Human Preference Evaluation

Momentum

4 papers in the last four weeks, down 33% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 41

May 6, 2026cs.CL

Why Expert Alignment Is Hard: Evidence from Subjective Evaluation

Aligning large language models with expert judgment is especially difficult in subjective evaluation tasks, where experts may disagree, rely on tacit criteria, and change their judgments over time. In this paper, we study expert alignment as a way to understand this difficulty. Using expert evaluations and follow-up questionnaires, we examine how different forms of expert information affect alignment and what this reveals about subjective judgment. Our findings show four consistent patterns. First, alignment difficulty varies substantially across experts, suggesting that expert evaluation styles differ widely in their distance from a model's prior behavior. Second, explicit criteria and reasoning do not always improve alignment, indicating that expert judgment is not fully captured by verbalized rules. Third, editing is sensitive to both the number and the identity of examples, with small numbers of edits providing useful but unstable gains. Fourth, alignment difficulty differs across evaluation dimensions: dimensions grounded more directly in proposal content are easier to align, while dimensions requiring external knowledge or value-based judgment remain harder. Taken together, these results suggest that expert alignment is difficult not only because of model limitations, but also because subjective evaluation is inherently heterogeneous, partly tacit, dimension-dependent, and temporally unstable.

Tzu-Mi Lin, Wataru Hirota, Tatsuya Ishigaki +2

National Yang Ming Chiao Tung University, Taiwan · Stockmark, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Japan +1

Human Preference Evaluation LLM Alignment Human-in-the-Loop Evaluation

Ask PDF

May 5, 2026cs.CV

WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models

Evaluating generative video models remains an open problem. Reference-based metrics such as Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) reward pixel fidelity over semantic correctness, while Frechet Video Distance (FVD) favors distributional textures over physical plausibility. Binary Visual Question Answering (VQA) based benchmarks like VBench~2.0 are prone to yes-bias and rely on low-resolution auditors that miss temporal failures. Moreover, their prompts target a single dimension at a time, multiplying the number of videos required while still not guaranteeing reliable results. WorldJen addresses these limitations directly. Binary VQA is replaced with Likert-scale questionnaires graded by a VLM that receives frames at native video resolution. Video generation costs are addressed by using adversarially curated prompts that are designed to exercise up to 16 quality dimensions simultaneously. The framework is built around two interlocking contributions. First, A blind human preference study is conducted, accumulating (2,696 pairwise annotations from 7 annotators with 100% pair coverage over 50 of the curated prompts

\times

6 state-of-the-art video models. A mean inter-annotator agreement of 66.9% is achieved and the study establishes a human ground-truth Bradley-Terry (BT) rating with a three-tier structure. Second, A VLM-as-a-judge evaluation engine using prompt-specific, dimension-specific Likert questionnaires (10 questions per dimension, 47,160 scored responses) judges the videos and reproduces the human-established three-tier BT rating structure independently. The VLM achieves a Spearman

\hatρ=1.000,~p=0.0014

that is interpreted as tier agreement with the human results. Six focused ablation studies validate the robustness of the VLM evaluation framework. Project page: https://moonmath.ai/worldjen/

Karthik Inbasekar, Guy Rom, Omer Shlomovits

Human Preference Evaluation Video Quality Assessment Vision-Language Model-as-a-Judge Video Generation Evaluation

Ask PDF

Apr 27, 2026cs.CY

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers

The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act in a given situation. Studies of agent-type value forks challenge this assumption by showing that people do not always judge humans and AI systems identically.This paper extends that challenge by examining two further possibilities: first, that evaluations of AI behavior change when its human origins are made visible; and second, that people judge the humans who program AI systems differently from either the machines or the human actors they are compared against. An experiment with 1,002 U.S. adults measured moral judgments in a runaway mine train scenario, varying the subject of evaluation across four conditions: a repairman, a repair robot, a repair robot programmed by company engineers, and company engineers programming a repair robot. We find no significant difference in evaluations of the repairman and the robot. However, judgments shifted substantially when the robot's actions were described as the product of human design. Participants exhibited markedly more deontological, rule-based reasoning when evaluating either the programmed robot or the engineers who programmed it, suggesting that rendering human agency visible activates heightened moral constraints. These findings indicate that people may evaluate humans, AI systems acting in the same situation, and the humans who design them in meaningfully different ways. The fact that these evaluations do not necessarily converge gives rise to the alignment target problem: which normative target should guide the development of artificial moral agents in high-stakes domains, and whether these plural judgments can be reconciled within a coherent account of value alignment.

Benjamin Minhao Chen, Xinyu Xie

The University of Hong Kong, Hong Kong, China

Human Preference Evaluation AI Alignment Moral Reasoning

Ask PDF

Apr 24, 2026cs.CL

Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement

Evaluating LLM-generated business ideas is often harder to scale than generating them. Unlike standard NLP benchmarks, business idea evaluation relies on multi-dimensional criteria such as feasibility, novelty, differentiation, user need, and market size, and expert judgments often disagree. This paper studies a methodological question raised by such disagreement: should an automatic judge approximate an aggregate consensus, or model evaluators individually? We introduce PBIG-DATA, a dataset of approximately 3,000 individual scores across 300 patent-grounded product ideas, provided by domain experts on six business-oriented dimensions: specificity, technical validity, innovativeness, competitive advantage, need validity, and market size. Analyses show substantial expert disagreement on fine-grained ordinal scores, while agreement is higher under coarse selection, suggesting structured heterogeneity rather than random noise. We then compare three judge configurations: a rubric-only zero-shot judge, an aggregate judge conditioned on mixed evaluator histories, and a personalized judge conditioned on the target evaluator's scoring history. Across dimensions and model sizes, personalized judges align more closely with the corresponding evaluator than aggregate judges, and evaluator agreement correlates with similarity of judge-generated reasoning only under personalized conditioning. These results indicate that pooled labels can be a fragile target in pluralistic evaluation settings and motivate evaluator-conditioned judge designs for business idea assessment.

Wataru Hirota, Tomoki Taniguchi, Tomoko Ohkuma +6

1Stockmark Inc · 2Asahi Kasei Corporation · National Institute of Informatics +1

Human Preference Evaluation Annotator Disagreement LLM-as-a-Judge

Ask PDF

Apr 23, 2026cs.CL

Preferences of a Voice-First Nation: Large-Scale Pairwise Evaluation and Preference Analysis for TTS in Indian Languages

Crowdsourced pairwise evaluation has emerged as a scalable approach for assessing foundation models. However, applying it to Text to Speech(TTS) introduces high variance due to linguistic diversity and multidimensional nature of speech perception. We present a controlled multidimensional pairwise evaluation framework for multilingual TTS that combines linguistic control with perceptually grounded annotation. Using 5K+ native and code-mixed sentences across 10 Indic languages, we evaluate 7 state-of-the-art TTS systems and collect over 120K pairwise comparisons from over 1900 native raters. In addition to overall preference, raters provide judgments across 6 perceptual dimensions: intelligibility, expressiveness, voice quality, liveliness, noise, and hallucinations. Using Bradley-Terry modeling, we construct a multilingual leaderboard, interpret human preference using SHAP analysis and analyze leaderboard reliability alongside model strengths and trade-offs across perceptual dimensions.

Srija Anand, Ashwin Sankar, Ishvinder Sethi +10

Indian Institute of Technology Madras, India · AI4Bharat, India · Josh Talks, India

Pairwise Preference Learning Human Preference Evaluation Pairwise Comparison TTS Synthesis Speech Generation Evaluation Pairwise Preference Evaluation+4

Ask PDF

Apr 14, 2026cs.AI

Rater State Bias in RLHF Preference Data: An Audit Framework

We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but they may also reflect the rater's state during annotation. Under sustained stressful or distressing conditions, raters' preferences may shift over time, so that preference data encode rater state alongside judgments about response quality. We argue that, if present, such shifts would differ from ordinary disagreement or random label noise. They would be state dependent, could be shared across annotators under similar conditions, and would not necessarily cancel during aggregation, reward modeling, and policy optimization. We propose rater state shift as a plausible and testable source of structured bias in RLHF preference data. This paper develops a hypothesis and an audit framework for studying this source of bias. We define rater state shift, rater state confound, and correlated rater state bias. We also propose survival level emotional authenticity as a candidate output signature, defined by lexical, pragmatic, discourse, and safety features whose reliability and validity remain to be demonstrated. We show that systematic rater state bias can survive aggregation and may enter the learned reward signal. We state five testable predictions, together with effect size thresholds for an initial audit, and note which require proprietary data. Finally, we present an audit protocol and pilot study plan that can be applied to publicly available instruction tuned models. We do not infer the training history of any specific deployed model.

Elena Kopteva, Vitaliy Hlynianyi-Zhuk

The Grainger College of Engineering, Department of Physics & Illinois Center for Advanced Studies of the Universe, University of Illinois Urbana-Champaign, Urbana, Illinois 61801, USA · Faculty of Applied Mathematics, Oles Honchar Dnipro National University, Dnipro, 49045, Ukraine · Department of Clinical Psychology, Kyiv Institute of Modern Psychology and Psychotherapy, Kyiv, 01133, Ukraine

Human Preference Evaluation Human-in-the-Loop Annotation Language Model Auditing RL from Human Feedback

Ask PDF

Mar 30, 2026cs.RO

Why That Robot? A Qualitative Analysis of Justification Strategies for Robot Color Selection Across Occupational Contexts

As robots increasingly enter the workforce, human-robot interaction (HRI) must address how implicit social biases influence user preferences. This paper investigates how users rationalize their selections of robots varying in skin tone and anthropomorphic features across different occupations. By qualitatively analyzing 4,146 open-ended justifications from 1,038 participants, we map the reasoning frameworks driving robot color selection across four professional contexts. We developed and validated a comprehensive, multidimensional coding scheme via human--AI consensus (

κ= 0.73

). Our results demonstrate that while utilitarian \textit{Functionalism} is the dominant justification strategy (52%), participants systematically adapted these practical rationales that align with existing racial and occupational stereotypes. Furthermore, we reveal that bias frequently operates beneath conscious rationalization: exposure to racial stereotype primes significantly shifted participants' color choices, yet their spoken justifications remained masked by standard affective or task-related reasoning. We also found that demographic backgrounds significantly shape justification strategies, and that robot shape strongly modulates color interpretation. Specifically, as robots become highly anthropomorphic, users increasingly retreat from functional reasoning toward \textit{Machine-Centric} de-racialization. Through these empirical results, we provide design implications to help reduce the perpetuation of societal biases in future workforce robots.

Jiangen He, Wanqi Zhang, Jessica K. Barfield

The University of Tennessee, Knoxville, Tennessee, USA · University of Kentucky, Lexington, Kentucky, USA

Human Preference Evaluation Human-Robot Interaction

Ask PDF

Mar 17, 2026cs.CL

Mediocrity is the key for LLM as a Judge Anchor Selection

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

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

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

LLM-as-a-Judge Pairwise Preference Evaluation Human Preference Evaluation

Ask PDF

Feb 11, 2026cs.CL

Evaluating Alignment of Behavioral Dispositions in LLMs

As people turn to LLMs for social advice, understanding their behavior in such contexts becomes essential. In this work, we focus on behavioral dispositions: the underlying tendencies that shape responses in social contexts. We introduce STAR, a framework for studying how closely the dispositions expressed by LLMs align with those of humans. STAR builds on established psychological questionnaires, adapting their items into realistic advice-seeking scenarios, as self-report may not transfer to actual advisory behavior. Using STAR, we construct a dataset of 23k scenarios, each validated by 3 raters and annotated with preferences from 10 participants. Across 25 LLMs, we find that (1) when human consensus is high, frontier models can fail to reflect it in 15-20% of cases, and smaller models fail at substantially higher rates; (2) when humans disagree, LLM recommendations are substantially less diverse than human choices, both within individual models and even across models from different providers, potentially narrowing the range of options users are guided toward; (3) LLMs' self-reported values are poor predictors of their recommendations. To support future research we make our dataset and code publicly available.

Amir Taubenfeld, Zorik Gekhman, Lior Nezry +8

Google Research · Hebrew University · University of Cambridge

Human Preference Evaluation LLM Alignment AI Alignment LLM Decision-Making

Ask PDF

Aug 11, 2025cs.CL

Expert Preference-based Evaluation of Automated Related Work Generation

Expert domain writing, such as scientific writing, typically demands extensive domain knowledge. Although large language models (LLMs) show promising potential in this task, evaluating the quality of automatically generated scientific writing is a crucial open issue, as it requires knowledge of domain-specific criteria and the ability to discern expert preferences. Conventional automatic evaluation metrics and LLM-as-a-judge systems, primarily designed for mainstream NLP tasks, are insufficient to grasp expert preferences and domain-specific quality standards. To address this gap and support realistic human-AI collaborative writing, we focus on related work generation, one of the most challenging scientific tasks, as an exemplar. We propose GREP, a multi-turn evaluation framework that integrates classical related work evaluation criteria with expert-specific preferences. GREP decomposes the evaluation into smaller fine-grained dimensions. This localized evaluation is further augmented with contrastive examples to provide detailed contextual guidance for the evaluation dimensions. Empirical investigation reveals that GREP is able to assess the quality of related work sections in a much more robust manner compared to standard LLM judges, reflects natural scenarios of scientific writing, and bears a strong correlation with the assessment of human experts. We also observe that generations from state-of-the-art LLMs struggle to satisfy validation constraints of a suitable related work section.

Furkan Şahinuç, Subhabrata Dutta, Iryna Gurevych

Ubiquitous Knowledge Processing Lab (UKP Lab) · Department of Computer Science and Hessian Center for AI (hessian.AI) · Technical University of Darmstadt +1

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

Ask PDF

Aug 3, 2025cs.HC

Harmonious Color Pairings: Insights from Human Preference and Natural Hue Statistics

While color harmony has long been studied in art and design, a clear consensus remains elusive, as most models are grounded in qualitative insights or limited datasets. In this work, we present a quantitative, data-driven study of color pairing preferences using controlled hue-based palettes in the HSL color space. Participants evaluated combinations of thirteen distinct hues, enabling us to construct a preference matrix and define a combinability index for each color. Our results reveal that preferences are highly hue dependent, thereby challenging classical color harmony theories. Yet, when averaged over hues, statistically meaningful patterns of aesthetic preference emerge, with certain hue separations perceived as more harmonious. Strikingly, these patterns align with hue distributions found in natural landscapes, pointing to a statistical correspondence between human color preferences and the structure of color in nature. Finally, we analyze our color-pairing score matrix through principal component analysis, which uncovers two complementary hue groups whose interplay underlies the global structure of color-pairing preferences. Together, these findings offer a quantitative framework for studying color harmony and its potential perceptual and ecological underpinnings.

Ortensia Forni, Alexandre Darmon, Michael Benzaquen

Econophysics Lab, Institut Louis Bachelier, 28 Pl. de la Bourse, Palais Brongniart, 75002 Paris, France · LadHyX UMR CNRS 7646, École Polytechnique, Institut Polytechnique de Paris, 91128 Palaiseau Cedex, France · Art in Research, 33 rue Censier, 75005 Paris, France +1

Human Preference Evaluation Human Preference Modeling

Ask PDF

Momentum

Related topics

Latest papers 41