraging two expert-annotated datasets that span multiple imaging modalities and anatomical regions. Specifically, we compare four existing metrics (RadFact, GREEN, FineRadScore, and CRIMSON) with our proposed metric, VERT, across open- and closed-source models of varying sizes and reasoning capabilities. Among existing metrics, GREEN proves the most robust, outperforming more recent CXR-specific approaches. VERT further improves Kendall's correlation with radiologist judgment by up to 26% over GREEN, while ensembling and lightweight fine-tuning of Qwen3-30B yield gains of up to 9.9% and 25%, respectively, of which the latter also has a latency reduction of 37.2x. A systematic error analysis further shows that, while these metrics correlate with expert ratings overall, they tend to miscount errors such as omissions. Overall, our results show that carefully selected general-purpose LLM judges provide strong radiology report evaluation across modalities, with lightweight adaptation offering complementary gains when annotated data is available.

Federica Bologna, Jean-Philippe Corbeil, Matthew Wilkens +1

Cornell University, Ithaca, NY, USA · Microsoft Healthcare & Life Sciences, Montr´eal, QC, Canada · Cornell University, Ithaca, NY +1

LLM-as-a-Judge Radiology Report Evaluation

Apr 3, 2026

A Scoping Review of LLM-as-a-Judge in Healthcare and the MedJUDGE Framework

As large language models (LLMs) increasingly generate and process clinical text, scalable evaluation has become critical. LLM-as-a-Judge (LaaJ), which uses LLMs to evaluate model outputs, offers a scalable alternative to costly expert review, but its healthcare adoption raises safety and bias concerns. We conducted a PRISMA-ScR scoping review of six databases (January 2020-January 2026), screening 11,727 studies and including 49. The landscape was dominated by evaluation and benchmarking applications (n=37, 75.5%), pointwise scoring (n=42, 85.7%), and GPT-family judges (n=36, 73.5%). Despite growing adoption, validation rigor was limited: among 36 studies with human involvement, the median number of expert validators was 3, while 13 (26.5%) used none. Risk of bias testing was absent in 36 studies (73.5%), only 1 (2.0%) examined demographic fairness, and none assessed temporal stability or patient context. Deployment remained limited, with 1 study (2.0%) reaching production and four (8.2%) prototype stage. Importantly, these gaps may interact: when judges and evaluated systems share training data or architectures, they may inherit similar blind spots, and agreement metrics may fail to distinguish true validity from shared errors. Minimal human oversight, limited bias assessment, and model monoculture together represent a governance gap where current validation may miss clinically significant errors. To address this, we propose MedJUDGE (Medical Judge Utility, De-biasing, Governance and Evaluation), a risk-stratified three-pillar framework organized around validity, safety, and accountability across clinical risk tiers, providing deployment-oriented evaluation guidance for healthcare LaaJ systems.

Chenyu Li, Zohaib Akhtar, Mingu Kwak +13

Department of Biomedical Informatics, School of Medicine, University of Pittsburgh, Pittsburgh, PA, USA · Department of Health Information Management, School of Health and Rehabilitation Sciences, University of Pittsburgh, Pittsburgh, PA, USA · OpenCura, Health Innovation Consortium +6

LLM-as-a-Judge Clinical Language Model Evaluation Language Model Safety Evaluation Bias in LLM-as-a-Judge

Apr 3, 2026

Reinforcement Learning-based Semi-supervised Knowledge Distillation with LLM-as-a-Judge

Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers. To overcome this, we propose a RL framework for reasoning distillation that leverages continuous, LLM-based rewards. Our method employs an efficient mechanism that computes a continuous CoT reward (CCR) directly from a single-token logit of a judge LLM, evaluating the student model's reasoning trajectory. This formulation provides an effective and scalable online training signal that can be applied to large volumes of unlabeled data. We demonstrate that, when paired with a strong judge, simply using CCR achieves performance comparable to that of ground-truth or pseudo-label verifiable rewards, and even surpasses them as the amount of unlabeled data increases. Furthermore, we find that combining them in a semi-supervised setup is highly synergistic: verifiable rewards help stabilize the CCR, while CCR improves the generalizability of verifiable rewards to related tasks. We also provide a comprehensive empirical comparison of various reward sources across multiple model architectures and dataset sizes. Our results show that this semi-supervised approach consistently enhances mathematical reasoning, yielding an absolute improvement of 5-10% on multiple reasoning tasks.

Yiyang Shen, Lifu Tu, Weiran Wang

University of Iowa · Oracle AI

RL for Language Model Reasoning Knowledge Distillation Numerical Reasoning in Language Models LLM-as-a-Judge Reinforcement Learning with Verifiable Rewards

Apr 2, 2026

Blinded Radiologist and LLM-Based Evaluation of LLM-Generated Japanese Translations of Chest CT Reports: Comparative Study

Background: Accurate translation of radiology reports is important for multilingual research, clinical communication, and radiology education, but the validity of LLM-based evaluation remains unclear. Objective: To evaluate the educational suitability of LLM-generated Japanese translations of chest CT reports and compare radiologist assessments with LLM-as-a-judge evaluations. Methods: We analyzed 150 chest CT reports from the CT-RATE-JPN validation set. For each English report, a human-edited Japanese translation was compared with an LLM-generated translation by DeepSeek-V3.2. A board-certified radiologist and a radiology resident independently performed blinded pairwise evaluations across 4 criteria: terminology accuracy, readability, overall quality, and radiologist-style authenticity. In parallel, 3 LLM judges (DeepSeek-V3.2, Mistral Large 3, and GPT-5) evaluated the same pairs. Agreement was assessed using QWK and percentage agreement. Results: Agreement between radiologists and LLM judges was near zero (QWK=-0.04 to 0.15). Agreement between the 2 radiologists was also poor (QWK=0.01 to 0.06). Radiologist 1 rated terminology as equivalent in 59% of cases and favored the LLM translation for readability (51%) and overall quality (51%). Radiologist 2 rated readability as equivalent in 75% of cases and favored the human-edited translation for overall quality (40% vs 21%). All 3 LLM judges strongly favored the LLM translation across all criteria (70%-99%) and rated it as more radiologist-like in >93% of cases. Conclusions: LLM-generated translations were often judged natural and fluent, but the 2 radiologists differed substantially. LLM-as-a-judge showed strong preference for LLM output and negligible agreement with radiologists. For educational use of translated radiology reports, automated LLM-based evaluation alone is insufficient; expert radiologist review remains important.

Yosuke Yamagishi, Atsushi Takamatsu, Yasunori Hamaguchi +4

Division of Radiology and Biomedical Engineering, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan · Department of Radiology, The University of Tokyo Hospital, Tokyo, Japan · Department of Radiology, Kanazawa University Graduate School of Medical Sciences, Ishikawa, Japan +2

Radiology Report Evaluation MT Evaluation LLM-as-a-Judge Bias in LLM-as-a-Judge

Apr 2, 2026

TSQueryBench: LLM-as-a-Judge for Time Series Explanations

Natural language explanations of time series data are increasingly produced by foundation models in high stakes domains, making factual correctness critical. Evaluating such explanations differs fundamentally from standard natural language generation: correctness requires verifying numerical claims against structured data rather than similarity to reference text. While LLM as a Judge has emerged as a scalable paradigm for text evaluation, its applicability to numerically grounded time series explanations remains unstudied. We introduce TSQueryBench, a controlled synthetic benchmark of 500 time series instances across 10 query types, each paired with correct, partially correct, and incorrect explanations. We evaluate six large language models across four tasks: explanation generation, relative ranking, independent scoring, and multi anomaly detection. Our central finding is a consistent generation evaluation asymmetry: models that fail to generate numerically correct explanations nonetheless reliably identify or score correct ones. These results show that rubric guided LLM evaluation is substantially more reliable than generation for time series reasoning, supporting LLM judges as scalable evaluators in numerically grounded settings. Code and data: https://github.com/Prxxthxm/TSQueryBench/

Preetham Sivalingam, Murari Mandal, Dhruv Kumar +1

BITS Pilani, Pilani, India · KIIT & Birla AI Labs, Bhubaneshwar, India · BITS Pilani & Birla AI Labs, Pilani, India +1

Explanation Evaluation Explainability Evaluation LLM-as-a-Judge Language Model Generation Evaluation Time Series Reasoning

Apr 1, 2026

Logarithmic Scores, Power-Law Discoveries: Disentangling Measurement from Coverage in Agent-Based Evaluation

LLM-based agent judges are an emerging approach to evaluating conversational AI, yet a fundamental uncertainty remains: can we trust their assessments, and if so, how many are needed? Through 960 sessions with two model pairs across 15 tasks, we show that persona-based agent judges produce evaluations indistinguishable from human raters in a Turing-style validation. We then identify a score-coverage dissociation: quality scores improve logarithmically with panel size, while unique issue discoveries follow a sublinear power law-both exhibit diminishing returns, but scores saturate roughly twice as fast as discoveries. We hypothesize this reflects a power law distribution of the finding space: critical issues are discovered first by small panels, while corner cases require progressively larger panels, analogous to species accumulation curves in ecology. The mechanism traces to ensemble diversity-Big Five personality conditioning makes agents probe different quality dimensions, with expert judges acting as adversarial probes that push discovery into the tail of the finding distribution. A controlled ablation confirms that structured persona conditioning, not simple prompting, is required to produce these scaling properties.

HyunJoon Jung, William Na

LLM-as-a-Judge AI Agent Evaluation

Mar 31, 2026

HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models

Evaluating humor in large language models (LLMs) is an open challenge because existing approaches yield isolated, incomparable metrics rather than unified model rankings, making it difficult to track progress across systems. We introduce HumorRank, a tournament-based evaluation framework and leaderboard for textual humor generation. On two public benchmarks (SemEval-2026 MWAHAHA and Humor Transfer Bench), we conduct extensive automated pairwise evaluation across nine models spanning proprietary, open-weight, and specialized systems. Pairwise judgments are produced by LLM judges grounded in the General Theory of Verbal Humor (GTVH): each judge integrates structured comedic analysis into adjudication, jointly yielding a preference decision, an interpretable rationale, and mechanism, delivery, and failure tags rather than a black-box funniness score. Judgments are aggregated via an Adaptive Swiss tournament, with Bradley-Terry Maximum Likelihood Estimation (MLE) producing globally consistent humor generation capability rankings. Rankings are cross-judge stable: independent LLM judges (Llama 3.3 70B and Qwen 2.5 72B) yield Kendall tau = 0.889 on both benchmarks, and a human calibration study shows human-LLM agreement tracking human-human agreement on hard funny-versus-funny pairs. Our results demonstrate that HumorRank yields statistically grounded model stratifications, showing that humor quality is associated with mastery of comedic mechanisms such as incongruity, conciseness, escalation, and absurdity rather than model scale alone, with specialized fine-tuned models reaching parity with far larger systems. HumorRank thus provides a scalable, interpretable, and reproducible methodology for benchmarking and understanding LLM-generated humor.

Edward Ajayi, Prasenjit Mitra

Carnegie Mellon University Africa Kigali, Rwanda

Humor Explanation Generation LLM Evaluation Generative AI Evaluation Text Generation LLM-as-a-Judge

Mar 31, 2026

When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment

Large Language Models (LLMs) show promise for automated grading, but their outputs can be unreliable. Rather than improving grading accuracy directly, we address a complementary problem: predicting when an LLM grader is likely to be correct. This enables selective automation where high-confidence predictions are processed automatically while uncertain cases are flagged for human review. We compare three confidence estimation methods (self-reported confidence, self-consistency voting, and token probability) across seven LLMs of varying scale (4B to 120B parameters) on three educational datasets: RiceChem (long-answer chemistry), SciEntsBank, and Beetle (short-answer science). Our experiments reveal that self-reported confidence consistently achieves the best calibration across all conditions (avg ECE 0.166 vs 0.229 for self-consistency). Surprisingly, self-consistency remains 38% worse despite requiring 5

\times

the inference cost. Larger models exhibit substantially better calibration though gains vary by dataset and method (e.g., a 28% ECE reduction for self-reported), with GPT-OSS-120B achieving the best calibration (avg ECE 0.100) and strong discrimination (avg AUC 0.668). We also observe that confidence is strongly top-skewed across methods, creating a ``confidence floor'' that practitioners must account for when setting thresholds. These findings suggest that simply asking LLMs to report their confidence provides a practical approach for identifying reliable grading predictions. Code is available here.

Robinson Ferrer, Damla Turgut, Zhongzhou Chen +1

University of Central Florida

Confidence Estimation in Language Models Language Model Calibration Automated Grading Selective Prediction LLM-as-a-Judge

Mar 31, 2026

Security in LLM-as-a-Judge: A Comprehensive SoK

LLM-as-a-Judge (LaaJ) is a novel paradigm in which powerful language models are used to assess the quality, safety, or correctness of generated outputs. While this paradigm has significantly improved the scalability and efficiency of evaluation processes, it also introduces novel security risks and reliability concerns that remain largely unexplored. In particular, LLM-based judges can become both targets of adversarial manipulation and instruments through which attacks are conducted, potentially compromising the trustworthiness of evaluation pipelines. In this paper, we present the first Systematization of Knowledge (SoK) focusing on the security aspects of LLM-as-a-Judge systems. We perform a comprehensive literature review across major academic databases, analyzing 863 works and selecting 45 relevant studies published between 2020 and 2026. Based on this study, we propose a taxonomy that organizes recent research according to the role played by LLM-as-a-Judge in the security landscape, distinguishing between attacks targeting LaaJ systems, attacks performed through LaaJ, defenses leveraging LaaJ for security purposes, and applications where LaaJ is used as an evaluation strategy in security-related domains. We further provide a comparative analysis of existing approaches, highlighting current limitations, emerging threats, and open research challenges. Our findings reveal significant vulnerabilities in LLM-based evaluation frameworks, as well as promising directions for improving their robustness and reliability. Finally, we outline key research opportunities that can guide the development of more secure and trustworthy LLM-as-a-Judge systems.

Aiman Al Masoud, Antony Anju, Marco Arazzi +6

Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy · Department of Computer Applications, Cochin University of Science and Technology, Kerala, India

LLM-as-a-Judge LLM Security LLM Reliability Adversarial Attacks on LLMs

Mar 30, 2026

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

Large Language Models (LLMs) are increasingly used as automated judges, yet decoding temperature is often set by intuition rather than evidence. We run over one million large scale evaluations, multiple open-source models, prompting strategies, and judging paradigms to examine how temperature affects judge reliability. Low temperatures yield consistent outputs with few errors, especially in smaller models, while higher temperatures reduce consistency and increase errors. Yet consistency alone does not guarantee sound judgments: low temperatures can narrow the range of reasoning explored. We characterize judge behavior through four reasoning personas and find that temperature shifts their distributions in model-dependent ways, most visibly in ambiguous cases where competing answers are hard to distinguish. Repeated high-temperature sampling reveals this hidden uncertainty, and combining it with majority voting or using high temperature for reasoning and low temperature for the final decision, improves agreement on ambiguous cases without hurting clear ones, at the cost of extra inference. Our findings suggest a simple rule: keep temperature low for stable outputs, but explore more when the judgment is hard.

Lujun Li, Lama Sleem, Yangjie Xu +4

University of Luxembourg · ETH Zürich

LLM-as-a-Judge LLM Evaluation LLM Reliability Language Model Decoding Reasoning Consistency in Language Models

Mar 30, 2026

Evaluating LLMs for Answering Student Questions in Introductory Programming Courses

The rapid emergence of Large Language Models (LLMs) presents both opportunities and challenges for programming education. While students increasingly use generative AI tools, direct access often hinders the learning process by providing complete solutions rather than pedagogical hints. Concurrently, educators face significant workload and scalability challenges when providing timely, personalized feedback. This study investigates the capabilities of LLMs to safely and effectively assist educators in answering student questions within a CS1 programming course. To achieve this, we established a rigorous, reproducible evaluation process by curating a benchmark dataset of 170 authentic student questions from a learning management system, paired with ground-truth responses authored by subject matter experts. Because traditional text-matching metrics are insufficient for evaluating open-ended educational responses, we developed and validated a custom LLM-as-a-Judge metric optimized for assessing pedagogical accuracy. Our findings demonstrate that models, such as Gemini 3 flash, can surpass the quality baseline of typical educator responses, achieving high alignment with expert pedagogical standards. To mitigate persistent risks like hallucination and ensure alignment with course-specific context, we advocate for a "teacher-in-the-loop" implementation. Finally, we abstract our methodology into a task-agnostic evaluation framework, advocating for a shift in the development of educational LLM tools from ad-hoc, post-deployment testing to a quantifiable, pre-deployment validation process.

Thomas Van Mullem, Bart Mesuere, Peter Dawyndt

AI in Education Generative AI in Education Computer Science Education LLM Evaluation LLM-as-a-Judge

Mar 30, 2026

Atomic and Holistic LLM Judges for Reference-Grounded Support Labels: A Prompt-Controlled Comparison

When an LLM judge only has to assign a three-way support label to a candidate answer given a reference, does asking it to decompose the answer into atomic claims help, and at what cost? We compare four single-call designs that share the judge model, the inputs, and the level of instruction detail: candidate-side atomic decomposition, a matched holistic rubric, reference-side decomposition that checks whether each reference claim is covered, and a bidirectional combination. Support labels are constructed from TruthfulQA, ASQA, and QAMPARI references (200 questions and 400 rows per dataset). All four designs are run with Opus-4.6, GPT-4.1, and Gemini Flash Lite; Sonnet-4.6 is added for the candidate-side and holistic designs. Candidate-side decomposition is weak where the label depends on completeness: the holistic rubric is more accurate on ASQA and QAMPARI for every judge while using fewer tokens. Reference-side decomposition is 12.5-21.3 points more accurate than holistic on ASQA for 28-29% more tokens, and stays near the holistic ceiling on QAMPARI at 63-69% more. On TruthfulQA misconceptions, candidate-side decomposition is competitive and significantly better for two judges. On a 60-row single-author subset whose labels are looser than strict reference completeness, candidate-side decomposition edges ahead of holistic for every judge, reversing the construction-label order. What a judge decomposes should follow what the label measures.

Xinran Zhang

University of California, Berkeley

LLM-as-a-Judge Language Model Generation Evaluation LLM Answer Verification

Mar 27, 2026

Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation

As Large Language Models (LLMs) exhibit plateauing performance on conventional benchmarks, a pivotal challenge persists: evaluating their proficiency in complex, open-ended tasks characterizing genuine expert-level cognition. Existing frameworks suffer from narrow domain coverage, reliance on generalist tasks, or self-evaluation biases. To bridge this gap, we present XpertBench, a high-fidelity benchmark engineered to assess LLMs across authentic professional domains. XpertBench consists of 1,346 meticulously curated tasks across 80 categories, spanning finance, healthcare, legal services, education, and dual-track research (STEM and Humanities). These tasks are derived from over 1,000 submissions by domain experts--including researchers from elite institutions and practitioners with extensive clinical or industrial experience--ensuring superior ecological validity. Each task uses detailed rubrics with mostly 15-40 weighted checkpoints to assess professional rigor. To facilitate scalable yet human-aligned assessment, we introduce ShotJudge, a novel evaluation paradigm that employs LLM judges calibrated with expert few-shot exemplars to mitigate self-rewarding biases. Our empirical evaluation of state-of-the-art LLMs reveals a pronounced performance ceiling: even leading models achieve a peak success rate of only ~66%, with a mean score around 55%. Models also exhibit domain-specific divergence, showing non-overlapping strengths in quantitative reasoning versus linguistic synthesis.. These findings underscore a significant "expert-gap" in current AI systems and establish XpertBench as a critical instrument for navigating the transition from general-purpose assistants to specialized professional collaborators.

Xue Liu, Xin Ma, Yuxin Ma +36

ByteDance Seed

LLM Evaluation Rubric-Based Evaluation LLM-as-a-Judge

Mar 26, 2026

Same Verdict, Different Reasons: LLM-as-a-Judge and Clinician Disagreement on Medical Chatbot Completeness

LLM-as-a-Judge frameworks are increasingly trusted to automate evaluation in place of human experts, yet their reliability in high-stakes medical contexts remains unproven. We stress-test this assumption for detecting incomplete patient-facing medical responses, evaluating three rubric granularities (General-Likert, Analytical-Rubric, Dynamic-Checklist) and three backbone models across two clinician-annotated datasets, including HealthBench, the largest publicly available benchmark for medical response evaluation. LLM Judges discriminate complete from incomplete responses at and slightly above near chance (AUC

0.49

--

0.66

); at the threshold required to recall

90\%

of incomplete responses, clinicians must still review the vast majority of the dataset, offering no triage utility. Even when model and clinician verdicts agree, they rarely cite the same explanation; and when they diverge, false positives stem from over-flagging non-essential gaps while false negatives reflect outright detection failures. These results reveal that LLM Judges and clinicians apply fundamentally different completeness standards; a finding that undermines their use as autonomous evaluators or triage filters in clinical settings.

Alexandra DeLucia, Heyuan Huang, Sonal Joshi +3

Data Science and AI Institute, Johns Hopkins University

LLM-as-a-Judge LLM Reliability Clinical Language Model Evaluation