Overview

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

162 papers19 papers in the last four weeks, up 12% on the four weeks before. 0.1% of all new papers.

Feb 17, 2026

What Is Missing: Interpretable Ratings for Large Language Model Outputs

Current Large Language Model (LLM) preference learning methods such as Proximal Policy Optimization and Direct Preference Optimization learn from direct rankings or numerical ratings of model outputs, these rankings are subjective, and a single numerical rating chosen directly by a judge is a poor proxy for the quality of natural language, we introduce the What Is Missing (WIM) rating system to produce rankings from natural-language feedback, WIM integrates into existing training pipelines, can be combined with other rating techniques, and can be used as input to any preference learning method without changing the learning algorithm, to compute a WIM rating, a human or LLM judge writes feedback describing what the model output is missing, we embed the output and the feedback with a sentence embedding model and compute the cosine similarity between the resulting vectors, we empirically observe that, compared to discrete numerical ratings, WIM yields fewer ties and larger rating deltas, which improves the availability of a learning signal in pairwise preference data, we use interpretable in the following limited sense: for each scalar rating, we can inspect the judge's missing-information text that produced it, enabling qualitative debugging of the preference labels.
Feb 11, 2026

Next-token Preference: Scaling Unsupervised Reward Modeling

Learning from feedback advances the capabilities and safety of frontier models, but preference supervision remains costly and difficult to scale. We introduce next-token preference (NTP), an unsupervised reward-modeling method that constructs preference pairs from the continuation structure of raw web text. NTP uses each prefix's original continuation as the chosen response and nearby continuations as in-batch negatives, without candidate generation or human or model-generated preference annotations. Training on 11M tokens of math-focused web data yields steady gains on RewardBench and RewardBench 2, with gains across model families and sizes. Across mathematical and general-domain web corpora, our method improves overall RewardBench 2 accuracy by 7.6-8.3 percentage points over initialization under the same token budget. Training on math-focused text yields gains of up to +16.1 on in-domain math subsets and consistent improvements on out-of-domain safety and general subsets. These reward models improve best-of-N selection on math, code, safety, and instruction following, and support math policy optimization competitive with supervised reward models of similar size. NTP also improves the label efficiency of subsequent supervised fine-tuning. Using half the labeled pairs from a curated preference dataset, NTP initialization surpasses base initialization trained on the full dataset. These results suggest that web text contains transferable preference signals that can reduce dependence on costly preference annotations.
Feb 2, 2026

Towards Optimality in Active Preference Learning

Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many existing approaches adopt classical experimental design criteria such as G- or D-optimality. These objectives are not tailored to the structure of preference learning, leaving open the design of problem-specific algorithms. In this work, we identify a simple intuition specific to preference learning that calls into question the suitability of these existing design objectives. Motivated by this insight, we propose two active learning algorithms. The first provides the first instance-dependent label complexity guarantee for this setting, and the second is a simple, practical greedy method. We show the optimality of our instance-dependent term up to a constant depending on the logit bound, compared with a lower-bound characteristic. We evaluate our algorithms on real-world preference datasets and synthetic data observing improved sample efficiency compared to existing methods.
Jan 18, 2026

ReWorld: Multi-Dimensional Reward Modeling for Embodied Video Generation

Current embodied video generation models primarily emphasize visual generative quality while overlooking physical fidelity, dynamic consistency, and task logic, especially for contact-rich manipulation tasks, which limits their applicability to downstream tasks. In this paper, we introduce ReWorld, a framework aimed to employ reinforcement learning to align the video generation with physical realism, task completion capability, embodiment plausibility and visual quality. Specifically, we first construct a large-scale (~235K) video preference dataset and employ it to train a hierarchical reward model designed to capture multi-dimensional reward consistent with human preferences. We further propose a practical alignment algorithm that post-trains flow-based video generators using this reward through a computationally efficient PPO-style algorithm. Comprehensive experiments and theoretical analysis demonstrate that ReWorld significantly improves the physical fidelity, logical coherence, embodiment and visual quality of generated rollouts, outperforming previous methods.
Nov 27, 2025

Co-Evolving Agents: Learning from Failures as Hard Negatives

Self-evolving agents improve their performance on long-horizon tasks by learning from their own interactions with an environment. A common approach uses the resulting failed trajectories as negatives for preference training. However, collecting an agent's own failures does not ensure that they provide informative supervision for further improvement. Obvious failures may be easy to reject without learning to identify errors in more plausible attempts. These plausible but incorrect trajectories can serve as hard negatives, helping agents learn to distinguish successful behavior from failures with less obvious errors. To enable agents to generate and learn from such informative negatives, we propose a co-evolving framework that couples a target agent's self-improvement with a failure agent trained to generate hard negatives. The failure agent learns exclusively from both agents' failed trajectories to generate higher-reward failures, which the target agent uses as negatives for preference training. As the target policy improves, its failures provide new training data for the failure agent. The updated failure agent, in turn, provides new negatives for target training, allowing negative generation to adapt alongside the target policy. Across online shopping, scientific reasoning, and interactive SQL querying, our framework improves average task reward by 5.7 over the baseline. These results demonstrate the value of learning to generate and use informative failures for agent self-improvement. We will make our code publicly available.
Sep 26, 2025

Adaptive Margin RLHF via Preference over Preferences

Margin-based optimization is fundamental to improving generalization and robustness in classification tasks. In the context of reward model learning from preferences within Reinforcement Learning from Human Feedback (RLHF), existing methods typically rely on no margins, fixed margins, or margins that are simplistic functions of preference ratings. However, such formulations often fail to account for the varying strengths of different preferences or they rely on noisy margin information derived from preference ratings. Furthermore, many existing methods that use adaptive margins assume access to accurate preference scores, which can be difficult for humans to provide reliably. We propose leveraging preferences over preferences, that is, annotations indicating which of two preferences reflects a stronger distinction, to infer adaptive margins on a per-datapoint basis. Such preference-over-preference annotations are general and can be incorporated into both standard RLHF reward modeling objectives and direct alignment losses. As a concrete instantiation, we introduce DPO-PoP, an extension to Direct Preference Optimization (DPO) that incorporates adaptive margins from preference-over-preference supervision, enabling improved discriminative and generative performance. Additionally, we show a tradeoff between discriminative and generative performance and propose two sampling strategies for gathering preference-over-preference labels to navigate it.
Jun 27, 2025

Interactive Multi-Objective Probabilistic Preference Learning with Soft and Hard Bounds

High-stakes decision-making involves navigating multiple competing objectives with expensive evaluations. For instance, in brachytherapy, clinicians must balance maximizing tumor coverage (e.g., an aspirational target or soft bound of >95% coverage) against strict organ dose limits (e.g., a non-negotiable hard bound of <601cGy to the bladder). Selecting Pareto-optimal solutions that match implicit preferences is challenging, as exhaustive Pareto frontier exploration is computationally and cognitively prohibitive, necessitating interactive frameworks to guide users. While decision-makers (DMs) often possess domain knowledge to narrow the search via such soft-hard bounds, current methods often lack systematic approaches to iteratively refine these multi-faceted preference structures. Furthermore, DMs often require confidence that they have not overlooked superior alternatives, a paramount necessity in high-stakes scenarios. We present Active-MoSH, an interactive local-global framework designed for this process. Its local component integrates probabilistic preference learning with an active sampling strategy to adaptively refine Pareto subsets while minimizing cognitive burden. To bolster decision confidence, Active-MoSH's global component, C-MoSH, leverages multi-objective sensitivity analysis to identify potentially overlooked, high-value points beyond immediate feedback. We demonstrate Active-MoSH's performance benefits through diverse synthetic and real-world applications. A high-stakes case study with real cervical cancer brachytherapy treatment plans and an image selection user study further validate our hypotheses regarding the framework's ability to improve convergence, enhance DM confidence, and provide expressive preference articulation.
May 30, 2025

MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a global reward function, failing to capture the inherently diverse and heterogeneous human preferences. Hence, such oversimplification limits LLMs from supporting personalization and pluralistic alignment. Theoretically, we show that when human preferences follow a mixture distribution of diverse subgroups, a single BT model has an irreducible error. While existing solutions, such as multi-objective learning with fine-grained annotations, help address this issue, they are costly and constrained by predefined attributes, failing to fully capture the richness of human values. In this work, we introduce MiCRo, a two-stage framework that enhances personalized preference learning by leveraging large-scale binary preference datasets without requiring explicit fine-grained annotations. In the first stage, MiCRo introduces context-aware mixture modeling approach to capture diverse human preferences. In the second stage, MiCRo integrates an online routing strategy that dynamically adapts mixture weights based on specific context to resolve ambiguity, allowing for efficient and scalable preference adaptation with minimal additional supervision. Experiments on multiple preference datasets demonstrate that MiCRo effectively captures diverse human preferences and significantly improves downstream personalization.
May 15, 2025

Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment

Reward models (RMs) are central to aligning large language models (LLMs) with human values, yet noisy preference feedback can induce reward misgeneralization through spurious correlations and overfitting. We characterize the training dynamics of preference pairs and uncover a distinctive optimization signature of noise: persistently high losses, sharp temporal fluctuations, and irregular gradient updates. Our analyses further show that excluding such pairs improves downstream alignment. In practice, however, reliable preferences are not known a priori, and self-filtering based on a model's own training signals can amplify confirmation bias. To address this challenge, we introduce Collaborative Reward Modeling (CRM), an online framework for identifying reliable preferences. CRM couples cross-model peer review with curriculum learning: two RMs evaluate each other's sample selections, while curriculum keeps their learning progress synchronized. Across extensive experiments, CRM improves RM generalization by up to 9.94 points on RewardBench under 40% preference noise. CRM further generalizes to implicit-reward alignment, offering a robust and broadly applicable approach to learning from imperfect feedback.
Apr 10, 2025

Dual-Difficulty Curriculum Learning for Direct Preference Optimization

Curriculum learning enhances Direct Preference Optimization (DPO) for aligning Large Language Models (LLMs), yet existing methods rely on a one-dimensional view of difficulty. In this work, we reframe alignment difficulty as a two-dimensional space spanned by Prompt Complexity (PC) and Pairwise Distinguishability (PD), providing a more principled foundation for alignment. We first demonstrate the efficacy of this space by developing DM-Curri-DPO, a framework of static curricula that already achieves significant gains over baseline methods. Moving beyond these handcrafted paths, we introduce our primary contribution: GSP-Curri-DPO, a novel Group-wise Self-Paced Learning framework. This advanced method empowers the model to navigate the difficulty grid, discovering an optimal learning trajectory based on its own evolving capabilities. Extensive experiments show our self-paced approach not only sets a new state-of-the-art on key benchmarks but, more importantly, demonstrates superior data efficiency and robustness to preference noise. Our work establishes a new paradigm for LLM alignment, offering both a structured difficulty space and an intelligent, model-driven methodology for navigating it.
Feb 2, 2025

Inferring the Unspoken: Aligning Embodied Agents with Implicit Preferences

Natural-language instructions rarely specify every detail required for embodied action. An agent asked to ``prepare an apple,'' for example, must still determine whether to wash or cut it, where to place it, and in what order to perform these actions. Such decisions often reflect user-specific preferences that are demonstrated through behavior but never explicitly stated. We study whether embodied agents can infer these latent preferences from a small number of prior demonstrations and apply them when planning in new situations. To support systematic evaluation, we introduce Preference-based Planning (PbP), a benchmark containing 5,000 evaluation groups and 290 preferences organized into three levels: atomic action parameters, strategic interaction and placement policies, and temporal ordering constraints. We further propose Inferring the Unspoken (InTU), a two-stage framework that first verbalizes the preference inferred from multimodal behavioral demonstrations and then generates an action plan conditioned on that explicit representation. Experiments with video-language and language models reveal a substantial preference-acquisition gap: models plan effectively when given the ground-truth preference, but their performance degrades sharply when the same preference must be inferred from behavior. Explicit verbalization consistently improves alignment over direct end-to-end planning, particularly for strong multimodal models, and provides greater robustness when preferences must transfer across visually distinct scenes. These results identify visual-to-semantic preference acquisition, rather than preference-conditioned planning alone, as a central bottleneck in personalized embodied intelligence. They also demonstrate that language can serve as an interpretable and transferable intermediate representation between observed behavior and personalized action.
Mar 16, 2024

A Probabilistic Approach for Model Alignment with Human Comparisons

A growing trend involves integrating human knowledge into learning frameworks, leveraging subtle human feedback to refine AI models. While these approaches have shown promising results in practice, the theoretical understanding of when and why such approaches are effective remains limited. This work takes steps toward developing a theoretical framework for analyzing the conditions under which human comparisons can enhance the traditional supervised learning process. Specifically, this paper studies the effective use of noisy-labeled data and human comparison data to address challenges arising from noisy environment and high-dimensional models. We propose a two-stage "Supervised Learning+Learning from Human Feedback" (SL+LHF) framework that connects machine learning with human feedback through a probabilistic bisection approach. The two-stage framework first learns low-dimensional representations from noisy-labeled data via an SL procedure and then uses human comparisons to improve the model alignment. To examine the efficacy of the alignment phase, we introduce a concept, termed the "label-noise-to-comparison-accuracy" (LNCA) ratio. This paper identifies from a theoretical perspective the conditions under which the "SL+LHF" framework outperforms the pure SL approach; we then leverage this LNCA ratio to highlight the advantage of incorporating human evaluators in reducing sample complexity. We validate the framework on a real high-dimensional crowdfunding-prediction task: under a fixed query budget, trading labels for comparisons improves accuracy precisely when labels are scarce, and the findings hold when the evaluator is replaced by real large language models. A study conducted via Amazon Mechanical Turk (MTurk) further validates the model primitives.