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

610 papers56 papers in the last four weeks, down 45% on the four weeks before. 0.4% of all new papers.

Feb 27, 2026

LFQA-HP-1M: A Large-Scale Human Preference Dataset for Long-Form Question Answering

Long-form question answering (LFQA) demands nuanced evaluation of multi-sentence explanatory responses, yet existing metrics often fail to reflect human judgment. We present LFQA-HP-1M, a large-scale dataset comprising 1.3M human pairwise preference annotations for LFQA. We propose nine rubrics for answer quality evaluation, and show that simple linear models based on these features perform comparably to state-of-the-art LLM evaluators. We further examine transitivity consistency, positional bias, and verbosity biases in LLM evaluators and demonstrate their vulnerability to adversarial perturbations. Overall, this work provides one of the largest public LFQA preference datasets and a rubric-driven framework for transparent and reliable evaluation.
Feb 24, 2026

QEDBENCH: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs

As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated evaluation. We demonstrate that standard "LLM-as-a-Judge" protocols suffer from a systematic Alignment Gap when applied to upper-undergraduate to early graduate level mathematics. To quantify this, we introduce QEDBench, the first large-scale dual-rubric alignment benchmark to systematically measure alignment with human experts on university-level math proofs by contrasting course-specific rubrics against expert common knowledge criteria. By deploying a dual-evaluation matrix (7 judges x 5 solvers) against 1,000+ hours of human evaluation, we reveal that certain frontier evaluators like Claude Opus 4.5, DeepSeek-V3, Qwen 2.5 Max, and Llama 4 Maverick exhibit significant positive bias (up to +0.18, +0.20, +0.30, +0.36 mean score inflation, respectively). Furthermore, we uncover a critical reasoning gap in the discrete domain: while Gemini 3.0 Pro achieves state-of-the-art performance (0.91 average human evaluation score), other reasoning models like GPT-5 Pro and Claude Sonnet 4.5 see their performance significantly degrade in discrete domains. Specifically, their average human evaluation scores drop to 0.72 and 0.63 in Discrete Math, and to 0.74 and 0.50 in Graph Theory. In addition to these research results, we also release QEDBench as a public benchmark for evaluating and improving AI judges. Our benchmark is publicly published at https://github.com/qqliu/Yale-QEDBench.
Feb 23, 2026

Case-Aware LLM-as-a-Judge Evaluation for Enterprise-Scale RAG Systems

Enterprise Retrieval-Augmented Generation (RAG) assistants operate in multi-turn, case-based workflows such as technical support and IT operations, where evaluation must reflect operational constraints, structured identifiers (e.g., error codes, versions), and resolution workflows. Existing RAG evaluation frameworks are primarily designed for benchmark-style or single-turn settings and often fail to capture enterprise-specific failure modes such as case misidentification, workflow misalignment, and partial resolution across turns. We present a case-aware LLM-as-a-Judge evaluation framework for enterprise multi-turn RAG systems. The framework evaluates each turn using eight operationally grounded metrics that separate retrieval quality, grounding fidelity, answer utility, precision integrity, and case/workflow alignment. A severity-aware scoring protocol reduces score inflation and improves diagnostic clarity across heterogeneous enterprise cases. The system uses deterministic prompting with strict JSON outputs, enabling scalable batch evaluation, regression testing, and production monitoring. Through a comparative study of two instruction-tuned models across short and long workflows, we show that generic proxy metrics provide ambiguous signals, while the proposed framework exposes enterprise-critical tradeoffs that are actionable for system improvement.
Feb 20, 2026

Luna-2: Scalable Single-Token Evaluation with Small Language Models

Real-time guardrails require evaluation that is accurate, cheap, and fast - yet today's default, LLM-as-a-judge (LLMAJ), is slow, expensive, and operationally non-deterministic due to multi-token generation. We present Luna-2, a novel architecture that leverages decoder-only small language models (SLMs) into a deterministic evaluation model to reliably compute complex task-specific LLMAJ metrics (e.g. toxicity, hallucination, tool selection quality, etc.) at an accuracy at par or higher than LLMAJ using frontier LLMs while drastically reducing the cost and latency of computation. Each metric is implemented as a lightweight LoRA/PEFT head on top of a shared SLM backbone, enabling hundreds of specialized metrics to run concurrently on a single GPU, deployable locally next to AI systems in a privacy-preserving and latency optimizing manner. Across content safety and hallucination benchmarks, Luna-2 matches the accuracy of state-of-the-art LLM-based evaluators while reducing inference cost by over 80x and latency by over 20x. In this paper, we outline the model architecture, training methodology and report real-world empirical results on accuracy, latency, and throughput results. In production, Luna-2 is protecting 100M+ AI sessions and processing over 100B tokens per month for our customers with eval cost savings of over $30M annually.
Feb 20, 2026

"How Do I ...?": Procedural Questions Predominate Student-LLM Chatbot Conversations

Providing scaffolding through educational chatbots built on Large Language Models (LLM) has potential risks and benefits that remain an open area of research. When students navigate impasses, they ask for help by formulating impasse-driven questions. Within interactions with LLM chatbots, such questions shape the user prompts and drive the pedagogical effectiveness of the chatbot's response. This paper focuses on such student questions from two datasets of distinct learning contexts: formative self-study, and summative assessed coursework. We analysed 6,113 messages from both learning contexts, using 11 different LLMs and three human raters to classify student questions using four existing schemas. On the feasibility of using LLMs as raters, results showed moderate-to-good inter-rater reliability, with higher consistency than human raters. The data showed that 'procedural' questions predominated in both learning contexts, but more so when students prepare for summative assessment. These results provide a basis on which to use LLMs for classification of student questions. However, we identify clear limitations in both the ability to classify with schemas and the value of doing so: schemas are limited and thus struggle to accommodate the semantic richness of composite prompts, offering only partial understanding the wider risks and benefits of chatbot integration. In the future, we recommend an analysis approach that captures the nuanced, multi-turn nature of conversation, for example, by applying methods from conversation analysis in discursive psychology.
Feb 18, 2026

References Improve LLM Alignment in Non-Verifiable Domains

While Reinforcement Learning with Verifiable Rewards (RLVR) has shown strong effectiveness in reasoning tasks, it cannot be directly applied to non-verifiable domains lacking ground-truth verifiers, such as LLM alignment. In this work, we investigate whether reference-guided LLM-evaluators can bridge this gap by serving as soft "verifiers". First, we design evaluation protocols that enhance LLM-based evaluators for LLM alignment using reference outputs. Through comprehensive experiments, we show that a reference-guided approach substantially improves the accuracy of less capable LLM-judges using references from frontier models; stronger LLM-judges can also be enhanced by high-quality (i.e., human-written) references. Building on these improved judges, we demonstrate the utility of high-quality references in alignment tuning, where LLMs guided with references are used as judges to self-improve. We show that reference-guided self-improvement yields clear gains over both direct SFT on reference outputs and self-improvement with reference-free judges, achieving performance comparable to training with ArmoRM, a strong finetuned reward model. Specifically, our method achieves 73.1% and 58.7% on AlpacaEval and Arena-Hard with Llama-3-8B-Instruct, and 70.0% and 74.1% with Qwen2.5-7B, corresponding to average absolute gains of +20.2 / +17.1 points over SFT distillation and +5.3 / +3.6 points over reference-free self-improvement on AlpacaEval / Arena-Hard. These results highlight the potential of using reference-guided LLM-evaluators to enable effective LLM post-training in non-verifiable domains.
Feb 18, 2026

Who can we trust? LLM-as-a-jury for Comparative Assessment

Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment often using pairwise comparative judgements. Existing approaches typically rely on single judges or aggregate multiple judges assuming equal reliability. In practice, LLM judges vary substantially in performance across tasks and evaluation aspects, and their judgment probabilities may be biased and inconsistent. Furthermore, human-labelled supervision for judge calibration may be unavailable. We first empirically demonstrate that inconsistencies in LLM comparison probabilities exist and show that it limits the effectiveness of direct probability-based ranking. To address this, we study the LLM-asa-jury setting and propose BT-sigma, a judge-aware extension of the Bradley-Terry model that introduces a discriminator parameter for each judge to jointly infer item rankings and judge reliability from pairwise comparisons alone. Experiments on benchmark NLG evaluation datasets show that BT-sigma consistently outperforms averaging-based aggregation methods, and that the learned discriminators strongly correlate with independent measures of the cycle consistency of LLM judgments. Further analysis reveals that BT-sigma can be interpreted as an unsupervised calibration mechanism that improves aggregation by modelling judge reliability.
Feb 17, 2026

*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation

Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing. To address these limitations, we build upon ParaPLUIE, a perplexity-based LLM-judge metric that estimates confidence over ``Yes/No'' answers without generating text. We introduce *-PLUIE, task specific prompting variants of ParaPLUIE and evaluate their alignment with human judgement. Our experiments show that personalised *-PLUIE achieves stronger correlations with human ratings while maintaining low computational cost.
Feb 17, 2026

LLM-as-Judge on a Budget

LLM-as-a-judge has emerged as a cornerstone technique for evaluating large language models by leveraging LLM reasoning to score prompt-response pairs. Since LLM judgments are stochastic, practitioners commonly query each pair multiple times to estimate mean scores accurately. This raises a critical challenge: given a fixed computational budget BB, how to optimally allocate queries across KK prompt-response pairs to minimize estimation error? We present a principled variance-adaptive approach leveraging multi-armed bandit theory and concentration inequalities. Our method dynamically allocates queries based on estimated score variances, concentrating resources where uncertainty is highest. Further, our algorithm is shown to achieve a worst-case score-estimation error of O~(∑i=1Kσi2B)\tilde{O}\left(\sqrt{\frac{\sum_{i=1}^K σ_i^2}{B}}\right), σi2σ_i^2 being the unknown score variance for pair i∈[K]i \in [K] with near-optimal budget allocation. Experiments on Summarize-From-Feedback and HelpSteer2 demonstrate that our method significantly outperforms uniform allocation, reducing worst-case estimation error while maintaining identical budgets. Our work establishes a theoretical foundation for efficient LLM evaluation with practical implications for AI safety, model alignment, and automated assessment at scale.
Feb 16, 2026

Synthetic Reader Panels: Tournament-Based Ideation with LLM Personas for Autonomous Publishing

We present a system for autonomous book ideation that replaces human focus groups with synthetic reader panels -- diverse collections of LLM-instantiated reader personas that evaluate book concepts through structured tournament competitions. Each persona is defined by demographic attributes (age group, gender, income, education, reading level), behavioral patterns (books per year, genre preferences, discovery methods, price sensitivity), and consistency parameters. Panels are composed per imprint to reflect target demographics, with diversity constraints ensuring representation across age, reading level, and genre affinity. Book concepts compete in single-elimination, double-elimination, round-robin, or Swiss-system tournaments, judged against weighted criteria including market appeal, originality, and execution potential. To reject low-quality LLM evaluations, we implement five automated anti-slop checks (repetitive phrasing, generic framing, circular reasoning, score clustering, audience mismatch). We report results from deployment within a multi-imprint publishing operation managing 6 active imprints and 609 titles in distribution. Three case studies -- a 270-evaluator panel for a children's literacy novel, and two 5-person expert panels for a military memoir and a naval strategy monograph -- demonstrate that synthetic panels produce actionable demographic segmentation, identify structural content issues invisible to homogeneous reviewers, and enable tournament filtering that eliminates low-quality concepts while enriching high-quality survivors from 15% to 62% of the evaluated pool.
Feb 14, 2026

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges

Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in this workflow, which we term Rubric-Induced Preference Drift (RIPD). Even when rubric edits pass benchmark validation, they can still produce systematic and directional shifts in a judge's preferences on target domains. Because rubrics serve as a high-level decision interface, such drift can emerge from seemingly natural, criterion-preserving edits and remain difficult to detect through aggregate benchmark metrics or limited spot-checking. We further show this vulnerability can be exploited through rubric-based preference attacks, in which benchmark-compliant rubric edits steer judgments away from a fixed human or trusted reference on target domains, systematically inducing RIPD and reducing target-domain accuracy up to 9.5% (helpfulness) and 27.9% (harmlessness). When these judgments are used to generate preference labels for downstream post-training, the induced bias propagates through alignment pipelines and becomes internalized in trained policies. This leads to persistent and systematic drift in model behavior. Overall, our findings highlight evaluation rubrics as a sensitive and manipulable control interface, revealing a system-level alignment risk that extends beyond evaluator reliability alone. The code is available at: https://github.com/ZDCSlab/Rubrics-as-an-Attack-Surface. Warning: Certain sections may contain potentially harmful content that may not be appropriate for all readers.
Feb 13, 2026

CLASE: A Hybrid Method for Chinese Legalese Stylistic Evaluation

Legal text generated by large language models (LLMs) can usually achieve reasonable factual accuracy, but it frequently fails to adhere to the specialised stylistic norms and linguistic conventions of legal writing. In order to improve stylistic quality, a crucial first step is to establish a reliable evaluation method. However, having legal experts manually develop such a metric is impractical, as the implicit stylistic requirements in legal writing practice are difficult to formalise into explicit rubrics. Meanwhile, existing automatic evaluation methods also fall short: reference-based metrics conflate semantic accuracy with stylistic fidelity, and LLM-as-a-judge evaluations suffer from opacity and inconsistency. To address these challenges, we introduce CLASE (Chinese LegAlese Stylistic Evaluation), a hybrid evaluation method that focuses on the stylistic performance of legal text. The method incorporates a hybrid scoring mechanism that combines 1) linguistic feature-based scores and 2) experience-guided LLM-as-a-judge scores. Both the feature coefficients and the LLM scoring experiences are learned from contrastive pairs of authentic legal documents and their LLM-restored counterparts. This hybrid design captures both surface-level features and implicit stylistic norms in a transparent, reference-free manner. Experiments on 200 Chinese legal documents show that CLASE achieves substantially higher alignment with human judgments than traditional metrics and pure LLM-as-a-judge methods. Beyond improved alignment, CLASE provides interpretable score breakdowns and suggestions for improvements, offering a scalable and practical solution for professional stylistic evaluation in legal text generation (Code and data for CLASE is available at: https://github.com/rexera/CLASE).
Feb 9, 2026

CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation

LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw: they implicitly assume that judges provide independent estimates of true quality. However, in practice, LLM judges exhibit correlated errors caused by shared latent confounders -- such as verbosity, stylistic preferences, or training artifacts -- causing standard aggregation rules like majority vote or averaging to provide little gain or even amplify systematic mistakes. To address this, we introduce CARE, a confounder-aware aggregation framework that explicitly models LLM judge scores as arising from both a latent true-quality signal and shared confounding factors. Rather than heuristically re-weighting judges, CARE separates quality from confounders without access to ground-truth labels. We provide theoretical guarantees for identifiability and finite-sample recovery under shared confounders, and we quantify the systematic bias incurred when aggregation models omit confounding latent factors. Across 12 public benchmarks spanning continuous scoring, binary classification, and pairwise preference settings, CARE improves aggregation accuracy, reducing error by up to 26.8%. Code is released in https://github.com/SprocketLab/CARE.
Feb 6, 2026

FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge

Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to task- and domain-specific evaluation criteria, systematic biases driven by non-semantic cues such as position, length, format, and model provenance, and evaluation inconsistency that leads to contradictory judgments across different evaluation modes (e.g., pointwise versus pairwise). To address these issues, we propose FairJudge, an adaptive, debiased, and consistent LLM-as-a-Judge. Unlike prior approaches that treat the judge as a static evaluator, FairJudge models judging behavior itself as a learnable and regularized policy. From a data-centric perspective, we construct a high-information-density judging dataset that explicitly injects supervision signals aligned with evaluation behavior. Building on this dataset, we adopt a curriculum-style SFT-DPO-GRPO training paradigm that progressively aligns rubric adherence, bias mitigation, and cross-mode consistency, while avoiding catastrophic forgetting. Experimental results on multiple internal and public benchmarks show that FairJudge consistently improves agreement and F1, reduces non-semantic biases, and outperforms substantially larger instruction-tuned LLMs. All resources will be publicly released after acceptance to facilitate future research.
Feb 6, 2026

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks

Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while LLM-as-a-judge approaches adapt to individual responses yet suffer from instability and bias. Human experts address this dilemma by combining domain-grounded principles with dynamic, claim-level assessment. Inspired by this process, we propose JADE, a two-layer evaluation framework. Layer 1 encodes expert knowledge as a predefined set of evaluation skills, providing stable evaluation criteria. Layer 2 performs report-specific, claim-level evaluation to flexibly assess diverse reasoning strategies, with evidence-dependency gating to invalidate conclusions built on refuted claims. Experiments on BizBench show that JADE improves evaluation stability and reveals critical agent failure modes missed by holistic LLM-based evaluators. We further demonstrate strong alignment with expert-authored rubrics and effective transfer to HealthBench and DR.BENCH, covering medical and 10-domain professional evaluation settings. Code and data are available at https://github.com/smiling-world/JADE.
Feb 3, 2026

MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems

Multi-Agent Systems (MAS) built on Large Language Models (LLMs) often exhibit high variance in their reasoning trajectories. Process verification, which evaluates intermediate steps in trajectories, has shown promise in general reasoning settings, and has been suggested as a potential tool for guiding coordination of MAS; however, its actual effectiveness in MAS remains unclear. To fill this gap, we present MAS-ProVe, a systematic empirical study of process verification for multi-agent systems (MAS). Our study spans three verification paradigms (LLM-as-a-Judge, reward models, and process reward models), evaluated across two levels of verification granularity (agent-level and iteration-level). We further examine five representative verifiers and four context management strategies, and conduct experiments over six diverse MAS frameworks on multiple reasoning benchmarks. We find that process-level verification does not consistently improve performance and frequently exhibits high variance, highlighting the difficulty of reliably evaluating partial multi-agent trajectories. Among the methods studied, LLM-as-a-Judge generally outperforms reward-based approaches, with trained judges surpassing general-purpose LLMs. We further observe a small performance gap between LLMs acting as judges and as single agents, and identify a context-length-performance trade-off in verification. Overall, our results suggest that effective and robust process verification for MAS remains an open challenge, requiring further advances beyond current paradigms. Code is available at https://github.com/Wang-ML-Lab/MAS-ProVe.
Feb 2, 2026

Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge

Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examined point-wise or pair-wise evaluation protocols; in contrast, our focus is on rubric-based evaluation, which has been attracting increasing attention owing to its utility for training models in domains where verification is otherwise difficult. In this work, we show that rubric-based evaluation implicitly resembles a multiple-choice setting and therefore exhibits position bias: LLMs tend to prefer score options that appear at specific positions within the rubric list. Through controlled experiments across multiple models and datasets, we demonstrate that this position bias is consistent. Its direction, however, is model-specific: some judges favor the first option, while others favor the last. We further identify a second, orthogonal axis of bias: when a prompt scores several criteria simultaneously, the ordering of the criteria itself shifts the resulting scores. We additionally explore permuting the order of the rubric options as a means of mitigating position bias, and find that although the bias can be attenuated, improvements in the correlation between model judgments and human annotations are obtained primarily for models that exhibit strong bias. Our results recast rubric-based LLM-as-a-judge as a multiple-choice problem with measurable, model-specific position bias, and we further confirm that only a small number of random order permutations are sufficient to reduce the error introduced by this bias for the majority of models.
Jan 30, 2026

Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design. In this work, we investigate whether smaller models can serve as efficient evaluators by leveraging internal representations instead of surface generation. We uncover a consistent empirical pattern: small LMs, despite with weak generative ability, encode rich evaluative signals in their hidden states. This motivates us to propose the Semantic Capacity Asymmetry Hypothesis: evaluation requires significantly less semantic capacity than generation and can be grounded in intermediate representations, suggesting that evaluation does not necessarily need to rely on large-scale generative models but can instead leverage latent features from smaller ones. Our findings motivate a paradigm shift from LLM-as-a-Judge to Representation-as-a-Judge, a decoding-free evaluation strategy that probes internal model structure rather than relying on prompted output. We instantiate this paradigm through INSPECTOR, a probing-based framework that predicts aspect-level evaluation scores from small model representations. Experiments on reasoning benchmarks (GSM8K, MATH, GPQA) show that INSPECTOR substantially outperforms prompting-based small LMs and closely approximates full LLM judges, while offering a more efficient, reliable, and interpretable alternative for scalable evaluation. The code and data are available at: https://github.com/zhuochunli/Representation-as-a-judge
Jan 30, 2026

Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations

Recent research has shown that large language models (LLMs) favor their own outputs when acting as judges, undermining the integrity of automated post-training and evaluation workflows. However, it is difficult to disentangle which behaviors are explained by narcissism versus experimental confounds. Specifically, LLM evaluators may deliver self-preferring verdicts when comparing responses to questions they fail on; these verdicts may not depend on the identity of the author, but on evaluator quality. We correct this by directly comparing the judge's voting distribution in cases where it evaluates itself versus another model. This evaluator quality baseline reveals that only 51% of examples in previous findings retain statistical significance against this null hypothesis, covering 89.6% of total self-preference probability mass. Finally, we compare the entropy of voting distributions, suggesting uncertainty-driven overlap, and show that our procedure enables more careful documentation against the backdrop of judge-bias research.
Jan 29, 2026

JURIST: Training Small Data-Reweighted Reasoning Judges for Test-Time Scaling in Code Generation

Best-of-N selection for code generation is only as good as the judge that picks among the candidates, and the judges accurate enough for this role are costly frontier LLMs. A small judge can be trained on abundant earlier data labeled by unit tests, but it is deployed on newer problems: the earlier problems are easier and teach it little, their tasks differ, and their candidates come from weaker policies, while data close to deployment are scarce. We present JURIST, a 1.7B reasoning judge that uses a small meta set close to deployment to learn how much each earlier training sample should count. In our experiments, we find that training on the meta set alone, or adding it to the training data, does not help, while using it to weight the earlier data through a bi-level objective adds 3.9 Hard points over adding it to the training data. On LiveCodeBench, JURIST reaches 84.7% Overall and matches Claude Sonnet 4.6 on Hard problems (73.8%) at 463x lower cost; on BigCodeBench, it surpasses all test-time scaling baselines (35.9%). Abundant earlier data, guided by a small deployment-aligned meta set, can thus train a compact judge that selects accurately at low cost.
Jan 27, 2026

ReportLogic: Evaluating Logical Quality in Deep Research Reports

Users increasingly rely on Large Language Models (LLMs) for Deep Research, using them to synthesize diverse sources into structured reports that support understanding and action. In this context, the practical reliability of such reports hinges on logical quality: whether the report's claims and arguments are explicitly supported and can be trusted as a basis for downstream use, rather than merely appearing fluent or informative. However, current evaluation frameworks largely overlook this requirement. To bridge this gap, we introduce ReportLogic, a benchmark that quantifies report-level logical quality through a reader-centric lens of auditability. Specifically, ReportLogic adopts a hierarchical taxonomy that evaluates whether readers can (1) trace an on-topic report structure with a unified analytical arc (Macro-Logic), (2) understand the progression with necessary context (Expositional-Logic), and (3) verify conclusions via explicit claim--support (Structural-Logic). Based on this taxonomy, we construct a human-annotated rubric-guided dataset and train an open-source LogicJudge for scalable evaluation. We further evaluate judge robustness via adversarial attacks, showing that off-the-shelf LLM judges are frequently influenced by superficial cues (e.g., verbosity), and reasoning modes can mask broken support relations. Overall, our results provide actionable guidance for building more robust logic evaluators and improving the logical reliability of LLM-generated reports.
Jan 13, 2026

From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges

Rubric-based text evaluation increasingly relies on large language models (LLMs) as scalable judges, yet frozen black-box models can interpret the same criteria inconsistently, produce score attributions that are difficult to audit, and map judgments poorly onto human scoring scales. We define this challenge as criteria transfer: translating human rubric intent into a stable, auditable inference-time scoring protocol. We introduce Rulers, which locks a task-level rubric specification, executes it through structured, evidence-grounded judgments, and calibrates the resulting signals to human score boundaries. Across four rubric-governed benchmarks and multiple frozen backbone models, Rulers achieves stronger agreement with human scores in most evaluated settings, while better matching empirical score distributions and remaining more stable under semantically equivalent rubric perturbations. Calibration controls and component ablations show that these gains cannot be attributed to post-hoc alignment alone, but depend on the combination of fixed criteria, traceable evidence, and calibrated score interpretation. These findings suggest that reliable LLM judging requires faithfully operationalizing human evaluation standards rather than relying on prompt-level scoring alone. Our code is available at https://github.com/LabRAI/Rulers.git.
Jan 12, 2026

What Are We Measuring in NLG? A Meta-Analysis of Evaluation Trends 2020-2025

As Natural Language Generation (NLG) dominates modern NLP, scalable evaluation remains a critical bottleneck. Consequently, LLM-as-a-judge (LaaJ) adoption has accelerated rapidly, appearing in more papers than human evaluation in 2025. This pivotal shift motivates a critical analysis of current evaluation practices. Overcoming the limits of rigid keyword filtering and manual review, we employ a multi-LLM information extraction pipeline to gather structured metadata from 14,171 papers across four major NLP conferences (2020-2025). Analyzing 3,334 filtered NLG papers, we identify three systemic challenges. (1) Metric inertia: despite the shift toward open-ended generation, legacy lexical metrics (BLEU, ROUGE) persist as primary indicators, typically used alongside rather than replaced by semantic alternatives. (2) Metric-criteria mapping problem: our paper-level co-occurrence data reveals that general-purpose automatic metrics are applied as broad proxies for quality, without specifying which dimension of text generation they are intended to evaluate. (3) Validation gap: LaaJ has grown rapidly without commensurate human validation (fewer than 8% of papers). Crucially, while LaaJ correlates with aggregate quality, alignment collapses on fine-grained criteria like fluency. To address these gaps, we distill our findings into a minimal Evaluation Checklist to guide metric selection, construct validity, and LaaJ deployment.
Jan 7, 2026

Gavel: Agent Meets Checklist for Evaluating LLMs on Long-Context Legal Summarization

Large language models (LLMs) now support contexts of up to 1M tokens, but their strengths and weaknesses on complex long-context tasks remain unclear. To study this, we focus on multi-document legal case summarization, where a single case often spans many documents exceeding 100K tokens. We systematically evaluate 12 frontier LLMs with Gavel, which consists of Gavel-Ref, a reference-based evaluation framework with checklist, residual-fact, and writing-style evaluations, and Gavel-Agent, a reference-free agent for evaluating factual coverage directly from source documents. Our results show that current models are more prone to omitting key information than hallucinating. They all perform well on simple checklist items, such as filing date, but struggle with rare and complex items, such as settlements. Performance also declines as case length increases. To meta-evaluate Gavel, we collect 160 hours of human annotations. Gavel-Agent reduces token usage by at least 36% compared to end-to-end and chunk-by-chunk methods while achieving competitive performance. Gavel-Agent also generalizes to the medical domain, performing the best with at least 77% fewer tokens.
Dec 23, 2025

Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration

Code from LLM-assisted development may contain defects like API hallucinations, motivating the development of code evaluation metrics to assess such code before deployment. As conventional rule-based metrics merely score code based on similarity to reference programs, and execution-based metrics require expensive manual preparation for tests, researchers have developed LLM-as-a-judge metrics for both behavioral and nonbehavioral code evaluation, and curated multiple benchmarks to validate their effectiveness. However, such benchmarks suffer from critical limitations: Some feature coarse-grained binary labels of passing/failing unit tests, unable to distinguish between fundamental and minor flaws; others utilize fine-grained criteria with manually annotated scores as ground-truth, but such criteria are often vaguely defined, introducing subjectivity and unreliability in human scores. Furthermore, they often directly prompt LLMs to generate code for evaluation, which may lead to unbalanced code quality distributions, failing to test the metrics' discriminative capability across varying quality levels. To curate a diverse benchmark with a balanced program quality distribution and streamline manual annotation, we propose AXIOM, a novel perturbation-based framework. It reframes program scores as the refinement effort needed for deployment, with two stages: (1) Quality-constrained semantic perturbation, prompting LLMs to apply sequences of predefined perturbation rules to existing programs, precisely controlling each program's target quality to achieve a balanced distribution. (2) Hybrid quality calibration, selecting semantically distinct programs for benchmark diversity, and performing streamlined manual annotation with multisource context. With AXIOM, we curate AXIOMBENCH, a large-scale multilingual benchmark with 1,962 code evaluation problems in a more balanced score distribution...
Dec 19, 2025

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens

LLM-as-a-Judge systems supply the reward signal in modern RLHF and RLVR pipelines, but their binary verdict reduces to a single linear readout F_gap on one hidden state. We show this readout is shallow enough that short, low-perplexity tokens flip the verdict from "No" to "Yes". These tokens are sampled from the judge's own next-token distribution at the response position, with no manual seed set and no gradient-based optimization. Our procedure, AdvJudge-Zero, reaches >>90% ensemble false-positive rate on 22 of 24 (model, dataset) cells across six Qwen, Llama, and Gemma judges, versus 54-72% for the prior curated 10-token benchmark, and the discovered surface transfers cross-format to a 70B scalar reward model. The same discovered pool enables a defense: a LoRA fine-tune stratified by a 9-class mechanism taxonomy hardens cross-family generalization where naive sampling on the same pool fails, with mechanism breadth rather than pool size carrying the gain. Under GRPO training, the hardened judge eliminates the reward-collapse failures (false-positive spikes and length collapse) we observe in the unhardened baseline on both MATH and GSM8K at ten seeds per condition. The discovered pool, the mechanism taxonomy, and per-prompt flip records will be released under responsible disclosure.
Nov 28, 2025

ORCA: Open-ended Response Correctness Assessment for Audio Question Answering

Reliable assessment of the abilities of large audio language models (LALMs) is essential to advancing the state of the art. As benchmarks rapidly evolve to incorporate complex reasoning and subjective tasks, they increasingly necessitate open-ended responses from LALMs. We present Open-ended Response Correctness Assessment (ORCA) -- a reliable and lightweight model-based approach for answer correctness and disagreement modeling. We employ a three-stage annotation pipeline combining human judgment, structured feedback, and human-AI correction, yielding 9,663 annotations across 3,699 question-answer pairs from 15 LALMs on three audio understanding and reasoning benchmarks (achieving a Krippendorff's alpha of 0.82). Our experiments employing curriculum learning show that ORCA models achieve a Spearman correlation of 0.91 with average human correctness ratings on seen benchmarks and generalize to unseen benchmarks with a score of 0.85, outperforming several LLM judge baselines including Gemini 2.5 Flash. Furthermore, we demonstrate that ORCA's predicted variance correlates strongly with human disagreement, allowing it to effectively identify problematic benchmark items.
Oct 28, 2025

Idea2Plan: Exploring AI-Powered Research Planning

Large language models (LLMs) have demonstrated significant potential to accelerate scientific discovery as valuable tools for analyzing data, generating hypotheses, and supporting innovative approaches in various scientific fields. In this work, we investigate how LLMs can handle the transition from conceptual research ideas to well-structured research plans. Effective research planning not only supports scientists in advancing their research but also represents a crucial capability for the development of autonomous research agents. Despite its importance, the field lacks a systematic understanding of LLMs' research planning capability. To rigorously measure this capability, we introduce the Idea2Plan task and Idea2Plan Bench, a set of benchmarks built from ICML 2025 and Nature Mental Health papers released after major LLM training cutoffs. Each benchmark instance includes a research idea and a grading rubric capturing the key components of valid plans. We further propose Idea2Plan JudgeEval, a complementary benchmark to assess the reliability of LLM-based judges against expert annotations. Experimental results show that GPT-5 achieves the strongest performance on the benchmark, though substantial headroom remains for improvement. Our study provides new insights into LLMs' capability for research planning and lays the groundwork for future progress.
Oct 23, 2025

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health records). To evaluate LLMs' ability to identify and redact such information, prior work introduced real-life, scenario-based benchmarks (e.g., ConfAIde, PrivacyLens) and found that LLMs can leak private information in complex scenarios. However, these evaluations relied on proxy LLMs to judge the helpfulness and privacy-preservation quality of LLM responses, rather than directly measuring users' perceptions. To understand how users perceive the helpfulness and privacy-preservation quality of LLM responses to privacy-sensitive scenarios, we conducted a user study (n=94n=94) using 90 PrivacyLens scenarios. We found that users had low agreement with each other when evaluating identical LLM responses. In contrast, five proxy LLMs reached high agreement, yet each proxy LLM had low correlation with users' evaluations. These results indicate that proxy LLMs cannot accurately estimate users' wide range of perceptions of utility and privacy in privacy-sensitive scenarios. We discuss the need for more user-centered studies to measure LLMs' ability to help users while preserving privacy, and for improving alignment between LLMs and users in estimating perceived privacy and utility.
Oct 9, 2025

BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution

Crowdsourced model evaluation platforms, such as Chatbot Arena, enable real-time evaluation from human perspectives to assess the quality of model responses. In the coding domain, manually examining the quality of LLM-generated content is extremely challenging, as it requires understanding long chunks of raw code and deliberately simulating code execution. To this end, we introduce BigCodeArena, an open human evaluation platform for code generation backed by a comprehensive and on-the-fly execution environment. Built on top of Chatbot Arena, BigCodeArena enables the execution of LLM-generated code and allows humans to interact with the execution process and outcomes. We collected over 14,000 raw code-centric conversation sessions across 10 widely used LLMs, spanning 10 languages and 8 types of execution environments. Among these conversations, we identified more than 4,700 multi-turn samples with pairwise human preferences. Further analysis uncovers underexplored preferences of LLMs in fine-grained domains characterized by tasks, languages, and frameworks. To systematically examine code understanding and generation capabilities of frontier LLMs, we curated two benchmarks based on the collected data, namely BigCodeReward and AutoCodeArena. For BigCodeReward, we post-processed the 4,700 conversations and evaluated the consistency between reward models and human preferences. The evaluation shows that most LLMs have superior performance in judging coding preferences when the execution results are available. Inspired by these findings, we propose AutoCodeArena, an automatic Elo rating benchmark designed to assess the coding quality of LLMs without human involvement. We find that proprietary LLMs like GPT-5, Claude-Sonnet-4, and Claude-Opus-4 still lead in code generation performance among recent emerging models.