Inter-Rater Reliability

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 31

Oct 7, 2026cs.CL

Nobody Truly Agrees on Sentiment: Humans, Bespoke Tools, and LLMs Struggle with Social Media Texts

Social media is a rich source of real-time public sentiment, but widely used sentiment analysis tools are often applied without understanding their limitations. In this study, we evaluate the inter-rater reliability of three bespoke sentiment analysis tools (TextBlob, VADER, and Twitter-roBERTa-base) and three large language models (LLMs: Qwen3-32B, GPT-OSS-120B, Llama-4-Maverick-17B) against six human raters across 100 tweets. We measured agreement using two statistical measures: Cohen's kappa for pairwise comparisons and Fleiss' kappa for multiple raters. Even among the human raters, our results showed only fair agreement, highlighting the subjectivity of sentiment analysis. Higher agreement was observed under the binary sentiment classification (negative vs. non-negative and positive vs. non-positive) than under the three-class classification across both humans and automated tools. The Twitter-roBERTa-base model showed the strongest alignment with human ratings, outperforming both bespoke sentiment tools and LLMs, particularly in distinguishing negative versus non-negative sentiment. LLMs showed substantial agreement among themselves and moderate to substantial alignment with humans, performing better in positive vs. non-positive classifications. Our findings underscore that domain-specific fine-tuning remains crucial for reliable social media sentiment analysis, and human-centered evaluation remains essential for establishing gold-standard labels.

Himarsha R. Jayanetti, Sivakanesan Dhanushkanda, Shuai Hao +2

Old Dominion University, Norfolk, Virginia, USA

Sentiment Analysis Social Media Analysis Inter-Rater Reliability LLM Evaluation

Oct 6, 2026cs.CL

Language-model ratings of depression reflect the rater more than the patient

Depression has no diagnostic blood test. Language models promise tireless, consistent assessment, but can accurate raters disagree about individuals? We pre-registered 880 language-model raters, crossing 11 open models with prompting and scoring choices, and applied them to 189 interviews against the eight-item Patient Health Questionnaire. Model choice explained 30.0% of summed-symptom score variance, stable participant differences 10.5%. Two randomly drawn raters with area under the receiver operating characteristic curve (AUC) >= 0.70 disagreed on screening decisions for 40% of participants, on average. Average over-rating governed how many were flagged, yet equal-capacity raters chose differently for about one participant in five. A locked analysis of 86 new interviews reproduced the main pre-registered findings. Exploratory recalibration with 40 labelled participants raised accuracy from about 60% to 75% and halved disagreement, leaving one participant in five decided differently. Calibration repaired much of the rater dependence without securing agreement about individuals.

Baihan Lin

Department of Artificial Intelligence and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, USA +2

Inter-Rater Reliability Annotator Disagreement Language Model Calibration Depression Severity Estimation Clinical Language Model Evaluation

Oct 5, 2026cs.AI

The Review Lottery: Benchmarking an Observational Estimator of Peer-Review Noise (ICLR 2017-2025)

How much of a conference accept/reject decision would change if the same paper were reviewed by a different set of reviewers? Running a second independent program committee is the gold standard for answering this, but it is prohibitively expensive: done only twice (NeurIPS 2014 and 2021). We build an observational estimator of this quantity from public review data alone, calibrate it twice, and apply it to nine years of ICLR (2017-2025; 36,113 papers, 134,912 reviews). The estimator decomposes scores with a Bayesian ordered-probit model into paper quality and reviewer noise, maps scores to decisions with a logistic model, and simulates two independent committees (posterior draws B=1,000; committee sizes k=2,3,4). Estimated disagreement rates are 23-30% at k=2 and 18-24% at k=4; 30-50% of accepted papers would be rejected. External calibration: at the NeurIPS 2021 reviewer-count caliber (k=3), the simulated 2021 disagreement rate is 23.3% [21.7%, 25.0%] vs. reported 23.0% (bias +0.3pp); accept precision and committee correlation agree within 5pp and 0.04. Internal calibration: on 18,740 papers with 4+ reviews, random model-free 2+2 reviewer splits agree with the k=2 simulation within 1pp in 2018 and 2021-2025. Longitudinally, we find no robust time trend in reviewer noise over 2017-2025. The high accepted-paper flip rates of 2020 and 2021 have distinct mechanisms: the 2020 four-point scale compressed scores (23.7% of papers had zero within-paper variance), and a counterfactual shows coarsening the scale raises disagreement by about 7pp; 2021 instead combined the lowest signal-to-noise ratio in the sample with the most threshold-crowded acceptances. For the LLM era, a 2023 breakpoint test on within-paper score variance finds no break, but the design has almost no power, and no post-2022 review text or confidence data exist, so no LLM attribution is attempted.

Feilian Huang

Independent researcher

Inter-Rater Reliability Annotator Disagreement Scholarly Peer Review

Sep 25, 2026cs.AI

LLM Judge Validation Under Sparse Overlap: From Inference to Design

Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. We prove that this overlap sparsity is the first-order determinant of wrong deployment decisions: at 5% pairwise overlap, wrong-decision rates reach 25% and the probability of selecting the wrong best judge among ten candidates is 65%. The two actionable levers are overlap quantity and allocation. For quantity, we derive a minimum-overlap formula showing

ρ\geq 0.25

suffices for non-borderline judges while borderline cases remain fundamentally hard. For allocation, a zero-cost stratified scheme halves false-rejection rates relative to random sampling when strata are informative. We validate on 10 LLM judges across four evaluation matrices spanning visual assessment, causal reasoning, and summarization.

Junxuan Li, Arko Mukherjee, Soumyabrata Pal

Adobe · Adobe Research

Inter-Rater Reliability LLM Evaluation LLM-as-a-Judge

Sep 14, 2026cs.LG

What an odour descriptor corpus can and cannot measure: valence, attenuation, and the ceiling of the public record

Machine olfaction trains on pooled public descriptor corpora, but whether a shared descriptor word measures the same thing across corpora has not been tested, nor has the ceiling of what any of them can measure. We audit four corpora from Pyrfume. Conditioning on the molecule makes McNemar's test the exact conditional test of the corpus effect. Corpora disagree heterogeneously across descriptors (

I^2 = 80\%

) and non-uniformly with labelling breadth (

z = 17.2

), so no single offset repairs pooling. Median tetrachoric agreement is 0.795 against median

\kappa

of 0.413: sources largely concur on which molecules deserve a word and differ on how readily they apply it. Of 109 descriptors with an estimable effect, 36 show large differential functioning on the ETS scale. Against a human panel's reliability, Morgan fingerprints with the full RDKit descriptor block reach 32.9% of achievable; adding every label from two merged corpora reaches 33.9%. The gap does not close with model capacity, encoding choice, more molecules, or more words. The missing variance is valence. One pleasantness rating per molecule reaches 54.6% of achievable (57.1% on an independent older instrument). Valence recovered from descriptors (

\rho = 0.457

) yields only 16.6%, so it must be measured. Five raters exceed structure plus the full descriptor record; fifteen to twenty saturate. We release a descriptor crosswalk and twenty machine-checked theorems.

Stylianos Kampakis, Fabio Rovai

Tesseract Academy, London, UK

Inter-Rater Reliability Molecular Property Prediction

Sep 8, 2026stat.AP

Bridging Network Psychometrics and Artificial Intelligence: An Ising-Potts Model with LLM-Derived Weights

The Potts model extends the Ising model to multinomial data. We introduce a Rater Ising-Potts model that uses agreement indicators between pairs of ratings and category labels, with weights derived from LLM embeddings. The model does not presuppose ordered category thresholds or equidistant scoring; instead, it focuses on pairwise agreement among ratings and assigns category-specific positive weights, making it suited for multi-category scoring reliability. We evaluate the model on three constructed-response datasets spanning a corpus of K=14,466 short answers on a three-level rubric and two AERA essay prompts of roughly 1,200-1,400 responses on four-point rubrics. We compare three strategies for sharpening the similarity signal: top-K pruning, min-max normalization with a power transformation, and ColBERT late-interaction similarities. Top-K pruning, which replaces the dense similarity graph with a sparse local network of strongest semantic neighbors, consistently yields the highest accuracy and Cohen's kappa, and the selected neighborhoods are always a small fraction of the corpus. Power tuning consistently ranks second, while ColBERT is competitive on longer essay prompts and adds little on short answers. Across all settings, most misclassifications occur between adjacent score levels, confirming that the model preserves the ordinal structure of scoring rubrics without imposing rigid assumptions. These findings suggest that LLM-derived similarities, combined with a parsimonious Potts formulation and a sparse local graph, offer a robust and interpretable framework for reliability auditing in educational assessment. We discuss extensions to multiple raters and hierarchical rating designs.

Matthias von Davier

Inter-Rater Reliability Psychometric Validation Rubric-Based Evaluation

Aug 10, 2026cs.LG

Finding the Signal in the Spam: Jointly Learning Rewards and Worker Reliability from Pairwise Comparisons

The problem of learning from pairwise comparisons has been widely studied across many domains such as recommendation systems, social choice, and more recently, fine-tuning large language models. In this problem, the goal is to learn item rewards based on pairwise comparisons between them. In many scenarios, these comparisons are elicited from crowdworkers using platforms such as Amazon Mechanical Turk, Scale AI, etc. However, crowdworkers are often unreliable due to limited domain knowledge or revenue-maximizing (spamming) behavior. In this work, our goal is to understand whether worker reliability (competency) can be learned jointly with item rewards. To this end, we adopt the Boltzmann-rational model for pairwise comparisons, which extends the Bradley-Terry-Luce model by incorporating worker competencies. We derive an EM-based algorithm for learning under this model by introducing Polya-Gamma latent variables to transform the logistic likelihood into a conditionally Gaussian form, enabling tractable optimization and leading to a simplified

Q

function in the E-step of the algorithm. This technique allows us to reduce our formulation to a matrix sensing problem, using which we establish theoretical convergence guarantees for our algorithm. We conduct extensive experiments on real-world and synthetic datasets. These experiments demonstrate the advantages of using our algorithm over several baselines and confirm its strong robustness to both spammers and adversarial workers, highlighting its practical effectiveness in realistic crowdsourcing and reward learning settings. The code and data is publicly available at https://github.com/KaustubhShejole/BoRa_EM.

Kaustubh Shivshankar Shejole, Tanish Agarwal, Arpit Agarwal +1

IIT Bombay, Mumbai, India – 400076

Pairwise Preference Learning Reward Modeling Inter-Rater Reliability Pairwise Preference Evaluation Learning with Noisy Labels

Aug 4, 2026cs.CL

Consensus Measures for Unstructured Biomedical Text Annotations

Biomedical literature is increasingly mined for knowledge beyond the questions it was written to answer. Because the target concepts are not known in advance, annotators prefer open-ended labels, whose agreement is hard to quantify. We study soft inter-rater reliability for annotators providing unstructured texts for biomedical annotation tasks. Synthetic experiments show that soft reliability can be quantified using a variety of semantic equivalence measures, and that the choice of measure affects failure modes of the estimation. Embeddings are scalable, but limited when differentiating similar but distinct concepts. Large language models are promising, but limited by scalability for estimating agreement by chance. Finally, we suggest measures based on natural language inference as a sensible compromise.

Pascal Wullschleger, Christian Kreis, Martin A. Walter +2

Hamilton Institute, Maynooth University, Ireland · University of Lucerne, Switzerland · Lucerne School of Computer Science and IT, Switzerland

Inter-Rater Reliability Semantic Textual Similarity

Jul 20, 2026cs.LG

AHEAD: Advancing Multi-Class Label Aggregation with Interpretable Cross-Annotator Modeling

Crowdsourced labeling provides valuable labeled data for domains across natural language processing, computer vision, and video. Label aggregation aims to infer latent true labels from noisy and biased annotations, with the key lying in annotator reliability estimation. Despite promising progress, existing approaches struggle with one real-world bottleneck: most individual annotators label only a small subset of tasks, making accurate annotator estimation highly intractable. In this paper, we focus on the considerably more challenging multi-class label aggregation and propose AHEAD (cross-Annotator learning and High-confidEnce Annotator-guideD label aggregation), a cross-annotator learning framework that advances annotator reliability estimation by leveraging the population-level data. Specifically, AHEAD first learns high-dimensional cross-annotator contexts via a graph neural network, deriving multi-view, complementary annotator embeddings by aggregating individual-level annotator features with contextual information. These embeddings are then decoded into interpretable annotator-specific confusion matrices to fit the observed labels. We formulate a composite objective incorporating high-confidence annotators to alleviate the unsupervised training issues faced by prior models. Experiments on 10 real-world datasets spanning NLP, CV, Video, and Audio show that AHEAD substantially improves label accuracy, increasing average accuracy from 68.75% to 73.23%, with gains of up to 14.9% in the best case. Meanwhile, scalability experiments on the largest dataset further demonstrate the overall superiority of our method.

Ju Chen, Sijia Xu, Jun Feng +2

Hohai University, China · University of New South Wales, Australia · Southeast University, China +1

Inter-Rater Reliability Noisy-Label Learning

Jul 8, 2026cs.CL

A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents

We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform, tested across three models in the Gemini family: 2.5 Flash, 3.5 Flash, and 3.1 Pro. Our primary evidence base uses Gemini 2.5 Flash as the ground-truth model, validated against three calibrated human raters on 209 stereo sessions, scored on 8 production dimensions: 152 full-duplex conversations across 13 accent-and-condition strata, together with 57 adversarial defect-injected clips. The evidence for Gemini 2.5 Flash is consistent across three tests. (i) On 5 of 8 dimensions the LALM-human Spearman rho departs from the pairwise human-human rho by at most 0.07, and on 7 of 8 dimensions the two quantities 95 percent bootstrap confidence intervals overlap. (ii) The LALM agrees with the three-rater human mean within 1 point on 60 to 92 percent of sessions on 6 of 8 dimensions. (iii) On 45 of 48 (defect, dimension) cells the LALM is as sensitive as humans or better under Newcombe-Wilson 95 percent confidence intervals, though most of these are underpowered nulls rather than demonstrated parity. Rank-ordering ability transfers across the Gemini family: 3.5 Flash improves simple agreement to 8 of 8 dimensions, while 3.1 Pro rates several dimensions markedly lower than humans despite comparable rank correlation. A model swap should be re-validated on calibration specifically, not assumed from rank-correlation alone. We identify four areas where deployment requires care, and we estimate that human rating alone for our current evaluation cadence costs roughly two orders of magnitude more than the equivalent LALM workload. The data presented here provides a defensible empirical basis for deploying the LALM as a substitute or fourth rater on the dimensions where the evidence supports it.

A. Sayyad, J. Emmons, S. Jones +2

Salesforce Applied AI Research, eVerse team

Audio-Language Model Evaluation Voice Agent Evaluation Inter-Rater Reliability LLM-as-a-Judge

Jun 24, 2026cs.CL

Introducing corpora Hlava Cor and Hlava AD: Human Label Variation in Coreference and Discourse Relations

As previous research on annotator disagreement in discourse phenomena has shown, understanding text coherence varies considerably from one individual to another. To explore this phenomenon, we created two corpora with multiple annotations of Czech texts, accompanied by annotators' explanations of their choices. The first corpus consists of 1,024 contexts annotated in parallel by three annotators. It captures differences in the identification of coreference across various text types and grammatical-semantic categories, including pronouns, full noun phrases, and anaphoric adverbials. The second corpus comprises 512 contexts, annotated in parallel by five annotators, and focuses on identifying discourse relations in attributive and non-attributive constructions. Both corpora achieve a comparable inter-annotator agreement of approximately 60-65%. For coreference annotation, agreement tends to be lower in cases where automatic coreference resolution models disagree, suggesting that when the models disagree, the examples tend to be more difficult or ambiguous for human annotators to interpret. The annotators' comments, both for coreference and discourse relations, further reveal differences in interpretation, varying levels of confidence in text understanding, and individual reading strategies.

Anna Nedoluzhko, Šárka Zikánová, Jiří Mírovský +2

Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics, Prague, Czech Republic

Inter-Rater Reliability Coreference Resolution Annotator Disagreement

Jun 22, 2026cs.CY

The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Regions with a Language-Model Panel

Most tools for measuring political positions, manifesto coding, expert surveys, text-scaling models, were built and validated on Western party systems, and outside that setting they work poorly, and often not at all. This paper is an attempt at a method for those settings. It treats a large language model not as a measurement device but as a single, fallible rater in a panel, roughly the way an expert survey treats one expert: the value comes from pooling many judges rather than trusting any one of them. I describe the panel, an applicability rule that keeps a score of zero distinct from a blank, and a lens system that separates what an actor says from what it does. I report three results. First, holding a definition-free round fixed, adding written axis definitions moves scores by a mean of 1.8 points on a 21-point scale and tightens agreement between raters (mean absolute gap 2.81 to 2.50; r 0.81 to 0.89); they make two independent raters agree more closely, which an arbitrary steer would not. Second, across nine models from eight laboratories in two countries, Krippendorff's alpha is 0.86 on both an interval and an ordinal metric, and it stayed put as the panel grew from five raters to nine. That is reliability, the reproducibility of a reading, and not validity, its correctness. Third, where the panel does disagree, the disagreement is informative: the sharpest split, a full-scale divergence on an actor's stance toward its state's foundational order, points to a referent problem, and a blind triple-coding puts about two-thirds of it down to interpretation rather than error. I try to be plain about what the method can't do, including the human validation it still lacks, and I release the instrument and data in full. The worked example is the Middle East and North Africa, but I'd expect the method to carry to any region these standard tools leave out.

Tarek Gara

*Independent researcher.

Inter-Rater Reliability LLM-Assisted Annotation LLM Reliability

Jun 17, 2026cs.CL

Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias

LLM-as-a-Judge has become the dominant evaluation paradigm for language models, but judge validation in practice relies on exact-match agreement, a metric that does not correct for chance and systematically overstates discriminative ability. We present the largest systematic evaluation of LLM-as-a-Judge to date: 21 judges from nine providers across MT-Bench, JudgeBench, and RewardBench, evaluated under three protocols (agreement, consistency, bias audit) over 118 runs and approximately 541,000 individual judgments. Four findings emerge, consistent across the full cohort, including the April 2026 frontier: kappa deflation between exact match and Cohen's kappa is universal (33--41 pp on MT-Bench), judge rankings shift by up to 14 positions across benchmarks, high test--retest reliability (>0.95) coexists with severe position bias (>0.10) in two production-deployed judges (instantiating a consistency--bias paradox), and verbosity bias is small (<0.011) across our cohort under a single pairwise rubric. We distill these into a Minimum Viable Validation Protocol.

Justin D. Norman, Michael U. Rivera, D. Alex Hughes

UC Berkeley School of Information 102 South Hall Drive, Berkeley CA, 94708

Inter-Rater Reliability LLM Evaluation LLM-as-a-Judge LLM Reliability Language Model Bias Evaluation Benchmark Validity+1

Jun 15, 2026cs.CV

Attention-Based Prototype Calibration for Multi-Rater Few-Shot Medical Image Segmentation

Few-shot medical image segmentation methods typically assume a single ground-truth annotation, overlooking systematic variability across expert raters commonly observed in clinical datasets. We propose an attention-based prototype calibration framework for few-shot multi-rater segmentation that models rater-specific deviations from a consensus representation in prototype space. A lightweight yet principled attention operator directly refines rater prototypes without modifying the backbone feature extractor, making the approach fully compatible with existing prototype-based few-shot segmentation methods. This design preserves semantic consistency while enabling personalized segmentation outputs with minimal computational overhead. Experiments on multi-rater medical imaging datasets demonstrate consistent improvements over baseline prototype approaches, highlighting the effectiveness of structured prototype calibration for modeling annotation variability.

Truong Vu, Minh Khoi Ho, Yutong Xie

Mohamed bin Zayed University of Artificial Intelligence

Prototype-Based Learning Inter-Rater Reliability Medical Image Segmentation Few-Shot Medical Image Segmentation

Jun 11, 2026stat.AP

Event-Aligned Analysis of Multi-Rater Pain Assessments Using Continuous Wearable Physiology

Pain is assessed differently by patients, nurses, and clinicians, yet most computational approaches assume a single ground-truth label - effectively ignoring who is doing the rating. We introduce a rater-aware, event-aligned framework that converts sparse, rater-specific pain ratings into discrete pain-change events and aligns continuous wearable physiological signals to these events, preserving rater identity throughout. Applied to multimodal wearable data collected during spine-related pain procedures, the framework identifies substantial disagreement across rater groups and provides preliminary, exploratory evidence of rater-dependent physiological differences preceding reported pain increases. These findings suggest that pain-physiology relationships may not be rater-invariant, and that aggregating assessments across raters may mask meaningful physiological patterns. A rater-aware, event-aligned perspective is therefore a promising direction for interpreting wearable data in real-world clinical pain assessment.

Saba A. Farahani, Elahe Khatibi, Thomas D. Hughes +3

University of California, Irvine · Irvine, CA, USA

Inter-Rater Reliability Annotator Disagreement Wearable Sensing Wearable Health Monitoring

Jun 10, 2026cs.IR

Factions Within, Uncertain Across: Within-Document Reader Sub-Groups in Social Highlighting

When many people highlight the same document, is the crowd a single consensus, or is it internally structured into reader sub-groups that mark different things -- and is that structure a stable property of a reader or of the document? Building on prior work showing an individual's within-document highlighting signal is a whisper while individuality lives in selection, we ask the group-level question on a co-readership platform using a margin-preserving curveball null. Experiment 1: within a document, readers form strong sub-groups -- pairs agree far beyond what shared salience, mark density, and sentence popularity predict (nearest-neighbour agreement z=+6.3, significant in 88% of documents). Under an eight-block region-preserving null, shared engagement with the same coarse regions of the document accounts for about 40% of this excess; the majority survives as finer reader-specific agreement (z=+3.6, 77% significant). So the within-document crowd is, in a descriptive sense, factional. Experiment 2: is that grouping a stable reader trait? Here we are honest about power. The cross-document split-half reproducibility of a pair's agreement is near zero pooled (+0.078 and 0.000 in two separately drawn samples), and a power calibration shows the test is informative only for pairs that co-read many documents. In the only informative high-overlap subset (k>=4), point estimates are positive but small-sample, imprecise across the separately drawn samples, never significant, and attenuate under the region-preserving null. We therefore leave cross-document stability unresolved: the data is consistent with anything from situational grouping to a weak-to-moderate stable reader trait. The crowd is factional within a document; whether its factions follow the reader across documents is, honestly, beyond our reach.

Kazuki Nakayashiki, Keisuke Watanabe

Glasp Inc.

Inter-Rater Reliability Annotator Disagreement

Jun 2, 2026cs.CL

The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human Alignment

LLM judges now score most open-ended NLP output, and their mutual agreement is routinely read as evidence that the scores can be trusted. That reading is unsafe: judges may agree because they capture quality, or because they share the same blind spots, and agreement statistics alone cannot tell these apart. We develop a geometric test that can. Treating each judge's scores as a vector, we measure spread, effective rank, the angle to human scores, and the judge-judge, judge-human, and human-human agreement triple for 42 judges on two community-built Indic benchmarks covering four domains and eight languages. Every comparison is reference-matched: a judge and a held-out rater are scored against the same two-rater mean, since an averaged reference otherwise flatters judges by several degrees. On subjective rubrics, judges agree with one another as much as humans do yet reach only 58-66% of human agreement and often concentrate on an axis humans do not weight. On the one rubric with a verifiable answer, most of that gap closes. Ensembles converge on the judges' shared axis rather than the human one, and training widens scores without rotating them. Inter-judge agreement is evidence of human alignment only after this check passes.

Sourabrata Mukherjee, Hamna Hamna, Kalika Bali +1

Microsoft Research

Inter-Rater Reliability Multilingual Language Model Evaluation LLM Evaluation LLM-as-a-Judge LLM Reliability

May 30, 2026cs.CV

Benchmarks for Vision-Language Models in Urban Perception Should Be Reliability-Aware and Negotiated

Vision-language models (VLMs) are increasingly used to generate structured descriptions of street-level imagery for tasks such as streetscape auditing, mapping, and public consultation. These uses combine observable attributes with appraisal categories, and the human targets are often distributions of judgments with disagreement and explicit non-response. This paper argues that benchmarking VLMs for urban perception should treat disagreement and abstention as measurement outcomes, report inter-annotator reliability alongside model alignment, and treat the label space and scoring policy as negotiable artifacts when outputs are intended to inform urban governance. We ground the argument in a benchmark of 100 Montreal street scenes annotated along 30 dimensions by 12 participants from seven community organizations, and in a deterministic zero-shot evaluation of seven VLMs. Across dimensions, model agreement with human consensus co-varies with dimension-level human reliability, and for the appraisal dimension Overall Impression models and annotators exhibit distributional mismatch including different rates of Not applicable. We close with actions for benchmark creators, model developers, and institutions to make uncertainty and benchmark assumptions visible in evaluation reports.

Rashid Mushkani

Université de Montréal, Montréal, Québec, Canada · Mila – Québec AI Institute, Montréal, Québec, Canada

VLM Evaluation Inter-Rater Reliability Vision-Language Models

May 25, 2026cs.CL

A Two-Phase Stability Study of LLM Judges and Bar Council Examiners on Thai Bar-Exam Free-Form Essays

Free-form legal essay evaluation in NLP treats expert inter-rater stability as a single ceiling number, and treats LLM-judge agreement with that ceiling as evidence of judge stability. We test both assumptions on the Thai bar examination through an identical-inputs protocol: three Bar Council-trained examiners (A, B, C) and a 26-LLM judge panel score the same 15 cross-graded answers from the same four inputs (question, official Bar Council grading regulation, gold answer, candidate answer). The headline finding is asymmetric. On 10 of 15 cells where the rubric prescribes both axes, all 29 raters converge in a tight band: panel agreement is universal. On the remaining 5 cells where the rubric does not prescribe how to grade a correct final answer that omits a decisive statutory citation, the human panel splits between two coherent readings (B/C majority at the upper rubric band, score 6-8; A minority at the lower band, score 1-2). The LLM judge population does not split symmetrically: 22 of 26 LLMs score in or near B/C's contested band, 3 sit in the regulation-silent middle gap, and only 1 (GPT-5.4 Nano) approaches A's band without consistently scoring within it. Zero LLMs in our 26-judge panel reproduce the minority human reading on the contested cells. The B/C-direction cluster spans every model size, vendor, and price tier we tested. An instrumented three-LLM anchor sub-panel (Claude 4.6 Opus, Gemini 3.1 Pro, GPT-5.4 Pro) carries determinism probes, input ablations, and bootstrap CIs, and reaches anchor panel

α= 0.77

on the 15 cells against human-panel

α= 0.36

. The high LLM-panel

α

reflects systematic convergence on the majority reading rather than balanced reproduction of both readings; a benchmark that selects its LLM judge by maximising agreement with a human reference panel will inherit this asymmetry by construction.

Pawitsapak Akarajaradwong, Wuttikrai Lertprasertphakorn, Chompakorn Chaksangchaichot +1

VISAI AI · Independent Researcher · Vidyasirimedhi Institute of Science and Technology

Inter-Rater Reliability Annotator Disagreement LLM-as-a-Judge Automated Essay Scoring Rubric-Based Evaluation

May 25, 2026cs.CL

Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why

Validating an LLM judge against human annotations usually means reporting several agreement statistics: accuracy, precision, recall,

F_1

, Cohen's

κ

, and one or more rank correlations. A survey of 24 recent LLM-as-judge papers finds metric choice entangled with the judgment scale, tie handling, invalid outputs, and abstention handling, and those choices rarely stated. For binary criteria -- the common case in rubric-based evaluation, where each criterion is graded MET or UNMET -- most of the reported numbers are redundant: Pearson's

r

, Spearman's

ρ

, Kendall's

τ_b

, the phi coefficient

φ

, and the Matthews Correlation Coefficient all reduce to a single number on non-degenerate binary data, so reporting several of them only creates an illusion of corroborating evidence. Cohen's

κ

is the one agreement coefficient that adds information: it shares

φ

's numerator but normalizes differently, and the gap between them measures how far the judge's positive-label rate has drifted from the human's. We then trace what changes when a judge may abstain with a CANNOT_ASSESS verdict: the three common ways of handling abstentions are not interchangeable preprocessing choices but answer different questions, and they break the binary equivalences. The same equivalences reappear, up to a negligible finite-sample correction, for multi-judge ensembles scored with Fleiss'

κ

or Krippendorff's

α

. We close with a reporting checklist that names the judgment scale, the abstention and tie handling mode, coverage, the confusion matrix, and the aggregation level alongside any scalar agreement coefficient.

Delip Rao, Chris Callison-Burch

University of Pennsylvania

Inter-Rater Reliability LLM Evaluation LLM-as-a-Judge Language Model Generation Evaluation

May 13, 2026cs.LG

Improving Reproducibility in Evaluation through Multi-Level Annotator Modeling

As generative AI models such as large language models (LLMs) become more pervasive, ensuring the safety, robustness, and overall trustworthiness of these systems is paramount. However, AI is currently facing a reproducibility crisis driven by unreliable evaluations and unrepeatable experimental results. While human raters are often used to assess models for utility and safety, they introduce divergent biases and subjective opinions into their annotations. Overcoming this variance is exceptionally challenging because very little data exists to study how experimental repeatability actually improves as the annotator pool grows. Standard evaluation practices typically rely on a small number of annotations per item (often 3 to 5) and lack the persistent rater identifiers necessary to model individual variance across items. In this work, we introduce a multi-level bootstrapping approach to realistically model annotator behavior. Leveraging datasets with a large number of ratings and persistent rater identifiers, we analyze the tradeoffs between the number of items (

N

) and the number of responses per item (

K

) required to achieve statistical significance.

Deepak Pandita, Flip Korn, Chris Welty +1

Rochester Institute of Technology · Google Research

Inter-Rater Reliability LLM Evaluation Human-in-the-Loop Evaluation ML Reproducibility

May 7, 2026cs.CL

Quantifying the Statistical Effect of Rubric Modifications on Human-Autorater Agreement

Autoraters, also referred to as LLM-as-judges, are increasingly used for evaluation and automated content moderation. However, there is limited statistical analysis of how modifications in a rubric presented to both humans and autoraters affect their score agreement. Rubrics that ask for an overall or \emph{holistic} judgment - for example, rating the

quality'' of an essay - may be inconsistently interpreted due to the complexity or subjectivity of the criteria. Conversely, rubrics can ask for \emph{analytic} judgments, which decompose assessment criteria - for example,

quality'' into fluency'' and organization''. While these rubrics can be edited to improve the individual accuracy of both human and automated scoring, this approach may result in disagreement between the two scores, or with the associated holistic judgment. Designing and deploying reliable autoraters requires understanding not just the relationship between human and autorater annotations but how that relationship changes as holistic or analytic judgments are elicited. The results indicate that rubric edits providing representative examples and additional context, and reducing positional bias in the rubric increased human-autorater agreement, while higher rubric complexity and conservative aggregation methods tended to decrease it. The findings from the automatic essay scoring and instruction-following evaluation domains suggest that practitioners should carefully analyze domain- and rubric-specific performance to move towards higher human-autorater agreement.

Jessica Huynh, Alfredo Gomez, Athiya Deviyani +3

Carnegie Mellon University · Google Research

Inter-Rater Reliability LLM-as-a-Judge Rubric-Based Evaluation

May 4, 2026cs.CV

Multi-Rater Calibrated Segmentation Models

Objective: Accurate probability estimates are essential for the safe deployment of medical image segmentation models in clinical decision-making. However, modern deep segmentation networks are often poorly calibrated, a problem exacerbated when multiple expert annotations exhibit substantial disagreement. While inter-rater variability is typically treated as noise, it provides valuable information about intrinsic annotation ambiguity that must be reflected in model confidence. Methods: We improve the probabilistic calibration of medical image segmentation models by reformulating multi-rater supervision as an ordinal learning problem. Voxel-wise annotator agreement is treated as an ordered target, linking predictive confidence to the empirical variability in training data. This formulation allows the use of ordinal-aware scoring rules, such as the Ranked Probability Score ordinal loss, combined with a standard binary objective to preserve discriminative performance. Results: We evaluated the proposed approach across four public segmentation benchmarks spanning ophthalmology, histopathology, and thoracic imaging. Calibration was assessed using a multi-rater extension of expected calibration error. Results consistently show that ordinal-aware training yields substantially improved calibration with respect to inter-rater agreement without degrading segmentation accuracy. Conclusions: Treating multi-rater annotations as ordered information provides a principled and architecture-agnostic route to more reliable probabilistic segmentation models.

Meritxell Riera-Marín, Javier García López, Júlia Rodríguez-Comas +2

aSycai Technologies SL, Scientific and Technical Department, Barcelona, Spain · bBCN Medtech, Universitat Pompeu Fabra, Barcelona, Spain · cInstitució Catalana de Recerca i Estudis Avançats (ICREA), Barcelona, Spain +1

Inter-Rater Reliability Image Segmentation Probability Calibration Medical Image Segmentation Segmentation Uncertainty Estimation

Apr 30, 2026cs.CV

Assessing Pancreatic Ductal Adenocarcinoma Vascular Invasion: the PDACVI Benchmark

Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate assessment of vascular invasion (VI), i.e., tumor extension into adjacent critical vessels. Despite its importance for preoperative staging and surgical planning, computational VI assessment remains underexplored. Two major challenges are the lack of public datasets and the diagnostic ambiguity at the tumor-vessel interface, which leads to substantial inter-rater variability even among expert radiologists. To address these limitations, we introduce the CURVAS-PDACVI Dataset and Challenge, an open benchmark for uncertainty-aware AI in PDAC staging based on a densely annotated dataset with five independent expert annotations per scan. We also propose a multi-metric evaluation framework that extends beyond spatial overlap to include probabilistic calibration and VI assessment. Evaluation of six state-of-the-art methods shows that strong global volumetric overlap does not necessarily translate into reliable performance at clinically critical tumor-vessel interfaces. In particular, methods optimized for binary segmentation perform competitively on average overlap metrics, but often degrade in high-complexity cases with low expert consensus, either collapsing in volume or overextending at uncertain boundaries. In contrast, methods that model inter-rater disagreement produce better calibrated probabilistic maps and show greater robustness in these ambiguous cases. The benchmark highlights the limitations of volumetric accuracy as a proxy for localized surgical utility, motivating uncertainty-aware probabilistic models for preoperative decision-making.

M. Riera-Marín, O. K. Sikha, J. Rodríguez-Comas +23

BCN Medtech, Universitat Pompeu Fabra, Barcelona, Spain · Universitätsklinikum Erlangen, Department of Radiology of the Uniklinikum Erlangen (UKER), Erlangen, Germany · University Hospital Erlangen, Imaging Science Institute, Erlangen, Germany +10

Inter-Rater Reliability Medical Image Analysis Medical Image Segmentation Oncology Segmentation Uncertainty Estimation Medical Image Benchmarks

Apr 23, 2026cs.CL

The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation

LLM-as-a-Judge is now widely used to rank model outputs, train reward models, and populate public leaderboards, but its run-to-run reliability remains under-characterized. We study repeated identical evaluations on 29 tasks spanning 10 categories using two OpenAI judge models (GPT-4o-mini and GPT-4.1-mini), with 50 pairwise trials and 50 pointwise trials per question, supplemented by temperature and prompt-sensitivity ablations. Across judges, pairwise preferences flip on average 13.6% of the time, with 28% of questions exceeding a 20% flip rate and one question reaching 56%. GPT-4o-mini also exhibits a significant first-position bias (72% A-majority, p = 0.024). At the same time, mean pointwise score gaps are small (0.19--0.36 on a 10-point scale) and not statistically significant in aggregate, producing a pairwise--pointwise gap: judges frequently choose a winner even when their own scalar scores provide little evidence of a meaningful quality difference. Beyond within-judge instability, cross-judge agreement is only 76% (

κ= 0.51

), semantically equivalent prompt templates change majority outcomes in 25% of tested cases, and deterministic decoding reduces but does not eliminate inconsistency. A reliability curve analysis shows that, in our dataset, 11 repeated trials are needed for a majority vote to recover the 50-trial reference verdict with 95% probability on average, rising to 15 for high-variance questions. These findings suggest that single-trial LLM judging is often too noisy for high-stakes evaluation, and that multi-trial aggregation, position randomization, and explicit uncertainty reporting should be standard practice. Because both judges are from a single provider, cross-provider replication remains an important next step.

Abel Yagubyan

Independent Researcher

Inter-Rater Reliability LLM Evaluation Pairwise Comparison LLM-as-a-Judge Bias in LLM-as-a-Judge Position Bias

Apr 21, 2026cs.CL

Structured Disagreement in Health-Literacy Annotation: Epistemic Stability, Conceptual Difficulty, and Agreement-Stratified Inference

Annotation pipelines in Natural Language Processing (NLP) commonly assume a single latent ground truth per instance and resolve disagreement through label aggregation. Perspectivist approaches challenge this view by treating disagreement as potentially informative rather than erroneous. We present a large-scale analysis of graded health-literacy annotations from 6,323 open-ended COVID-19 responses collected in Ecuador and Peru. Each response was independently labeled by multiple annotators using proportional correctness scores, reflecting the degree to which responses align with normative public-health guidelines, allowing us to analyze the full distribution of judgments rather than aggregated labels. Variance decomposition shows that question-level conceptual difficulty accounts for substantially more variance than annotator identity, indicating that disagreement is structured by the task itself rather than driven by individual raters. Agreement-stratified analyses further reveal that key social-scientific effects, including country, education, and urban-rural differences, vary in magnitude and in some cases reverse direction across levels of inter-annotator agreement. These findings suggest that graded health-literacy evaluation contains both epistemically stable and unstable components, and that aggregating across them can obscure important inferential differences. We therefore argue that strong perspectivist modeling is not only conceptually justified but statistically necessary for valid inference in graded interpretive tasks.

Olga Kellert, Sriya Kondury, Candice Koo +2

Arizona State University

Inter-Rater Reliability Annotator Disagreement

Apr 21, 2026cs.AI

Has Automated Essay Scoring Reached Sufficient Accuracy? Deriving Achievable QWK Ceilings from Classical Test Theory

Automated essay scoring (AES) is commonly evaluated on public benchmarks using quadratic weighted kappa (QWK). However, because benchmark labels are assigned by human raters and inevitably contain scoring errors, it remains unclear both what QWK is theoretically attainable and what level is practically sufficient for deployment. We therefore derive two dataset-specific QWK ceilings based on the reliability concept in classical test theory, which can be estimated from standard two-rater benchmarks without additional annotation. The first is the theoretical ceiling: the maximum QWK that an ideal AES model that perfectly predicts latent true scores can achieve under label noise. The second is the human-like ceiling: the QWK attainable by an AES model with human-level scoring error, providing a practical target when AES is intended to replace a single human rater. We further show that human--human QWK, often used as a ceiling reference, can underestimate the true ceiling. Simulation experiments validate the proposed ceilings, and experiments on real benchmarks illustrate how they clarify the current performance and remaining headroom of modern AES models.

Masaki Uto

The University of Electro-Communications, Tokyo, Japan

Inter-Rater Reliability Educational Assessment Automated Essay Scoring Psychometric Validation

Aug 6, 2025cs.LG

Honest and Reliable Evaluation and Expert Equivalence Testing of Automated Neonatal Seizure Detection

Reliable evaluation of machine learning models for neonatal seizure detection is critical for clinical adoption. Current practices often rely on inconsistent and biased metrics, hindering model comparability and interpretability. Expert-level claims about AI performance are frequently made without rigorous validation, raising concerns about their reliability. This study aims to systematically evaluate common performance metrics and propose best practices tailored to the specific challenges of neonatal seizure detection. Using real and synthetic seizure annotations, we assessed standard performance metrics, consensus strategies, and human-expert level equivalence tests under varying class imbalance, inter-rater agreement, and number of raters. Matthews and Pearson's correlation coefficients outperformed the area under the curve in reflecting performance under class imbalance. Consensus types are sensitive to the number of raters and agreement level among them. Among human-expert level equivalence tests, the multi-rater Turing test using Fleiss k best captured expert-level AI performance. We recommend reporting: (1) at least one balanced metric, (2) Sensitivity, specificity, PPV and NPV, (3) Multi-rater Turing test results using Fleiss k, and (4) All the above on held-out validation set. This proposed framework provides an important prerequisite to clinical validation by enabling a thorough and honest appraisal of AI methods for neonatal seizure detection.

Jovana Kljajic, John M. O'Toole, Robert Hogan +1

Faculty of Technical Sciences, University of Novi Sad, 21000 Novi Sad, Serbia · CergenX Ltd, Dublin, Ireland

Inter-Rater Reliability Automated Evaluation

May 29, 2024cs.LG

Hierarchical Bayesian Crowdsourcing with Item Difficulty

In applied statistics and machine learning, the gold standards used for training are often biased and almost always noisy. Dawid and Skene's justifiably popular crowdsourcing model adjusts for rater sensitivity and specificity, but fails to capture distributional properties of rating data gathered for training, which in turn biases training. In this study, we introduce a general purpose measurement-error model with which we can infer consensus categories by adding item-level effects for difficulty, discriminativeness, and guessability. We further show how to constrain the bimodal posterior of these models to avoid adversarial raters. We validate our model's goodness of fit with posterior predictive checks, the Bayesian analogue of

χ^2

tests, and assess its predictive accuracy using leave-one-out cross-validation. We illustrate our new model with two well-studied data sets, binary rating data for caries in dental X-rays and implication in natural language.

Seong Woo Han, Ozan Adıgüzel, Bob Carpenter

University of Pennsylvania · Columbia University · Center for Computational Mathematics, Flatiron Institute

Inter-Rater Reliability Latent Variable Models Bayesian Inference Hierarchical Bayesian Modeling Learning with Noisy Labels

Date pendingcs.AI

Measurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation

Agentic AI evaluation pipelines produce benchmark scores that justify deployment decisions, safety certifications, and regulatory compliance claims. No formal framework has yet characterized how validity degrades across the stages of these pipelines. We present a three-layer compounding validity model,

V_{total} \leq V_1 \times V_2 \times V_3

, that captures multiplicative degradation across task generation (

V_1

), human-simulator calibration (

V_2

), and automated judgment (

V_3

). Under empirically grounded estimates, a pipeline retaining 70% validity at each stage is at most 34% valid against the intended construct (range 0.17-0.54 across the empirical estimate bounds). We examine the model's predictions against a structured survey of 55 published agentic evaluation papers, finding that approximately 82% of papers in this purposive sample apply structurally mismatched, incomplete, or absent inter-rater reliability (IRR) metrics, a pattern consistent with systematic

V_3

collapse. We further identify empirical evidence of

V_1

failures (task validity flaws in 7 of 10 popular benchmarks) and

V_2

miscalibration (up to 9 percentage points inter-simulator variance, with systematic demographic disparities for non-Standard American English speakers). We derive eight prescriptions grounded in psychometric science and domain-stratified reliability thresholds (ICC

\geq

0.70;

\alpha \geq

0.67/0.70/0.80 by consequence level) that practitioners and benchmark authors can apply immediately. The framework provides a tractable knowledge-based tool for diagnosing and correcting evaluation pipeline validity before deployment decisions are made.

William Caban

Red Hat, Inc., Raleigh, North Carolina, USA · Alma Mater Europaea University, Vienna, Austria

Inter-Rater Reliability AI Agent Evaluation AI Agent Benchmarks Psychometric Validation Benchmark Validity