Preference Learning

Follow this topic Ask about this topic

Preference learning studies how to infer what people value from pairwise comparisons, rankings, choices, behavior, and other feedback. Common approaches include Bradley–Terry and Gaussian-process models, active query selection, inverse reinforcement learning, and reward-model training with methods such as direct preference optimization. These techniques support personalized recommendations, robot and agent behavior, and multi-objective decisions where no single fixed reward captures every user’s priorities. A central challenge is that preferences can be noisy, context-dependent, and heterogeneous, so researchers must balance efficient data collection and accurate prediction against robust generalization and faithful representation of differing values.

Latest papers

149 papers19 papers in the last four weeks, up 36% on the four weeks before. 0.1% of all new papers.

Jun 12, 2026

S $^2$ COPE: Self-Supervised Concept Discovery via Preference Learning

Current representation learning paradigms force a fundamental compromise: self-supervised methods scale to massive datasets but yield opaque features, whereas interpretable models remain bottlenecked by the need for dense human annotation. We introduce Self-Supervised Concept discOvery via Preference lEarning (\model), a label-free framework that resolves this dilemma. Instead of treating Vision-Large-Language Models (VLLMs) as static feature extractors, \model leverages them as active participants in a self-supervised preference optimization loop. By autonomously hypothesizing, validating, and reinforcing candidate visual attributes directly from raw imagery, our framework discovers novel, structured concepts without a single label. Extensive experiments across natural, medical, and physics domains demonstrate that \model successfully extracts domain-specific concepts where standard VLLMs often fail to generate. By amortizing concept discovery directly into the VLLM backbone through our self-supervised preference objective -- rather than relying on static generation and disjoint filtering -- we achieve up to a 24-point absolute improvement in downstream top-1 classification accuracy on unseen data. Our work suggest that interpretability can emerge through a model's autonomous interaction with incidental visual structures, without any human supervision.

Shilong Xiang, Zirui Zhang, Chengzhi Mao

Rutgers University

Vision-Language Models Self-Supervised Learning VLM Interpretability Preference Learning Unsupervised Visual Concept Discovery

Jun 10, 2026

PAWS: Preference Learning with Advantage-Weighted Segments

Preference-based reinforcement learning (PbRL) learns policies from human trajectory-level comparisons, avoiding explicit reward design and expert demonstrations. Existing methods typically train utility functions on trajectory or segment-level preferences while relying on per-step utility estimates during policy optimization. This training and inference mismatch induces a distribution shift that severely degrades temporal credit assignment and limits policy learning. We analyze this issue and propose PAWS, a segment-based preference learning method that performs policy updates directly using segment-level advantage functions. By aligning utility training with policy optimization, PAWS preserves trajectory-level preference information and avoids unreliable per-step learning signals. Experiments on simulated robotic manipulation and locomotion tasks demonstrate that PAWS consistently outperforms existing PbRL approaches, highlighting the importance of distribution-consistent preference learning.

Aleksandar Taranovic, Onur Celik, Niklas Freymuth +6

Autonomous Learning Robots, Karlsruhe Institute of Technology, Karlsruhe, Germany · Bosch Center for Artificial Intelligence, Renningen, Germany · Institute for Material Handling and Logistics (IFL), Karlsruhe Institute of Technology, Karlsruhe, Germany

Credit Assignment in RL Robotic RL Policy Learning Preference Learning Preference-Based RL

Jun 8, 2026

Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short

Reinforcement learning with verifiable rewards (RLVR) has become a leading paradigm for improving the reasoning ability of large language models through outcome-based supervision. However, verifiable rewards frequently become uninformative at the group level: when all sampled traces of a given prompt receive identical rewards, group-relative advantage estimation provides no gradient signal, even though the traces may differ substantially in reasoning quality. We propose Reasoning Arena, an adaptive training framework that routes such non-diverse reward groups to a judge system instead of discarding them. Beyond examining the final answer, Reasoning Arena constructs trace tournaments, where reasoning traces are compared head-to-head to expose finer-grained preferences within the group, converting reasoning quality into rich relative reward signals. To make reward estimation efficient, rather than exhaustively comparing every pair, each new trace is evaluated against a small, dynamically updated pool of previously generated traces as anchors to efficiently establish a relative ranking. We then fit a Bradley-Terry model on the incomplete comparison graph, enabling scalable RL integration without quadratic pairwise comparisons. Empirical results demonstrate that Reasoning Arena consistently outperforms the RLVR baseline by 7.6% on average in competition mathematics and coding benchmarks. By converting otherwise wasted zero-advantage samples into useful gradient updates, our method accelerates training by 27% to 41%, saving nearly 50% of generation compute, and substantially improves overall reasoning performance.

Han Zhou, Adam X. Yang, Laurence Aitchison +2

University of Cambridge · 2Mistral AI · *Work done as an AI Scientist Intern at Mistral AI.

Pairwise Preference Learning Reward Modeling RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards Bradley–Terry Model Reward Design for RL+1

Jun 8, 2026

DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity

Reward models trained from pairwise preferences often exploit superficial shortcut cues rather than learning true response quality. We propose DynaCF, a dynamic reweighting framework for mitigating shortcut learning in reward model training. Unlike static shortcut heuristics, DynaCF measures shortcut sensitivity online during optimization by applying semantics-preserving counterfactual perturbations and tracking the resulting margin shifts and preference flips under the current model. Samples with higher shortcut sensitivity are dynamically downweighted in the Bradley-Terry objective, encouraging the model to rely less on superficial patterns and more on task-relevant preference signals. Extensive experiments show that DynaCF consistently improves robustness in preference modeling.

Fengyuan Liu, Yongliang Miao, Zirui He +3

The Chinese University of Hong Kong, Shenzhen · New Jersey Institute of Technology · Institute of Computing Technology, CAS

Pairwise Preference Learning Reward Modeling Pairwise Preference Evaluation Shortcut Learning Preference Learning Preference Modeling

Jun 7, 2026

Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries

Personalized decision-making in multi-objective bandits requires learning user-specific trade-offs among competing objectives. Since arm utility depends on both unknown rewards and unknown preferences, existing methods infer preferences only from utility feedback, entangling preference learning with reward exploration. In practice, however, users often reveal their priorities through proactive conversational queries (e.g., "cheap and clean hotel"), yet this structured signal is not leveraged. We formalize a proactive query-based framework in which user queries provide structured preference signals. Modeling these signals via a Plackett-Luce subset choice model, we show that query-only learning is insufficient due to a fundamental shift-invariance barrier. To resolve this, we introduce MO-PQUCB, a hybrid algorithm that integrates query-based preference anchoring with bandit feedback through shift-invariant regularization and dual-exploration UCB. We prove that proactive queries accelerate preference estimation and yield improved regret scaling over prior preference-aware MO-MAB methods. Under corrupted queries, we further characterize statistical limits and design a robust estimator achieving near-optimal performance when the corruption is sparse. Experiments validate both theoretical and practical gains.

Linfeng Cao, Ming Shi, Ness B. Shroff

Department of Computer Science and Engineering, The Ohio State University · Department of Electrical Engineering, University at Buffalo · Department of Electrical and Computer Engineering, The Ohio State University

Multi-Armed Bandits Combinatorial Multi-Armed Bandits User Preference Modeling Preference Learning Preference Elicitation Preference Modeling

Jun 4, 2026

Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents

As Large Language Model (LLM) capabilities advance, locally deployed personal agents relying on API-based remote models and external skills have emerged as a novel paradigm. With the rapid expansion of available skills, enabling personal agents to learn and adapt to implicit user preferences becomes a critical challenge. However, local deployment constraints preclude complex centralized selection algorithms, creating an urgent need for a lightweight local preference harness. This paper explores the implementation of such a harness through a novel architecture that strictly decouples statistical preference learning from semantic intent parsing. Specifically, we leverage localized statistical results to influence and modulate the selection decisions of the remote LLM. Extensive evaluations demonstrate that our decoupled approach achieves the lowest cumulative regret and highest test accuracy, significantly outperforming traditional memory-augmented agents.

Zeyu Gan, Huayi Tang, Yong Liu

Gaoling School of Artificial Intelligence Renmin University of China Beijing, China

LLM Agents User Preference Modeling Preference Learning

Jun 3, 2026

Rethinking Sales Lead Scoring with LLM-based Hierarchical Preference Ranking

Sales lead conversion in high-stakes domains (e.g., automotive, real estate) differs fundamentally from e-commerce recommendation due to prolonged decision cycles and multi-stage funnels. Traditional lead scoring methods rule-based scorecards, machine learning, or pointwise CTR models face severe challenges: sparse supervision, a semantic gap in unstructured CRM logs, and inability to capture relative lead priority. While Large Language Models(LLMs) offer superior semantic understanding of customer interactions, general-purpose LLMs are ill-suited for lead ranking: they generate text rather than comparable scores, and lack alignment with the hierarchical priorities of sales funnels. We introduce an LLM-based discriminative framework for sales lead scoring, which supports joint modeling of structured CRM features and unstructured customer interactions. On top of this framework, we propose HPRO (Hierarchical Preference Ranking Optimization), which augments sales lead scoring with a hierarchical preference ranking objective. HPRO employs a margin-aware Bradley-Terry formulation to transform sparse binary labels into dense, funnel-aware preference pairs, enabling lead scoring to leverage both pointwise and pairwise supervision. Experiments on large-scale data from a leading NEV brand demonstrate state-of-the-art classification (AUC 0.8161) and ranking performance (+39.7% precision among top-ranked leads). A 132-day online A/B test validates 9.5% sales volume uplift, confirming real-world commercial impact.

Chenyu Zhang, Yiwen Liu, Yin Sun +4

Intelligent Business Team, Li Auto Inc.

Learning to Rank LLM Reranking Bradley–Terry Model Preference Learning

May 30, 2026

Enhancing LLM Metacognition via Cognitive Pairwise Training

Reinforcement learning with verifiable rewards (RLVR) has become central to LLM reasoning, but its outcome-level rewards can make models more willing to give confident answers when evidence or reasoning is unreliable. Existing SFT or RL methods mainly teach LLMs to refuse or express uncertainty at the response level, which can overfit abstention behavior rather than improve reasoning reliability. To address this limitation, we propose Cognitive Pairwise Training (CPT), a cognitive mid-training alignment stage that turns pairwise comparisons over reasoning traces into a reusable alignment signal. By learning to distinguish trustworthy from flawed reasoning, CPT encourages the model to internalize a reasoning-quality discrimination boundary rather than memorize surface refusal patterns. Across five model scales and three model families, CPT improves the reasoning--metacognition trade-off. At 14B, CPT+RL outperforms the standard SFT+RL pipeline by +2.2 math-average points and +5.2 abstention-F1 points. Further analyses show that CPT improves trace quality and exhibits strong robustness and scalability across evaluation and training settings. Code and models are released at https://github.com/Tsinghua-dhy/CPT.

Weitao Li, Hao Zhou, Xuanyu Lei +11

Dept. of Comp. Sci. & Tech., Institute for AI, Tsinghua University, Beijing, China · Institute for AI Industry Research (AIR), Tsinghua University, Beijing, China · WeChat AI, Tencent Inc., China

Pairwise Preference Learning RL for Language Model Reasoning LLM Post-Training Preference Learning Metacognition in Language Models

May 30, 2026

Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning

Agent skills are callable procedural modules that provide reusable knowledge and execution policies for complex agentic tasks. However, existing methods mainly focus on selecting relevant skills or improving the skills themselves, while overlooking whether a relevant skill should actually be invoked at the current decision point. Unhelpful invocations may introduce irrelevant context and disrupt an otherwise correct execution process. To address this issue, we propose SelSkill, a dual-granularity preference-learning framework for selective skill invocation. SelSkill formulates skill use as a skill-or-skip decision, uses predictive uncertainty to prioritize candidate decision points, and constructs controlled invoke-skip preference pairs from shared trajectory prefixes. It further combines episode-level outcome preferences with step-level invocation preferences to capture both overall trajectory quality and the local effectiveness of skill invocation. On ALFWorld with Qwen3-8B, SelSkill improves task success by 10.9 points over the skill-enabled baseline and 7.8 over No-Skill, with 29.1-point higher execution precision. On BFCL, task success and execution precision improve by 5.7 and 29.5 points, respectively. Zero-shot results on Tau-bench and PopQA suggest partial transfer to unseen domains and skills.

Chishui Chen, Jiaye Lin, Te Sun +6

Meituan · Shanghai Jiao Tong University · Nanjing University +2

LLM Agent Skill Learning Tool-Using Agents Preference Learning

May 29, 2026

The Representation-Rationalizability Tradeoff in Reward Learning

In RLHF, each training example contains a prompt

x

and two candidate responses

y,y'

, and annotators provide pairwise preferences between these responses. The learning problem is to convert these heterogeneous pairwise judgments into a single scalar reward

r(x,y)

that measures response quality for each prompt. Classical social choice implies an impossibility because heterogeneous annotator samples can induce pooled preferences with Condorcet cycles, so no scalar reward can evaluate all compared response pairs consistently. A growing literature analyzes RLHF as a social-choice problem, but usually assumes a fixed finite set of alternatives, i.e., a pre-enumerated finite set of candidate responses for each prompt. Modern pipelines instead score responses through a learned representation

φ(x,y)

before a scalar head, so

φ

determines which responses are treated as distinguishable alternatives and which comparisons are visible to the reward model. Once this embedding is part of the problem, the impossibility results from social choice theory become a tradeoff. We show that the excess cross-entropy loss of any reward built on

φ

decomposes exactly into a representational term, which a richer

φ

shrinks, and an aggregation term, which a richer

φ

enlarges by exposing more comparisons that no scalar can rank consistently. The same results extend to direct preference optimization (DPO), and jointly training the embedding and the reward cannot guarantee to recover the sweet spot of this tradeoff. Experiments on synthetic data and real preference datasets corroborate our results.

Jing Dong, Yaoliang Yu, Pascal Pourpart

Vector Institute · University of Waterloo & Vector Institute

Pairwise Preference Learning Reward Modeling Reinforcement Learning Social Choice Theory Pairwise Preference Evaluation Direct Preference Optimization+3

May 29, 2026

Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences

Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce a monolithic reward model, inevitably averaging out inherently conflicting user preferences (e.g., helpfulness vs. harmlessness). While Variational Preference Learning (VPL) offers a pathway to personalization, adapting it to decentralized settings presents a fundamental challenge: posterior collapse driven by severe local data scarcity and heterogeneity. In this paper, we propose Federated Variational Preference Alignment with Gumbel-Softmax Prior (FedVPA-GP), a framework designed to disentangle diverse preferences without compromising privacy. To stabilize variational inference, we introduce a Federated Mixture Prior that enables clients to leverage the aggregate population distribution as a dynamic prior. Furthermore, we incorporate an Orthogonal Loss that explicitly enforces the separation of preference prototypes in the latent space. Experiments on the HH-RLHF dataset demonstrate that FedVPA-GP significantly outperforms monolithic baselines, successfully disentangling conflicting user intents and enabling dynamic preference switching.

Jabin Koo, Hoyoung Kim, Minwoo Jang +1

Department of CSE, POSTECH, Pohang, Republic of Korea · National AI Research Lab, Seoul, Republic of Korea · Graduate School of AI, POSTECH, Pohang, Republic of Korea

LLM Alignment Preference Alignment User Preference Modeling Preference Learning Federated Learning

May 28, 2026

Reward Learning from Best-of- $N$ Preference Data: Targets, Tradeoffs, and Design Principles

Best-of-

N

sampling is widely used to construct pairwise preference data:

N

candidates are drawn from a base distribution, and the best is paired with a rejected response. Despite its widespread use, what Bradley--Terry (BT) reward learning extracts from such data, and how to choose

N

and the base distribution, remain unclear. We specialize a recent analysis of preference data via its induced conditional distribution to Best-of-

N

. For independent-reference variants, we derive closed-form reward targets as explicit functions of

N

and the base distribution, and show that they preserve the latent reward ranking. For the practical Best-vs-Random and Best-vs-Worst variants, chosen and rejected responses are coupled through the same candidate set, so exact BT representability generally fails; nevertheless, bounded-class minimizers approach the reference targets as

N

grows. Although margin and connectivity are known to govern sample efficiency in pairwise preference learning, Best-of-

N

couples them through

N

in opposing directions: larger

N

widens pairwise margins but reduces connectivity. This trade-off yields two design principles: use larger

N

when preference labels are the bottleneck, smaller

N

when generation is the bottleneck; and shape the base distribution to place mass between the responses whose comparison matters most at test time. Experiments on synthetic and real preference data support the predicted dependence on sample size and base-distribution shape.

Rattana Pukdee, Maria-Florina Balcan, Pradeep Ravikumar

Machine Learning Department Carnegie Mellon University

Pairwise Preference Learning Reward Modeling Pairwise Comparison Pairwise Preference Evaluation Preference Learning Best-of-N Sampling+3

May 28, 2026

Calibrated Preference Learning: The Case of Label Ranking

Calibration, the alignment of predicted probabilities with true outcome frequencies, is essential for reliable decision-making. While extensively studied for classification and regression, calibration has not been formally addressed for probabilistic label ranking, where the goal is to predict a distribution over orderings of a label set. Naively treating rankings as classes ignores their structure and fails to capture important modalities such as pairwise and top-k predictions. We formalize calibration for label ranking and develop a hierarchy of notions covering full rankings, sub-rankings, and top-k rankings. We prove that full-rank calibration implies the others but not conversely, and sub-ranking and top-k calibration are incomparable. Empirically, we find popular label ranking models are often poorly calibrated, with substantial differences between sub-ranking and top-k metrics. Applying our framework to RLHF reward models, we find that calibration correlates strongly but not perfectly with benchmark accuracy, suggesting it captures a meaningful quality dimension beyond top-1 accuracy. These findings motivate future work on understanding the downstream effects of miscalibration and developing methods to correct it.

Santo M. A. R. Thies, Viktor Bengs, Timo Kaufmann +2

Data Science and its Applications, Deutsches Forschungsinstitut für Künstliche Intelligenz (DFKI), Kaiserslautern, Germany · Munich Center for Machine Learning, Munich (MCML), Germany · Ludwig Maximilian Universität München, Munich, Germany

Probability Calibration Learning to Rank Preference Learning

May 28, 2026

From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals

As candidate generation and high-throughput experimentation advance, the primary bottleneck in materials discovery is shifting from property prediction to making reliable evaluations among massive candidate sets. We propose a Knowledge-Augmented Preference Signals Framework, MaterEval, that automatically produces, for the same candidate, two evaluations: an informed judgment that follows expert rules and provides supporting evidence, and a rule-removed blind guess. By pairing the two evaluations as preference data, we guide general-purpose large language models (LLMs), originally lacking materials-specific criteria, from intuitive judgment toward reliable evaluation supported by explicit evidence. To balance throughput, cost, and reliability, we further introduce a fast-slow reasoning scheme that decouples large-scale rapid screening from in-depth review on a small subset. Using high-entropy alloy (HEA) assessment as a case study, we show that, without external retrieval and relying solely on internalized capabilities, small open-source LLMs achieve substantial gains in accuracy, conclusion consistency, and evidence discrimination, approaching the performance of rule-based closed-source LLMs. These results demonstrate that expert rules can be systematically transformed into learnable preference signals, enabling a low-cost and deployable evaluation module for autonomous materials discovery loops.

Yeyong Yu, Wenya Hu, Xing Wu +1

School of Computer Engineering & Science, Shanghai University, Shanghai, 200444, China. · Center of Materials Informatics and Data Science, Materials Genome2026 Institute, Shanghai University, Shanghai, 200444, China. · Key Laboratory of Silicate Cultural Relics Conservation (Shanghai University), Ministry of Education, China. +1

LLM Evaluation Pairwise Preference Evaluation Materials Science Large Language Model-Guided Scientific Discovery Preference Learning

May 27, 2026

Evolving to the Aesthetics of a Vision-Language Model

Evolutionary systems have demonstrated remarkable results in creative domains, with recent applications in generative typography, design, and music. However, an open problem remains in designing fitness functions that effectively capture the desired aesthetics of abstract outputs. In this work, we explore two methods for evaluating the aesthetics of a population using Vision-Language Models (VLMs). The first method uses CLIP-IQA to predict an aesthetic score for each design. The second method instead pits candidates against each other, with winners determined by a VLM using a custom prompt specified by the user. The outcomes of these pairwise comparisons are then used to estimate a population ranking via the Glicko rating system. We present these methods in the context of a case study using a custom generative system and compare the resulting rankings with an artist's aesthetic ranking and those produced by other aesthetic evaluation techniques. Additionally, we document the artist's experience using these approaches to evolve designs, critically analysing the strengths and weaknesses of both methods.

Stephen James Krol, Jon McCormack

SensiLab, Monash University Melbourne, Australia

VLM Evaluation Preference Learning

May 26, 2026

Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics

Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting their effectiveness as signals for shaping model behaviour.While individual factuality metrics are unreliable, their combination can more effectively capture diverse factual errors. We leverage this insight to introduce an automated training pipeline that improves factual consistency in summaries by aggregating scores from different weak metrics. Our approach avoids the need for complex reward shaping by mapping scores to preferences and filtering out cases with high disagreement between metrics. For each source document, we generate lexically similar summary pairs by varying decoding strategies, enabling the model to learn from factual differences caused by subtle lexical differences. This approach constructs a high-quality preference dataset using only source documents.Experiments demonstrate consistent factuality gains across models, ranging from early encoder-decoder architectures to modern large language models, with smaller models reaching comparable factuality to larger ones.

Yuxuan Ye, Raul Santos-Rodriguez, Edwin Simpson

Intelligent System Laboratory University of Bristol United Kingdom

Factual Consistency Evaluation Text Summarization Preference Learning

May 25, 2026

CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations

Prior work establishes that controlled contrastiveness between self-generated responses from large language models, set via reward scores, improves downstream preference tuning in English. We extend this method to multiple languages and evaluate two models across a total of 14 high and low-resource languages on a diverse set of tasks. Our central finding is that cross-lingual contrastive preference tuning on self-generations (CroCo) transfers without language-specific preference annotation. A reward model trained on English preferences (atop a multilingual base) produces useful within-language rankings across most languages, and pairing in either a monolingual or multilingual setting improves over each model on the majority of setups while preventing the catastrophic forgetting of supervised fine-tuning. We observe that the gains require on-policy data. Off-policy responses reduce the benefit and online preference optimization fails to improve over the offline variant. Specifically, on structured tasks, our method matches or exceeds the base in 6/7 languages for EuroLLM-9B and 4/7 settings for Aya-3B. On open-ended generation, evaluated by two judges, both tuned models win 28/30 times against their respective base across 15 evaluated languages (high and low-resource). Overall, we show promising directions for multilingual preference tuning using self-generations.

Mike Zhang, Ali Basirat, Desmond Elliott

Department of Computer Science (DIKU), University of Copenhagen · Centre for Language Technology (CST), University of Copenhagen · Pioneer Centre for Artificial Intelligence

Multilingual Language Models LLM Alignment Preference Learning Cross-Lingual Transfer

May 25, 2026

Active Query Synthesis for Preference Learning

Efficient learning of user preferences is crucial for many modern decision making systems but typically requires costly labeled data. Active learning reduces this cost, yet standard methods are computationally expensive due to pool-based evaluation. Further, most methods assume all query feedback is equally reliable, ignoring that pairwise queries between nearly identical or entirely dissimilar items yield ambiguous, low-confidence responses. To address the issue of feedback reliability, we introduce a novel confidence aware response model that explicitly accounts for these ambiguous comparisons. To overcome the computational bottleneck of pool-based evaluation, we propose an active query synthesis framework, Info-Synth that generates optimal queries by maximizing a mutual information-based objective within a continuous space. Moreover, we propose two strategies, Pair M-dist and Pair Opt-dist, that extend Info-Synth to select effective queries even when restricted to finite query pools. We demonstrate our framework's versatility and performance across synthetic preference learning, constrained text summary datasets, and subjective, continuous-space controller gain tuning for a simulated mobile robot.

Namrata Nadagouda, Nauman Ahad, Maegan Tucker +1

Georgia Institute of Technology · Gauss Labs

Pairwise Preference Learning Active Learning Preference Learning Preference Elicitation Active Preference Learning

May 25, 2026

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift

Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore, we study W2S preference learning under zero-shot distribution shift and find that strong students trained on weak preference labels can appear successful in-distribution while failing to transfer across preference datasets. We provide evidence for a representational failure mode in which weak-supervised fine-tuning can pull the strong model toward source-domain features instead of maintaining broadly transferable preference representations. To mitigate this, we propose Representation Anchoring (Anchor), a simple yet effective regularizer that constrains excessive drift from the pretrained strong model's representation space during fine-tuning, while still allowing task-relevant adaptation. Across preference domains, datasets, and model families, Anchor consistently improves out-of-distribution transfer while maintaining competitive in-distribution performance. Together, our evaluation protocol, transfer-aware metrics, and method expose hidden brittleness in current W2S reward modeling and provide a practical path toward more robust preference transfer.

Khoi Le, Tri Cao, Phong Nguyen +5

National University of Singapore · VinUniversity · Nanyang Technological University

Pairwise Preference Learning Reward Modeling Representation Learning OOD Generalization Weak-to-Strong Generalization Preference Learning

May 22, 2026

Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models

Individual fairness, the notion that "similar individuals should be treated similarly," provides a strong and flexible fairness guarantee for algorithmic decision makers. However, a barrier to implementing individual fairness in practice is the difficulty of learning the similarity metric over individuals. In this work, we present an algorithm for learning a Mahalanobis similarity metric from triplet queries of the form "is individual

i

more similar to individual

j

or

k

?" We work in the standard Bradley-Terry model for pairwise comparisons. Our algorithm consists of a spectral initialization step followed by gradient descent. We provide extensive theoretical guarantees on our algorithm, showing that it converges quickly to the ground truth metric despite the non-convexity of the loss in our model. Because our focus is on fairness, we also show that individual fairness with respect to an estimated metric is sufficient to achieve similar fairness with respect to the true metric. We also discuss potential applications of our work to AI model tuning. Finally, we present experimental results that demonstrate the convergence of our algorithm and the fairness performance of downstream fair predictors trained on our estimated metric.

Conlan Olson, Linjun Zhang, Zhun Deng +1

Columbia University · Rutgers University · UNC Chapel Hill +1

Mahalanobis Distance Algorithmic Fairness Metric Learning Bradley–Terry Model Preference Learning

May 20, 2026

Beyond Scalar Objectives: Expert-Feedback-Driven Autonomous Experimentation for Scientific Discovery at the Nanoscale

Self-driving laboratories or autonomous experimentation are emerging as transformative platforms for accelerating scientific discovery. Bayesian optimization (BO) is among the most widely used machine learning frameworks for these purposes, but these BO-based frameworks rely on predefined scalar descriptors to guide experimentation. In many situations, the determination of an appropriate scalar descriptor can be challenging, and may fail to capture subtle yet scientifically important phenomena apparent to experts with interdisciplinary insight. To overcome this limitation, here we develop deep-kernel pairwise learning (DKPL), an approach for autonomous microscopy experiments which incorporates human expertise and interdisciplinary scientific knowledge into an active learning loop. Instead of relying on explicit scalar objectives, DKPL enables experts to directly evaluate which experimental output is more promising using interdisciplinary knowledge. DKPL then learns a latent utility function from these expert judgements to guide subsequent autonomous microscopy experiments. We demonstrate DKPL's performance in learning physically meaningful nanoscale structures while effectively prioritizing high-information measurement regions using an experimental model dataset with known ground truth. We further apply DKPL to analyze the character of ferroelectric domain walls, where we find DKPL capable of distinguishing between high and low characteristic domain-wall angles in bismuth ferrite, and able to discover both head-to-head and tail-to-tail domain-wall character in erbium manganite. This development establishes an approach to integrate expert knowledge into autonomous microscopy experiments and demonstrates a pathway toward expert-guided self-driving laboratories capable of addressing scientific problems beyond the limits of scalar-metrics-driven learning.

Ralph Bulanadi, Jefferey Baxter, Arpan Biswas +5

Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA · University of Tennessee-Oak Ridge Innovation Institute, University of Tennessee, Knoxville, TN 37996, USA · Department of Material Science and Engineering, School of Materials and Chemical Technology, Institute of Science Tokyo, Yokohama, 226-8502, Japan +3

Pairwise Preference Learning Deep Kernel Learning Active Learning Materials Science Kernel Methods Preference Learning+1

May 19, 2026

Preferences Order, Ratings Anchor: From Fused Expert Aesthetic Ground Truth to Self-Distillation

Pairwise preferences and pointwise ratings are the two dominant annotation protocols in image aesthetic assessment (IAA), yet existing benchmarks adopt only one, leaving their complementarity unmeasured under controlled conditions. We introduce PPaint, a matched dual-protocol benchmark in which 15 domain experts, 5 per category, annotate 150 Chinese paintings under both protocols across five aesthetic dimensions, collecting 45,900 pairwise expert judgments through a locally dense preference design alongside the matched ratings. The matched design reveals complementary strengths: preferences yield more consistent ordinal rankings, while ratings anchor the absolute score scale. Fusing both signals via two independent preference-to-score methods yields a fused expert ground truth on which the two constructions converge to nearly identical scores. The same preference-to-score principle extends to label-free VLM training. PSDistill converts VLM pairwise judgments into calibrated pseudo-scores via an Elo reference pool, and trains the same VLM with confidence-weighted ranking optimization to produce a single-pass aesthetic scorer. Trained on a single painting category, the distilled Qwen3-VL-8B improves mean SRCC from 0.504 to 0.709 across all three categories, outperforming all open-source baselines including the dedicated aesthetic model ArtiMuse and matching closed-source Gemini-3.1-Pro within 0.04 SRCC at single-pass inference cost, with cross-domain transfer further validated on APDDv2. We will release the full PPaint dataset and training code.

Yuanpei Zhao, Jie Lin, Chao Zhang +5

1Sichuan University · 2NetEase Fuxi AI Lab · †Work done during an internship at NetEase Fuxi AI Lab. +1

Pairwise Preference Learning Personalized Image Aesthetics Assessment Pairwise Comparison Pairwise Preference Evaluation VLM Distillation Pairwise Ranking+3

May 19, 2026

CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging

Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond functional correctness. While rubric-based LLM judges improve interpretability by decomposing evaluation into explicit criteria, most existing pipelines remain pointwise: they score each response independently and derive preferences by comparing aggregated scores. We show that this design is poorly matched to pairwise code preference prediction and can underperform a strong monolithic judge. We propose CriterAlign, a criterion-centric framework that adapts rubric-based judging to pairwise preference evaluation through direct criterion-level pairwise judgments, tie-driven criterion refinement, swap-consistency filtering, and final pairwise synthesis. We further introduce Human-Preference-Aligned Guidance (HPAG), synthesized offline from training examples by extracting recurring rationale gaps between human preferences and monolithic judge predictions, and injected into the criterion generator, criterion judge, and final judge. On BigCodeReward, CriterAlign improves a Qwen2.5-VL-32B monolithic judge from 60.4% to 66.3% accuracy, with ablations confirming the contributions of pairwise criterion design and HPAG.

Zhenyu Li, Aleksandar Cvejic, Zehui Chen +1

KAUST · USTC

Pairwise Preference Learning Human Preference Evaluation Pairwise Comparison LLM-as-a-Judge Pairwise Preference Evaluation Pairwise Ranking+4

May 19, 2026

DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs

Vision-Language-Action (VLA) policies increasingly rely on asynchronous inference to hide model latency behind ongoing robot motion. During inference, the robot continues executing its current action chunk while the next chunk is generated from the observation available at inference start. By the time the new chunk is executed, the robot or scene may have changed, so an action that fits the prediction-time state can be misaligned with the execution-time state. Training-time methods modify the policy input or supervised target based on the expected execution delay, but do not directly supervise how actions should change as the scene evolves between prediction and execution. Runtime repair methods improve chunk continuity or modify actions during deployment, but can still leave actions aligned with the prediction-time state rather than the execution-time state. Our key insight is that execution-time observations are unavailable when the online prediction is made but are available in recorded trajectories during offline training, making the prediction-execution mismatch observable during training. We propose DEFLECT, an offline post-training framework that turns this temporal contrast into preference supervision for a policy acting from stale inputs. Across Kinetix, LIBERO, and three real-robot tasks, DEFLECT improves delay robustness across the evaluated VLA policies and settings. At the longest supported delay, it improves success by 4.2 percentage points over VLASH on Kinetix and by 22.7 points over naive asynchronous execution with GR00T N1.7 on LIBERO.

Yixiang Zhu, Yonghao Chen, Jiaxiang Zou +2

The Hong Kong University of Science and Technology (Guangzhou) · One Robotics

Robotic Control Visuomotor Policy Learning Vision-Language-Action Models VLMs for Robotics Preference Learning

May 18, 2026

General Preference Reinforcement Learning

Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reasoning on math and code but depends on a programmatic verifier that cannot reach open-ended tasks, while preference optimization handles open-ended generation yet forgoes the continuous exploration that powers online RL. Closing this gap requires a verifier for open-ended quality, but a scalar reward model is the wrong shape for the job. Quality is multi-dimensional, and any scalar score is an incomplete proxy that lets online RL collapse onto whichever axis the score is most sensitive to. We turn instead to the General Preference Model (GPM), which embeds responses into

k

skew-symmetric subspaces and represents preference as a structured, intransitivity-aware comparison. Building on this, we propose General Preference Reinforcement Learning (GPRL), which carries the

k

-way structure through to the policy update. GPRL computes per-dimension group-relative advantages, normalizes each on its own scale so no axis can dominate, and aggregates them with context-dependent eigenvalues. The same structure powers a closed-loop drift monitor that detects single-axis exploitation and corrects it on the fly by reweighting dimensions and tightening the trust region. Starting from

\texttt{Llama-3-8B-Instruct}

, GPRL reaches a length-controlled win rate of

56.51\%

on AlpacaEval~2.0 while also outperforming SimPO and SPPO on Arena-Hard, MT-Bench, and WildBench by resisting reward hacking across extended training runs.

Muhammad Umer, Muhammad Ahmed Mohsin, Ahsan Bilal +5

Stanford University · The University of Oklahoma

Preference Modeling Multi-Objective Language Model Alignment RL Fine-Tuning Policy Learning Preference Learning Preference-Based RL

May 15, 2026

Learning What Evaluators Value: A Reliable Approach to Modeling Evaluator Preferences

In many applications, human and LLM evaluators use assessments of relevant criteria to create an overall evaluation for an item or individual. For example, in admissions, committees assess candidates on attributes such as test scores, GPA, and research experience to evaluate their overall fit for the program. Another example arises in medical care where clinicians use patient reports of symptoms to consider preliminary diagnoses and assess risks. Each setting involves mapping multiple criteria to an overall evaluation -- a process that reflects the evaluator's underlying preferences. We focus on the fundamental question of learning these preferences. Many applications of this problem make specific modeling assumptions on evaluator preferences that may be substantially violated in the real world. We make the minimal assumption that the preference function is coordinate-wise non-decreasing, which is reasonable in a large number of evaluation settings. We theoretically characterize the severity of model mismatch for many common assumptions and show that it can lead to significant issues for learning evaluator preferences and other important downstream tasks. We then present an algorithm for learning evaluators' preferences that is robust to model mismatch. We prove theoretically that our algorithm can learn any preference function without sacrificing performance when the linearity assumption holds. Evaluations of our algorithm with synthetic simulations and real-world data confirm its ability to learn preferences robustly and illustrate key aspects of LLM and human preferences.

Madeline Celi Kitch, Nihar B. Shah

Carnegie Mellon University

Human Preference Modeling Preference Learning Preference Modeling

May 14, 2026

AI Outperforms Humans in Personalized Image Aesthetics Assessment via LLM-Based Interviews and Semantic Feature Extraction

Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI. Various deep learning (DL)-based models have been proposed for this task, training on image evaluation data to extract objective low-level features. However, aesthetic preferences are inherently subjective and individual-dependent. Accurate prediction thus requires the extraction of high-level semantic features of images and the active collection of preference information from the target individual. To address this issue, we focus on the utility of Large Language Models (LLMs) pretrained on vast amounts of textual data, and develop an integrated DL-LLM system. The system actively elicits aesthetic preferences through LLM-based semi-structured interviews and predicts aesthetic evaluation by leveraging both low-level and high-level features. In our experiments, we compare the proposed system against conventional systems, human predictors, and the target individual's own re-evaluations after a certain time interval. Our results show that the proposed system outperforms all of them, with particularly strong performance on highly-rated images. Moreover, the prediction error of the proposed system is smaller than within-person variability, while human predictors show the largest error, likely due to the influence of their own aesthetic values. These results suggest that AI may be better positioned than others or one's future self to capture individual aesthetic preferences at a given point. This opens a new question of whether AI could serve as a deeper interpreter of human aesthetic sensibility than humans themselves.

Yoshia Abe, Tatsuya Daikoku, Yasuo Kuniyoshi

Graduate School of Information Science and Technology The University of Tokyo Bunkyo-ku, Tokyo 113-8654, Japan

Personalized Image Aesthetics Assessment Image Quality Assessment Preference Learning Preference Elicitation

May 12, 2026

Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an explicit aesthetic judgment. Most existing solutions reduce this judgment to predicting a scalar score for a single image. We first ask whether such scores faithfully capture comparative preference: in a controlled study with eight expert annotators, score-derived rankings align poorly with the same annotators' direct comparisons, while direct ranking yields substantially higher inter-annotator agreement on best- and worst-image labels. Motivated by this finding, we introduce the Visual Aesthetic Benchmark (VAB), which casts aesthetic evaluation as comparative selection over candidate sets with matched subject matter. VAB contains 400 tasks and 1,195 images across fine art, photography, and illustration, with labels derived from the consensus of 10 independent expert judges per task. Evaluating 20 frontier MLLMs and six dedicated visual-quality reward models, we find that the strongest system identifies both the best and the worst image correctly across three random permutations of the candidate order in only 26.5% of tasks, far below the 68.9% achieved by human experts. Fine-tuning a 35B-parameter model on 2,000 expert examples brings its accuracy close to that of a 397B-parameter open-weight model, suggesting that the comparative signal in VAB is transferable. Together, these results expose a clear and measurable gap between current multimodal models and expert aesthetic judgment, and VAB provides the first set-based, expert-grounded testbed on which that gap can be tracked and closed.

Yichen Feng, Yuetai Li, Chunjiang Liu +14

Multimodal Large Language Models Image Quality Assessment Multimodal Model Evaluation Preference Learning

May 12, 2026

YFPO: Yoked Feature Preference Optimization with Neuron-Guided Rewards

Preference optimization has become a widely used post-training paradigm for improving the reasoning abilities of large language models. Existing methods typically learn from preferred and dispreferred responses as external behavioral supervision, while largely ignoring capability-related signals encoded in the model's internal representations. In this work, we study whether such internal signals can provide useful auxiliary supervision for mathematical reasoning. We introduce YFPO (Yoked Feature Preference Optimization), a neuron-guided preference optimization framework that couples response-level preference learning with neuron-level rewards. YFPO first uses AttnLRP to identify math-associated internal features, and then derives an auxiliary reward from the activation margin of these neurons between preferred and dispreferred responses. This reward is combined with the standard preference optimization objective, encouraging the model to align external preferences with internal math-related features. We conduct small-scale experiments on GSM8K with a compact language model. Results show that neuron-guided rewards can influence preference optimization dynamics and yield measurable improvements in several settings, suggesting that internal representations can serve as lightweight and interpretable signals for reasoning-oriented post-training.

Yifan Le

Independent Researcher

Preference Optimization Language Model Post-Training Preference Learning LLM Mathematical Reasoning

May 11, 2026

Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training

Preference learning methods like Direct Preference Optimization (DPO) are known to induce reliance on spurious correlations, leading to sycophancy and length bias in today's language models and potentially severe goal misgeneralization in future systems. In this work, we provide a unified theoretical analysis of this phenomenon, characterizing the mechanisms of spurious learning, its consequences on deployment, and a provable mitigation strategy. Focusing on log-linear policies, we show that standard preference-learning objectives induce reliance on spurious features at the population level through two channels: mean spurious bias and causal-spurious correlation leakage. We then show that this reliance creates an irreducible vulnerability to distribution shift: more data from the same training distribution fails to reduce the model's dependence on spurious features. To address this, we propose tie training, a data augmentation strategy using ties (equal-utility preference pairs) to introduce data-driven regularization. We demonstrate that this approach selectively reduces spurious learning without degrading causal learning. Finally, we validate our theory on log-linear models and provide empirical evidence that both the spurious learning mechanisms and the benefits of tie training persist for neural networks and large language models.

Christian Moya, Alex Semendinger, Guang Lin +1

Department of Mathematics, Purdue University, West Lafayette IN, USA

Pairwise Preference Learning LLM Alignment Preference Optimization Spurious Correlation Robustness Preference Learning Spurious Correlation