Preference Optimization

Follow this topic Ask about this topic

Momentum

13 papers in the last four weeks, up 30% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 98

May 27, 2026cs.CL

Hallucination Detection-Guided Preference Optimization for Clinical Summarization

Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications. We introduce Hallucination Detection Guided Self-Refinement (HDSR), an inference-time method that leverages hallucination detectors to guide iterative summary revisions toward factual corrections. Building on this, we propose HDSR for Preference Learning (HDSR-PL), which converts detector-guided refinement trajectories into preference pairs for model finetuning. Extensive experiments show that our methods substantially reduce hallucinations for Llama and Gemma models in summarizing real-world clinical notes from MIMIC-IV-Note v2.2. For example, HDSR reduces 24% and HDSR-PL reduces 48% hallucinations in Llama-3.1-8B-Instruct. Importantly, both methods preserve summary fluency, coherence, and relevance according to human expert and LLM-Jury evaluations. Together, these results demonstrate that detection-informed refinement and preference learning offer an automated solution for improving factual faithfulness in clinical summarization.

Shamanth Kuthpadi Seethakantha, Dung Ngoc Thai, Vara Prasad Gudi +6

1Manning College of Information and Computer Sciences · 2Ensemble HP · 3Columbia University +1

LLM Self-Refinement LLM Hallucination Mitigation Healthcare Hallucination in Language Models Text Summarization Preference Optimization

May 26, 2026cs.LG

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise comparisons. This pairwise reduction is limiting when training data naturally contains multiple candidate images for the same prompt, and when continuous reward scores can provide richer information than a single winner-loser label. To address these limitations, we propose Diffusion LAIR, a reward-aware listwise preference optimization method for diffusion models. For each prompt, LAIR converts reward scores across a group of candidate images into centered advantage weights, then optimizes an advantage-weighted regression objective on the implicit reward, defined as the denoising-loss improvement of the current model over a fixed reference model, with a quadratic penalty that regularizes the magnitude of the implicit reward. The resulting objective uses all candidates simultaneously rather than selecting pairs, and remains conservative by explicitly controlling the magnitude of the implicit reward. The LAIR objective admits a bounded closed-form optimum in implicit-reward space, clarifying how the regularization strength controls the magnitude of the preference update. Experiments show that Diffusion LAIR outperforms strong preference optimization baselines on SD1.5 and SDXL across text-to-image generation, compositional generation, and image editing benchmarks.

Austin Wang, Jiaqi Han, Stefano Ermon +1

Caltech · Stanford University

Diffusion Model Alignment Preference Optimization T2I Diffusion Models

May 22, 2026cs.LG

Convex Optimization for Alignment and Preference Learning on a Single GPU

Fine-tuning large language models (LLMs) to align with human preferences has driven the success of systems such as Gemini and ChatGPT. However, approaches like Reinforcement Learning from Human Feedback (RLHF) remain computationally expensive and complex. Direct Preference Optimization (DPO) offers a simpler alternative but has limitations such as inconsistent ranking accuracy, high dependence on GPU resources, and expensive hyperparameter tuning. We propose the Convex Optimization for Alignment and Preference Learning Algorithm (COALA): a novel lightweight strategy with strong theoretical guarantees. By leveraging the convex optimization reformulation of neural networks, COALA eliminates the need for a reference model and obtains significant reduction in both training time and VRAM consumption, thus enabling efficient training on a single GPU. Experiments across four datasets--including a 26621-sample synthetic Educational Feedback dataset--and six models (including Llama-3.1-8B) demonstrate COALA's competitive performance and efficiency while utilizing as little as ~17.6% of DPO's total TFLOPs. COALA exhibits stable, monotonically increasing rewards and reaches peak margins in significantly shorter time in comparison to traditional methods such as DPO and ORPO. To the best of our knowledge, this is the first time convex optimization has been effectively applied to preference fine-tuning of LLMs.

Miria Feng, Mert Pilanci

Department of Electrical Engineering, Stanford University, California, United States.

Pairwise Preference Learning LLM Alignment LLM Fine-Tuning Efficient Language Model Training Preference Optimization

May 21, 2026cs.CL

Token-weighted Direct Preference Optimization with Attention

Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses equally, neglecting the differing importance of individual tokens. Existing token-level PO methods compute the token weights using either token-position-based heuristic functions or probability estimates given by a separately trained model, which lacks robustness and incurs extra training cost. In contrast, we propose Token-weighted DPO (TwDPO) -- a novel training objective grounded on token-weighted RL -- and AttentionPO -- an instantiation of TwDPO that uses attention from the LLM itself to estimate token weights. AttentionPO prompts the LLM to serve as a pairwise judge and check where the model attends when comparing the responses. This design makes AttentionPO content-aware, adjusting weights based on response content, and efficient, incurring only two extra forward passes per example. Experiment results show that AttentionPO significantly improves performance on AlpacaEval, MT-Bench, and ArenaHard, surpassing existing Preference Optimization methods.

Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1

Cornell University · Vanderbilt University

Pairwise Preference Learning LLM Alignment Direct Preference Optimization Preference Optimization Preference-Based RL

May 20, 2026cs.AI

TO-Agents: A Multi-Agent AI Pipeline for Preference-Guided Topology Optimization

Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied to those preferences. We present TO-Agents, a multi-agent AI framework that connects natural-language design intent with iterative topology optimization. The framework converts a human-provided problem description into validated solver inputs, runs a topology optimization solver, renders the resulting 3D topology, and uses multi-view vision-language reasoning with an independent judge agent to critique each result and revise solver parameters. We evaluate the framework on two long-horizon design tasks: a cantilever beam benchmark and a phone-stand product design. In both tasks, the designer specifies an aesthetic preference for hierarchically branched structures inspired by natural tree morphologies, and the system performs four revision cycles across ten independent replicates. TO-Agents produces at least one preference-aligned design in 60% of trials for each case study, corresponding to up to 6x more successful trials than an ablated pipeline without visual or historical feedback. Judge scores and human evaluations show that the pipeline can identify effective parameter levers, recover from poor revisions, and expand design exploration. A manufacturing agent further post-processes top-ranked designs for additive manufacturing, enabling end-to-end intent-to-prototype design. We also identify failure modes, including overshooting, selective memory, misplaced tools, and incorrect parameter reasoning. These results suggest that agentic topology optimization can shift designers from low-level parameter tuning toward higher-level specification of form and function, while highlighting safeguards needed for reliable autonomous engineering design.

Isabella A. Stewart, Hongrui Chen, Faez Ahmed

Department of Civil and Environmental Engineering Massachusetts Institute of Technology Cambridge, MA, 02139 USA · Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge, MA, 02139 USA

Topology Optimization Multi-Agent System Optimization Multi-Agent Collaboration Tool-Using Vision-Language Agents Preference Optimization Natural Language to Optimization Modeling

May 20, 2026cs.AI

Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment

Direct Preference Optimization (DPO) has emerged as a popular alternative to Reinforcement Learning from Human Feedback (RLHF), offering theoretical equivalence with simpler implementation. We prove this equivalence is conditional rather than universal, depending on an implicit assumption frequently violated in practice: the RLHF-optimal policy must prefer human-preferred responses. When this assumption fails, DPO optimizes relative advantage over the reference policy rather than absolute alignment with human preferences, leading to pathological convergence where policies decrease DPO loss while preferring dispreferred responses. We characterize when this assumption is violated, show the existence of an undesirable solution space, and prove that DPO and RLHF optimize fundamentally different objectives in such cases. To address this, we introduce Constrained Preference Optimization (CPO), augmenting RLHF with constraints for provable alignment. We further provide a geometric interpretation through soft margin ranking, revealing that DPO implements margin ranking with potentially negative targets. Our theoretical analysis establishes when DPOs' guarantees hold and provides solutions preserving simplicity with provable alignment. Comprehensive experiments on standard benchmarks demonstrate that CPO achieves state-of-the-art performance. Code is available at: https://github.com/visitworld123/CPO.

Zhiqin Yang, Yonggang Zhang, Wei Xue +3

1The Hong Kong University of Science and Technology · 2LIGHTSPEED · 3Hong Kong Baptist University.

LLM Alignment Direct Preference Optimization Preference Optimization Preference Alignment RL from Human Feedback

May 20, 2026cs.LG

WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems

Existing neural solvers for Multi-Objective Combinatorial Optimization Problems (MOCOPs) commonly adopt decomposition-based strategies that scalarize an MOCOP into multiple subproblems associated with distinct weight vectors. However, they either inject weights only once during decoding, limiting weight-conditioned context modeling, or primarily during encoding, causing weight-signal dilution during decoding. Moreover, preference optimization methods rely on purely random sampling to construct solution pairs for training solvers, which often produces less informative pairs and thus leads to low training effectiveness. To better address these limitations, we propose an efficient Weight-Conditioned neural solver (WeCon). Specifically, we design an encoder layer with three attention blocks and our proposed Gated Residual Fusion (GRF) block to facilitate harmonious interaction between instance features and weights, thereby generating informative weight-conditioned context. We further introduce a plug-and-play Residual Fusion (RF) block in the decoder to alleviate weight-signal dilution. Finally, we propose Efficient Preference Optimization (EPO), which constructs high-quality solutions, thereby generating more informative pairs to improve training effectiveness. Experiments on four MOCOP variants across different problem scales and distribution patterns demonstrate that WeCon achieves HyperVolume (HV) values comparable to SOTA solver POCCO-W, while reducing inference time by 40%. Ablation studies validate the contributions of all designs.

Xuan Wu, Jinbiao Chen, Yang Li +7

Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, China · Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore 117576, Singapore · College of Software, Jilin University, Changchun 130012, China +3

Preference Optimization Multi-Objective Optimization Neural Combinatorial Optimization

May 13, 2026cs.CV

Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization under joint probabilistic modeling. We propose a stage-wise preference optimization framework for hallucination reduction through targeted multimodal data construction. Rather than directly optimizing on generic instruction-following data, our approach progressively constructs hallucination-focused preference pairs near known failure boundaries. The framework emphasizes ambiguous spatial orientation, object relationships, OCR uncertainty, and adversarial false-premise training. Hallucinated negatives are generated through minimally perturbed yet visually inconsistent alternatives, enabling Direct Preference Optimization (DPO) to better separate grounded reasoning from plausible hallucination. Experiments on open-source benchmarks and real-world multimodal evaluation scenarios demonstrate improved grounding consistency, reduced hallucination, and more informative grounded responses. Cross-model qualitative evaluation further shows that the proposed multimodal LLM DPO framework produces more visually grounded responses than several frontier proprietary VLMs, such as in ambiguous spatial reasoning and adversarial false-premise settings. The results suggest that hallucination may arise not only from limited model capacity, but also from inherent tendencies of autoregressive probabilistic generation to favor linguistically plausible continuations under weak visual grounding. Future work may explore physical consistency modeling, uncertainty-aware multimodal reasoning, and architectural alternatives beyond standard autoregressive decoding.

Qinwu Xu

Meta AI

VLM Robustness Hallucination in Language Models VLM Hallucination Preference Optimization VLM Hallucination Mitigation

May 12, 2026cs.CL

TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching

Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language models from pairwise preferences, but it models preferences over full sequences even though generation is driven by per-token decisions. Existing token-level extensions typically decompose a sequence-level Bradley-Terry objective across timesteps, leaving per-prefix (state-wise) optimality implicit. We study how to recover token-level preference optimality using only standard sequence-level pairwise comparisons. We introduce Token-level Bregman Preference Optimization (TBPO), which posits a token-level Bradley-Terry preference model over next-token actions conditioned on the prefix, and derive a Bregman-divergence density-ratio matching objective that generalizes the logistic/DPO loss while preserving the optimal policy induced by the token-level model and maintaining DPO-like simplicity. We introduce two instantiations: TBPO-Q, which explicitly learns a lightweight state baseline, and TBPO-A, which removes the baseline through advantage normalization. Across instruction following, helpfulness/harmlessness, and summarization benchmarks, TBPO improves alignment quality and training stability and increases output diversity relative to strong sequence-level and token-level baselines.

Truong Nguyen, Tien-Phat Nguyen, Linh Ngo Van +3

Hanoi University of Science and Technology · University of Stuttgart · German Research Center for Artificial Intelligence +3

Pairwise Preference Learning LLM Alignment Pairwise Preference Evaluation Pairwise Ranking Density Ratio Estimation Preference Optimization+2

May 12, 2026cs.CL

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 12, 2026cs.CL

StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models

While large language models excel at factual adaptation, their ability to internalize nuanced philosophical frameworks under severe data constraints remains underexplored. We investigate this by specializing small LLMs on micro-datasets of foundational Stoic texts using preference optimization (ORPO, AlphaPO). Evaluated via a multi-model critic bank, our results show that just 300 high-fidelity examples can induce strong alignment with inward-facing Stoic virtues, closely approaching few-shot prompting while freeing the context window. Critically, however, all models, including few-shot baselines, exhibit a persistent failure on Stoicism's outward-facing cosmopolitan duties, pointing to a representational limitation of small models that micro-dataset adaptation alone cannot overcome.

Ishmam Khan, Sindhuja Thogarrati, Shuo Zhang

Tufts University · Bose Corporation

LLM Alignment LLM Fine-Tuning Small Language Models Preference Optimization Moral Reasoning

May 11, 2026cs.LG

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

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

May 11, 2026cs.CV

Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping

Recently, post-training methods based on reinforcement learning, with a particular focus on Group Relative Policy Optimization (GRPO), have emerged as the robust paradigm for further advancement of text-to-image (T2I) models. However, these methods are often prone to reward hacking, wherein models exploit biases in imperfect reward functions rather than yielding genuine performance gains. In this work, we identify that normalization could lead to miscalibration and directly removing the prompt-level standard deviation term yields an optimal policy ascent direction that is linear in the advantage but still limits the separation of genuine signals from noise. To mitigate the above issues, we propose Super-Linear Advantage Shaping (SLAS) by revisiting the functional update from an information geometry perspective. By extending the Fisher-Rao information metric with advantage-dependent weighting, SLAS introduces a non-linear geometric structure that reshapes the local policy space. This design relaxes constraints along high-advantage directions to amplify informative updates, while tightening those in low-advantage regions to suppress illusory gradients. In addition, batch-level normalization is applied to stabilize training under varying reward scales. Extensive evaluations demonstrate that SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks. In particular, it yields faster training dynamics, improved out-of-domain performance on GenEval and UniGenBench++, and enhanced robustness to model scaling, while mitigating reward hacking and preserving semantic and compositional fidelity in generations.

Haoyuan Sun, Jing Wang, Yuxin Song +9

Nanyang Technological University · Baidu Inc. · Zhejiang University +3

Reward Hacking Preference Optimization RL for Diffusion Models RL Post-Training

May 11, 2026cs.CL

DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization

Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reasoning diversity. To address this limitation, we propose Directional-Groupwise Preference Optimization (DGPO), a lightweight framework that aggregates supervision signals at the group level and explicitly models direction-aware alignment through multi-candidate comparisons. DGPO organizes forward and reverse question-answer instances into structured sets and optimizes a margin-based likelihood objective that separates coherent reasoning paths from inconsistent alternatives. This group-wise formulation captures richer relative information than pairwise objectives and reinforces consistency across diverse reasoning pathways. Empirical results show that our constructed reverse data yields a 3.2% average improvement across five benchmarks, while DGPO further delivers consistent gains across multiple datasets and model families, achieving average accuracy improvements of up to 3.6%.

Mengyi Deng, Zhiwei Li, Xin Li +4

1Information Hub, The Hong Kong University of Science and Technology (Guangzhou), China · 2The Hong Kong University of Science and Technology, Hong Kong SAR

LLM Alignment Reasoning Consistency in Language Models Preference Optimization Preference Alignment LLM Reasoning

May 11, 2026cs.LG

MASS-DPO: Multi-negative Active Sample Selection for Direct Policy Optimization

Multi-negative preference optimization under the Plackett--Luce (PL) model extends Direct Preference Optimization (DPO) by leveraging comparative signals across one preferred and multiple rejected responses. However, optimizing over large negative pools is costly, and many candidates contribute redundant gradients due to their similar effects on policy updates. We introduce MASS-DPO, a multi-negative active sample selection method that derives a PL-specific Fisher-information objective for selecting compact, informative negative subsets within each prompt. The resulting log-determinant objective selects negatives that contribute complementary information for policy updates, yielding compact subsets that retain the full pool's information while reducing redundancy. In practice, this favors negatives whose gradients cover different update directions, reducing redundant signal from near-duplicate candidates while preserving the most useful training information. Across four benchmarks spanning recommendation and multiple-choice QA and three model families, MASS-DPO consistently exceeds or matches existing methods in accuracy, improves Recall/NDCG and margin-based optimization dynamics, and delivers stronger alignment with substantially fewer negatives.

Rohan Surana, Xintong Li, Sheldon Yu +7

1UC San Diego · 2Adobe Research

Direct Preference Optimization Active Learning Preference Optimization Preference-Based RL

May 9, 2026cs.LG

Mechanistic Analysis of Alignment Algorithms in Language Models

Post-training alignment algorithms are predominantly evaluated as black boxes, obscuring how they reshape language models' internal computations. We present a systematic mechanistic analysis of six preference-optimization methods: PPO, DPO, SimPO, ORPO, GRPO, and KTO across three open-weight model families. By integrating layer-wise linear probing, Sparse Autoencoders, and crosscoders, we localize preference representations and quantify alignment-induced geometric transformations in latent space. We find that preference signals consistently concentrate in early--mid or mid--late layers, but different objectives induce qualitatively distinct representational shifts. KTO and GRPO enhance linear separability through constructive feature sharing and sparse, high-salience recruitment. In contrast, DPO and ORPO degrade separability via non-constructive geometric rotation and feature attenuation, while PPO and SimPO largely preserve baseline geometry. These transformations exhibit architecture-dependent variability, demonstrating that behavioral alignment does not imply uniform internal restructuring. Our findings establish alignment as a heterogeneous intervention, motivate standardized feature-level auditing for safety and interpretability, and highlight the need for mechanism-aware optimization objectives.

Aarush Sinha, Ishan Garg, Veeraraju Elluru +2

University of Copenhagen · Independent · IIT Jodhpur +2

LLM Interpretability Mechanistic Interpretability Preference Optimization Preference Alignment

May 9, 2026cs.LG

$ξ$ -DPO: Direct Preference Optimization via Ratio Reward Margin

Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference model through a simple objective. However, the joint tuning of the hyperparameters

β

and

γ

in SimPO remains a central challenge. We argue that this difficulty arises because the margin formulation in SimPO is not easily interpretable across datasets with different reward gap structures. To better understand this issue, we conduct a comprehensive analysis of SimPO and find that

β

implicitly controls sample filtering, while the effect of

γ

depends on the reward gap structure of the dataset. Motivated by these observations, we propose

ξ

-DPO: Direct preference optimization via ratio reward margin. We first reformulate the preference objective through an equivalent transformation, changing the optimization target from maximizing the likelihood of reward gaps to minimizing the distance between reward gaps and optimal margins. Then, we redefine the reward in a ratio form between the chosen and rejected, which effectively cancels the effect of

β

and yields a bounded and interpretable margin. This margin is called the ratio reward margin and is denoted by

ξ

. Unlike the margin

γ

in SimPO,

ξ

explicitly represents the desired relative separation between chosen and rejected responses and can be determined from the initial reward gap distribution, avoiding repeated trial-and-error tuning. ....

Zhengyuan Fan, Zhonghua Wu, Yuxuan Du +1

School of Computer Science, Northwestern Polytechnical University

Pairwise Preference Learning Direct Preference Optimization Preference Optimization RL Post-Training

May 8, 2026cs.LG

Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph

Direct Preference Optimization (DPO) aligns language models using pairwise preference comparisons, offering a simple and effective alternative to Reinforcement Learning (RL) from human feedback. However, in many practical settings, training data consists of multiple rollouts per prompt, inducing rich preference structure that pairwise DPO fails to exploit. Collapsing such data into independent pairs discards transitivity, introduces redundant or conflicting supervision, and can lead to unstable optimization. We propose Graph Direct Preference Optimization (GraphDPO), a principled generalization of DPO that operates over directed acyclic preference graphs induced by rollout rankings. GraphDPO encodes dominance relations as edges and optimizes a graph-structured Plackett--Luce-inspired objective that aggregates supervision over graph neighborhoods, enforcing transitivity while recovering standard DPO as a special case. To handle discrete or sparse signals, we introduce an equivalence-class construction where responses with identical preferences form graph layers, and intra-layer edges contribute zero loss, preventing spurious gradients. Despite leveraging full graph structure, GraphDPO maintains linear per-prompt complexity via efficient log-sum-exp aggregation. We further incorporate optional ground-truth anchoring by inserting verified solutions as dominant nodes and applying an annealed schedule that stabilizes early training while gradually relaxing oracle supervision. Experiments on reasoning and program synthesis tasks demonstrate superior performance, suggesting that graph-structured preference modeling is a scalable and robust alternative to pairwise and listwise alignment objectives.

Ning Liu, Chuanneng Sun, Kristina Klinkner +1

Amazon

Pairwise Preference Learning LLM Alignment Direct Preference Optimization Preference Optimization Preference-Based RL

May 7, 2026cs.CV

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models

Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct preference optimization (DPO), which avoids explicit reward modeling, has been widely studied. However, its reliance on binary feedback limits it to coarse-grained modeling on chosen-rejected pairs, resulting in suboptimal optimization. In this paper, we propose ArenaPO, which leverages Arena scores as offline rewards to provide refined feedback, thus achieving efficient and fine-grained optimization without a reward model. This enables ArenaPO to benefit from both the rich rewards of traditional RLHF and the efficiency of DPO. Specifically, we first construct a model Arena in which each model's capability is represented as a Gaussian distribution, and infer these capabilities by traversing the annotated pairwise preferences. Each output image is treated as a sample from the corresponding capability distribution. Then, for a image pair, conditioned on the two capability distributions and the observed pairwise preference, the absolute quality gap is estimated using latent-variable inference based on truncated normal distribution, which serves as fine-grained feedback during training. It does not require a reward model and can be computed offline, thus introducing no additional training overhead. We conduct ArenaPO training on Pick-a-Pic v2 and HPD v3 datasets, showing that ArenaPO consistently outperforms existing baselines.

Zhikai Li, Yue Zhao, Edward Zhongwei Zhang +4

Institute of Automation, Chinese Academy of Sciences · University of California, Berkeley · University of California, Santa Barbara

Diffusion Model Alignment Preference Optimization Offline Preference Optimization T2I Diffusion Models

May 6, 2026cs.LG

Towards General Preference Alignment: Diffusion Models at Nash Equilibrium

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally efficient alternative that avoids explicit reward modeling and has been widely adopted in diffusion alignment. However, existing preference-based methods for diffusion alignment still rely on reward-induced preference signals and typically assume that human preferences can be adequately modeled by the Bradley--Terry (BT) model, which may fail to capture the full complexity of human preferences. In this paper, we formulate diffusion alignment from a game-theoretic perspective. We propose Diffusion Nash Preference Optimization (Diff.-NPO), an intuitive general preference framework for diffusion alignment. Diff.-NPO encourages the current policy to play against itself to achieve self improvement and lead to a better alignment. Empirically, we demonstrate the effectiveness of Diff.-NPO on the text-to-image generation task via various metrics. Diff.-NPO consistently outperforms existing preference-based diffusion alignment methods.

Jiaming Hu, Jiamu Bai, Haoyu Wang +2

Boston University · Penn State University · University at Albany

Diffusion Model Alignment Preference Optimization Preference Alignment T2I Diffusion Models

May 5, 2026cs.AI

Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models

Vision-Language Models (VLMs) have broad potential in privacy-sensitive domains such as healthcare and finance, yet strict data-sharing constraints render centralized training infeasible. Federated Learning mitigates this issue by enabling decentralized training, but practical deployments face challenges due to client heterogeneity in computational resources, application requirements, and model architectures. Under extreme model and data heterogeneity, replacing parameter aggregation with preference-based collaboration offers a more suitable interface, as it eliminates the need for direct parameter or data exchange. Motivated by this, we propose MoR, a federated alignment framework that combines GRPO with Mixture-of-Rewards for heterogeneous VLMs. In MoR, each client locally trains a reward model from local preference annotations, capturing specific evaluation signals without exposing raw data. To combine these heterogeneous supervision signals, MoR introduces a Mixture-of-Rewards mechanism with learned routing, which adaptively fuses client reward models according to the input and alignment objective. The server then optimizes a base VLM using GRPO with a KL penalty to a reference model, enabling preference alignment without requiring client models to share architectures or parameters. Experiments on diverse public vision-language benchmarks demonstrate that MoR consistently outperforms federated alignment baselines in generalization and cross-client adaptability. Our approach provides a scalable solution for privacy-preserving alignment of heterogeneous VLMs under federated settings.

Shule Lu, Yujing Wang, Hainan Zhang +5

Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing · Institute of Artificial Intelligence, Beihang University, China · MAIS, Institute of Automation, Chinese Academy of Sciences, China +2

Reward Modeling Preference Optimization Vision-Language Alignment RL for VLMs Heterogeneous Federated Learning

May 1, 2026cs.IR

DynamicPO: Dynamic Preference Optimization for Recommendation

In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback negatives and sharpen preference boundaries. However, our empirical analyses reveal a counterintuitive phenomenon, preference optimization collapse, where increasing the number of negative samples can lead to performance degradation despite a continuously decreasing training loss. We further theoretically demonstrate that this collapse arises from gradient suppression, caused by the dominance of easily discriminable negatives over boundary-critical negatives that truly define user preference boundaries. As a result, boundary-relevant signals are under-optimized, weakening the model's decision boundary. Motivated by these observations, we propose DynamicPO (Dynamic Preference Optimization), a lightweight and plug-and-play framework comprising two adaptive mechanisms: Dynamic Boundary Negative Selection, which identifies and prioritizes informative negatives near the model's decision boundary, and Dual-Margin Dynamic beta Adjustment, which calibrates optimization strength per sample according to boundary ambiguity. Extensive experiments on three public datasets show that DynamicPO effectively prevents optimization collapse and improves recommendation accuracy on multi-negative preference optimization methods, with negligible computational overhead. Our code and datasets are available at https://github.com/xingyuHuxingyu/DynamicPO.

Xingyu Hu, Kai Zhang, Jiancan Wu +7

University of Science and Technology of China, Hefei, China · Shanghai Innovation Institute, Shanghai, China · Meituan, Chengdu, China

Hard Negative Mining Preference Optimization Large Language Model-Based Recommendation User Preference Modeling

Apr 27, 2026cs.CV

ViPO: Visual Preference Optimization at Scale

While preference optimization is crucial for improving visual generative models, how to effectively scale this paradigm remains largely unexplored. Current open-source preference datasets contain conflicting preference patterns, where winners excel in some dimensions but underperform in others. Naively optimizing on such noisy datasets fails to learn preferences, hindering effective scaling. To enhance robustness against noise, we propose Poly-DPO, which extends the DPO objective with an additional polynomial term that dynamically adjusts model confidence based on dataset characteristics, enabling effective learning across diverse data distributions. Beyond biased patterns, existing datasets suffer from low resolution, limited prompt diversity, and imbalanced distributions. To facilitate large-scale visual preference optimization by tackling data bottlenecks, we construct ViPO, a massive-scale preference dataset with 1M image pairs at 1024px across five categories and 300K video pairs at 720p+ across three categories. State-of-the-art generative models and diverse prompts ensure reliable preference signals with balanced distributions. Remarkably, when applying Poly-DPO to our high-quality dataset, the optimal configuration converges to standard DPO. This convergence validates dataset quality and Poly-DPO's adaptive nature: sophisticated optimization becomes unnecessary with sufficient data quality, yet remains valuable for imperfect datasets. We validate our approach across visual generation models. On noisy datasets like Pick-a-Pic V2, Poly-DPO achieves 6.87 and 2.32 gains over Diffusion-DPO on GenEval for SD1.5 and SDXL, respectively. For ViPO, models achieve performance far exceeding those trained on existing open-source preference datasets. These results confirm that addressing both algorithmic adaptability and data quality is essential for scaling visual preference optimization.

Ming Li, Jie Wu, Justin Cui +3

University of Central Florida · 2ByteDance Seed · ‡ This work was done during the first author’s internship at USA +1

Diffusion Model Alignment Direct Preference Optimization Preference Optimization

Apr 27, 2026cs.LG

Hindsight Preference Optimization for Financial Time Series Advisory

Time series models predict numbers; decision-makers need advisory -- directional signals with reasoning, actionable suggestions, and risk management. Training language models for such predictive advisory faces a fundamental challenge: quality depends on outcomes unknown at prediction time. We bridge two ideas from reinforcement learning -- using information unavailable during execution to retrospectively generate training signal, and preference alignment -- and propose Hindsight Preference Optimization: observed outcomes let an LLM judge rank candidate advisories on dimensions that scalar metrics cannot capture, producing preference pairs for DPO without human annotation. We apply this to Vision-Language-Model-based predictive advisories on S&P 500 equity time series, demonstrated by a 4B model outperforming its 235B teacher on both accuracy and advisory quality.

Yanwei Cui, Guanghui Wang, Xing Zhang +7

1AWS Generative AI Innovation Center · 2HSBC Holdings Plc. HSBC Technology Center China

LLM Alignment Financial Forecasting LLM-Based Time Series Forecasting Preference Optimization Financial Time Series Finance

Apr 23, 2026cs.AI

Align Generative Artificial Intelligence with Human Preferences: A Novel Large Language Model Fine-Tuning Method for Online Review Management

Online reviews have played a pivotal role in consumers' decision-making processes. Existing research has highlighted the significant impact of managerial review responses on customer relationship management and firm performance. However, a large portion of online reviews remains unaddressed due to the considerable human labor required to respond to the rapid growth of online reviews. While generative AI has achieved remarkable success in a range of tasks, they are general-purpose models and may not align well with domain-specific human preferences. To tailor these general generative AI models to domain-specific applications, finetuning is commonly employed. Nevertheless, several challenges persist in finetuning with domain-specific data, including hallucinations, difficulty in representing domain-specific human preferences, and over conservatism in offline policy optimization. To address these challenges, we propose a novel preference finetuning method to align an LLM with domain-specific human preferences for generating online review responses. Specifically, we first identify the source of hallucination and propose an effective context augmentation approach to mitigate the LLM hallucination. To represent human preferences, we propose a novel theory-driven preference finetuning approach that automatically constructs human preference pairs in the online review domain. Additionally, we propose a curriculum learning approach to further enhance preference finetuning. To overcome the challenge of over conservatism in existing offline preference finetuning method, we propose a novel density estimation-based support constraint method to relax the conservatism, and we mathematically prove its superior theoretical guarantees. Extensive evaluations substantiate the superiority of our proposed preference finetuning method.

Yanan Wang, Yong Ge

Department of Information Systems and Operations Management, The University of Texas at Arlington · Department of Management Information Systems, University of Arizona

LLM Hallucination Mitigation LLM Fine-Tuning Preference Optimization User Preference Modeling

Apr 22, 2026cs.AI

HiPO: Hierarchical Preference Optimization for Adaptive Reasoning in LLMs

Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over dispreferred responses in their entirety and lacks the granularity to provide feedback on subsections of many-step solutions typical of reasoning tasks. Existing methods excel at either stable preference learning (e.g., DPO variants like KTO and RSO) or structured reasoning (e.g., ReMA's multi-agent RL framework, Tree of Thoughts), but fail to merge these complementary strengths. We propose HiPO (Hierarchical Preference Optimization), an extension of DPO that separates responses into reasoning segments (query clarification and context, reasoning steps, and answer) and computes loss as a weighted sum of the DPO loss for each segment. Our approach enables segment-specific training while maintaining DPO's computational efficiency and training stability. We demonstrate that for multiple 7B LLMs fine-tuned using HiPO and DPO on the Math Stack Exchange preference dataset, the models trained with HiPO outperform the others on a variety of common math benchmarks and achieve greater organization, logical flow, and consistency as measured by GPT-4.1.

Darsh Kachroo, Arjun Prasaath Anbazhagan, Adriana Caraeni +2

Vellore Institute of Technology, Chennai · Northwestern University · University of Massachusetts Amherst +2

LLM Alignment Direct Preference Optimization Mathematical Reasoning Preference Optimization LLM Reasoning

Apr 20, 2026cs.LG

Towards Disentangled Preference Optimization Dynamics: Suppress the Loser, Preserve the Winner

Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they try to suppress the rejected one, and there is no general way to prevent this across different objectives. We address this issue with a unified incentive-score decomposition of preference optimization, revealing that different objectives share the same local update directions and differ only in their scalar weights. This decomposition provides a common framework for analyzing objectives that were previously studied in separate settings. Building on this decomposition, by analyzing the dynamics of the chosen/rejected likelihoods, we identify the disentanglement band (DB), a simple, testable condition that tells us when training can follow the desired path: suppress the loser while preserving the winner, possibly after an early stage. Using the DB, we propose reward calibration (RC), a plug-and-play method that adaptively rebalances the updates for chosen and rejected responses to satisfy the DB, without redesigning the base objective. Empirical results show that RC leads to more disentangled dynamics, with better downstream performance observed across several settings. Our code is available at https://github.com/IceyWuu/DisentangledPreferenceOptimization.

Wei Chen, Yubing Wu, Junmei Yang +5

1South China University of Technology · 2AIP, RIKEN · 3Columbia University +1

Pairwise Preference Learning LLM Alignment Preference Optimization

Apr 17, 2026cs.CL

GroupDPO: Memory-Efficient Group-Wise Direct Preference Optimization

Preference optimization is widely used to align Large Language Models (LLMs) with preference feedback. However, most existing methods train on a single positive-negative pair per prompt, discarding additional supervision available in preference datasets that typically contain multiple candidate responses. Motivated by this limitation, recent work explores group-wise preference optimization, which jointly contrasts multiple responses for the same prompt, but its empirical behavior and scalability remain underexplored due to the memory overhead of group-coupled objectives. In this work, we present a unified empirical and systems study of group-wise preference optimization and develop a memory-efficient implementation for group-coupled objectives. By instantiating first-order linearization with objective-specific per-response coefficients, our implementation preserves first-order gradients while decoupling samples during backpropagation, substantially reducing peak memory usage and enabling scalable training with larger groups. Across offline and online settings, we show that leveraging multiple responses consistently outperforms single-pair training. Furthermore, incorporating a negative log-likelihood (NLL) term on positive responses is critical for both performance gains and training stability.

Jixuan Leng, Si Si, Hsiang-Fu Yu +2

Carnegie Mellon University · Google DeepMind · Google

LLM Alignment Direct Preference Optimization Preference Optimization LLM Training Memory-Efficient Training

Feb 10, 2026cs.AI

Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge

Multi-agent systems (MAS) can substantially extend the reasoning capacity of large language models (LLMs). Most MAS frameworks aggregate agent outputs via simple majority voting, discarding the evidential structure of reasoning traces. Majority voting is brittle under confabulation consensus, where agents share correlated biases and converge on the same incorrect rationale. We introduce AgentAuditor, which moves beyond frequency-based aggregation by organizing agent traces into a Reasoning Tree that explicitly represents agreements and divergences in their reasoning. AgentAuditor resolves conflicts by comparing branch-level evidence at critical divergence points, turning global adjudication into efficient, localized verification. We further propose Anti-Consensus Preference Optimization (ACPO), which trains the adjudicator with evidence-verified preference supervision to reduce conformity to misleading majority cues. Across four MAS frameworks and multiple reasoning benchmarks, AgentAuditor consistently improves aggregation performance over majority voting, with gains of up to 5% absolute accuracy while remaining token-efficient.

Wei Yang, Shixuan Li, Heng Ping +3

University of Southern California

LLM Auditing Preference Optimization Multi-Agent Systems Multi-Agent Consensus Multi-Agent Reasoning Reasoning Verification

Feb 1, 2026cs.AI

Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment

Offline preference optimization aligns reasoning models from fixed chosen--rejected pairs, yet standard methods apply gradient updates from every pair regardless of its training value under the current policy. We argue that this uniform treatment is wasteful and potentially harmful. From the perspective of gradient utility, we show that a pair's contribution depends jointly on informativeness and stability. Pair utility drifts as the policy evolves, high-gradient samples can coincide with high-curvature regions, leading to noisy and destabilizing updates, and the most effective supervision comes from stable confident errors where the model is reliably wrong yet curvature remains low. These findings motivate SAGE (Stability-Aware Gradient Efficiency), which maintains difficulty-stratified candidate pools refreshed during training and selects pairs within each pool by a forward-pass signal-to-curvature score. Only pairs with high current utility receive gradient computation; the rest are excluded from backpropagation. On mathematical reasoning benchmarks across multiple model scales, SAGE outperforms full-data and size-matched baselines while producing substantially smoother optimization trajectories.

Hui Wu, Hengyi Cai, Jinman Zhao +6

Baidu Inc. · University of Toronto · School of Intelligence Science and Technology, Peking University +1

Pairwise Preference Learning Training Data Selection Preference Optimization Offline Preference Optimization Gradient Descent Dynamics Gradient Alignment