Direct Preference Optimization

Also known as DPO

Ask about this topic

Overview

Direct Preference Optimization (DPO) studies how to align a model with preferences by training it to favor chosen responses over rejected ones, usually relative to a reference model. Research extends the basic pairwise objective with adaptive margins and weighting, token- or segment-level credit, methods for noisy or conflicting labels, and online or curriculum-based data selection. DPO is used for language-model alignment in helpfulness, safety, and reasoning, and is increasingly adapted to multimodal models and diffusion-based image, video, and audio generation. A central tension is improving preference alignment and robustness without sacrificing general capabilities, diversity, or reliable performance when preferences and inputs shift.

Latest papers

CardsList

162 papers24 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Sep 13, 2026

Bridging Data, Reasoning, and Alignment: A Unified Framework for Context-Aware Instruction-Following TTS

The ISCSLP 2026 CoT-TTS Challenge requires TTS systems to generate Chain-of-Thought (CoT) reasoning from dialogue history before synthesizing contextually appropriate speech. While the official baseline establishes a unified architecture, it remains constrained by limited contextual comprehension, weak instruction fidelity, and suboptimal audio quality. We present a systematic optimization pipeline to address these limitations. First, we develop a data process framework that cleans raw data via FullSubNet denoising, Qwen3-ASR re-transcription, and Qwen3.5-35B-A3B-based history-CoT consistency analysis, while distilling 545K high-fidelity instruction samples using Qwen3-TTS and Seed-VC under strict quality filtration. Second, we propose a Context-Aware Direct Preference Optimization (CA-DPO) method. By employing a cascaded filtering strategy, ASR prescreening, LLM tournament ranking, and speaker similarity verification, we obtain high-confidence preference pairs that significantly enhance holistic ``Context→\rightarrowCoT→\rightarrowSpeech'' consistency during DPO training. Third, we establish an evaluation method featuring a 500-sample test set and an LLM-as-Judge framework to independently assess reasoning and execution fidelity. Experiments demonstrate that our system significantly outperforms the baseline across all objective and subjective metrics, validating our data governance and alignment strategies.

Jingbin Hu, Luyu Wang, Wenjie Tian +7

Shenzhen Pimei Technology Co., Ltd., Guangdong, China · School of Intelligence Science and Technology, Nanjing University, Suzhou, China · State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China

Text-to-SpeechSpeech Language ModelsDirect Preference Optimization
AskPDF
Sep 11, 2026

Direct Preference Density Alignment for Conversational Audio Equalization

Large Language Model alignment typically relies on learned proxy reward models, which significantly increase the memory footprint during training and are notoriously prone to instability and reward hacking. While offline methods like Direct Preference Optimization (DPO) bypass the reward model, they lose the ability to perform online exploration. If no optimization constraints are applied, this can lead to format collapse in bounded, continuous spaces. To resolve this, we propose Direct Preference Density Alignment: An alternative framework that removes the need for a learned proxy reward model while strictly preserving the benefits of online reinforcement learning. We leverage large-scale user data (approximately 90,000 samples) to construct non-parametric preference density maps, establishing an empirical reward surface. In addition to removing the reward model, Direct Preference Density Alignment enables the combination of the online structural grounding of Group Relative Policy Optimization (GRPO) with the targeted offline refinement of DPO. We show that this GRPO+DPO combination achieves the highest performance, and in a blind audio equalization listening test, enables a 1.5B-parameter model to achieve perceptual parity with a carefully prompt-engineered GPT-4o mini baseline, using only a fraction of the inference compute.

Ioannis Stylianou, Sven Ewan Shepstone, Jon Francombe +2

Department of Electronic Systems Aalborg University Aalborg, Denmark · Bang & Olufsen A/S Struer, Denmark

RL for Language ModelsLLM AlignmentDirect Preference OptimizationPreference Optimization
AskPDF
Sep 10, 2026

LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation

Large language model serving costs scale directly with output sequence length, yet standard preference alignment often inflates response verbosity without improving utility. We study whether the parameterization of post-training updates affects generation length: low-rank subspaces alter sequence length without modifying the alignment loss. We present LOCUS, a method that selects a task-aware low-rank adaptation subspace to minimize output-token cost subject to a utility constraint. Within this subspace, post-training retains the native preference objective with a frozen backbone. Across Anthropic HH-RLHF dialogue preferences, we evaluate two ∼\sim3B decoder backbones, Pythia-2.8B and Qwen2.5-3B, against protocol-matched full-parameter DPO and DrDPO branches and the released SamPO checkpoint. LOCUS reduces continuation length by up to 39.84% on Pythia-2.8B and by 14.87--17.58% on Qwen2.5-3B while updating only 0.24--0.28% of model parameters, with no material change in the internal preference diagnostic.

Dongfang Zhao

Direct Preference OptimizationControllable Text GenerationLow-Rank AdaptationLanguage Model Post-Training
AskPDF
Sep 10, 2026

Preference Optimization with LALM Feedback for Continuous Autoregressive Non-Verbal Vocalization Generation

We propose a preference optimization framework with Large Audio-Language Model (LALM) feedback for controllable non-verbal vocalization (NVV) generation in continuous autoregressive speech models. To construct preference data without human preference annotation, we build a bilingual prompt corpus by combining NVV-injected real transcripts with LLM-generated semantically aligned prompts, perform stochastic model rollouts, and use a LALM to rank candidate utterances and form same-prompt chosen--rejected pairs. We then adopt a two-stage optimization strategy: Rejection Sampling Fine-Tuning (RSFT) first adapts the model to LALM-selected high-scoring samples, followed by Anchored Flow-DPO, which formulates pairwise preference optimization using utterance-level flow-matching loss and retains the chosen-sample flow-matching objective as an SFT anchor. This design enables DPO-style preference learning without explicit sequence likelihoods while preserving direct supervision on preferred realizations. On the official 1,600-utterance NVVSpeech Challenge Track~2 test set, our method achieves a Final Track2Score of 75.80 (79.39 ZH / 72.21 EN), outperforming the VoxCPM2 baseline by +1.84. The improvements are mainly driven by higher NVV Accuracy and NVV Perceptual Effect, while Overall Quality remains stable.

Jingbin Hu, Qirui Zhan, Yuang Cao +7

Shenzhen Pimei Technology Co., Ltd., Guangdong, China · Yutu Zhineng, Beijing, China · State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China +1

Nonverbal Vocalization GenerationDirect Preference OptimizationControllable Speech GenerationAudio Generation
AskPDF
Sep 7, 2026

You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMs

Ask a language model to respond "very excitedly," and its output is typically only mildly more energetic. We quantify this effect. We condition an instruction-tuned LLM on a continuous Valence-Arousal (VA) target, where valence measures how pleasant a state is and arousal how activated it is, measure the achieved affect with a frozen regressor, and sweep the requested target from -1 to +1. The response moves far less than asked: the gain, the slope of achieved against requested affect, is only 0.26 for valence and 0.13 for arousal on Llama-3.1-8B, where a faithful controller would score 1. The model systematically undershoots requested emotional intensity, which puts a number on the qualitative observation of Fazzi et al. (2025). Our experiments trace this to the preference-learning pipeline. Training targets from natural corpora such as EmoBank are neutral-heavy, and the sampled candidates themselves rarely reach extreme affect, so Direct Preference Optimization (DPO) is left with no extreme exemplar to prefer. If instead we cover the target space uniformly and sample a hotter, larger candidate pool, valence gain rises from 0.26 to 0.40 +/- 0.02 (3 seeds) and extrapolation error drops, at only a modest in-distribution cost (EmoBank-test VA distance 0.092 to 0.107). The same recipe reproduces on Qwen3-8B (gain_v 0.44, with in-distribution accuracy preserved). Arousal is harder and less reliable: its gain barely moves on average and swings across seeds (0.14 +/- 0.07, against valence's tight +/- 0.02), because raising arousal needs candidates the base model is reluctant to generate. The evidence indicates that faithful intensity is bottlenecked by the extremity of the candidate pool rather than by the conditioning format.

Hyunwoo Kim, Usama Khalid

Department of Computer Software Hanyang University, Seoul

Direct Preference OptimizationValence-Arousal ModelingLanguage Model Post-TrainingEmotion Representation in Language Models
AskPDF
Sep 7, 2026

Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking

Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated with only one negative candidate per training instance. This discards information from the remaining candidates retrieved for the same mention. We introduce multi-negative direct preference optimisation (MDPO), a reference-based pairwise objective that compares the correct entity with all valid rejected candidates associated with each mention. MDPO preserves the Bradley-Terry formulation of DPO while exploiting the complete candidate set through masked, length-normalised sequence scores. We evaluate MDPO on hipe-2020 and newseye, covering French, German, English, Swedish, and Finnish historical newspaper text. Experiments show that MDPO improves over supervised fine-tuning and single-negative DPO, with particularly strong gains for NIL mentions, semantic ambiguity, OCR noise, and historically difficult names. Further analyses disentangle candidate-generation and selection errors, showing that candidate retrieval remains a key bottleneck for end-to-end entity linking. These results demonstrate that incorporating all within-instance negative candidates is a simple and effective improvement for LLM-based historical entity linking.

Tien Nam Nguyen, Emanuela Boros, Ahmed Hamdi +3

L3i, University of La Rochelle, La Rochelle, France · University of Toulouse, IRIT, Toulouse, France · University of Innsbruck, Austria +1

LLM AlignmentDirect Preference OptimizationEntity Linking
AskPDF
Sep 6, 2026

DIPLOMAT: Dialogue-Span-Aware Direct Preference Optimization for Polite Persuasive Workplace Negotiation Dialogues

Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resolving conflicts constructively. However, misunderstandings, misaligned preferences, and interpersonal friction often impede successful outcomes. Politeness mitigates these challenges by fostering trust, reducing tension, and preventing escalation, and persuasive communication helps overcome resistance, align preferences, and guide participants toward mutually beneficial agreements. Motivated by these insights, we present DIPLOMAT, a dialogue system for polite and persuasive workplace negotiation. To support its development, we introduce PROWESS, a dataset of multi-turn workplace negotiation dialogues generated via a multi-agent framework and enriched withnegotiation strategies, politeness levels, persuasive strategies. DIPLOMAT is trained using Dialogue-Span-Aware Direct Preference Optimization (DSA-DPO), a novel preference learning objective that identifies key dialogue spans for preference alignment. This enables DIPLOMAT to generate contextually coherent responses that employ intended negotiation strategies, maintain politeness, and incorporate effective persuasion strategies throughout interactions. Automatic and human evaluation on PROWESS confirm that DIPLOMAT consistently outperforms baselines in generating coherent, polite, and persuasive negotiation responses.

Bibhuti Jha, Rishikant Chigrupaatii, Priyanshu Priya +1

Department of Computer Science and Engineering, Indian Institute of Technology Patna, India · GREYC Laboratory, University of Caen Normandy, France

Automated NegotiationDirect Preference OptimizationPersuasion in Language Models
AskPDF
Sep 1, 2026

CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs

Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce CopyShield, a controlled benchmark comparing three representative defenses at distinct intervention levels: contrastive decoding (output), Direct Preference Optimization (behavioral), and activation intervention (representation). We evaluate CopyShield on two model families, LLaMA-3.1-8B and Mistral-7B-v0.3, using controlled memorization over five public-domain books and a shared protocol measuring literal leakage, calibrated non-literal leakage, utility, and degeneracy. Across these methods, intervention level is associated with distinct compliance-utility trade-offs. On LLaMA-3.1-8B, contrastive decoding remains near-degeneracy-free (0-2%) but reaches a literal-suppression floor at NV-Recall 0.192-0.203. DPO nearly eliminates literal leakage (0.263 to 0.002) but induces paraphrase-loop degeneracy in 58% of QA outputs, with no utility gain over the SFT baseline. Activation intervention attains the lowest non-literal flagging rate (1/200) by blocking 84% of non-literal queries before generation. Human evaluation confirms that DPO has low coherence, whereas activation lowers perceived copyright risk through broad refusal. On Mistral-7B-v0.3, the output- and representation-level patterns persist, while DPO degeneracy falls to 10-14%, showing that its severity is model-dependent. Together, CopyShield provides cross-level reference baselines and identifies targeted non-literal suppression as an open challenge. The code is available at https://github.com/spotai-mbzuai/CopyShield.git.

Maryam Alshehyari, Dushyant Singh Chauhan, Samuele Poppi +3

Computing and Mathematical Science Division Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)

LLM Safety BenchmarksDirect Preference OptimizationContrastive DecodingCausal Interventions in Language Models
AskPDF
Aug 31, 2026

PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization

Direct Preference Optimization (DPO) simplifies alignment through pairwise comparisons but assumes all observed preferences are reliable. Real data often violates this assumption, leading to reversed, weak, or ambiguous labels that cause harmful policy updates. To address this, we propose Posterior Label Correction DPO (PLC-DPO) to robustly optimize preferences by routing each pair's training signal as a clean, flip, or tie case. The key idea is to use the calibrated policy-reference margin as online evidence to take appropriate correction actions. This reframes noisy preference learning as actively correcting supervision direction and strength rather than merely filtering suspicious examples. Across 57 dataset-model-benchmark cells, PLC-DPO obtains the best mean win rate against DPO (60.5 vs. 55.5 for the next-best method). Injected-noise and tie stress tests, human disagreement analysis, and self-confirmation diagnostics further show that the routing remains stable and distinguishes flipped from weakly directional pairs.

Boryeong Cho, Sumyeong Ahn, Se-Young Yun

KAIST AI · KENTECH

Pairwise Preference LearningDirect Preference OptimizationPreference AlignmentPreference Learning
AskPDF
Aug 27, 2026

Disentangling Optimization Scale from Preference Scale in DPO

Direct Preference Optimization (DPO) is a widely used objective for aligning language models from preference data, with the coefficient ββ commonly interpreted as controlling the KL constraint to a reference policy. We show that ββ entangles two distinct roles: it governs the effective inverse preference-noise scale and simultaneously rescales the optimization dynamics, coupling this scale with the effective step size. As a consequence, at a fixed learning rate the achieved policy deviation is non-monotone in ββ: it vanishes in a dead zone at small ββ, reaches a peak at an intermediate value, and decreases again for larger ββ. Moreover, standard DPO loss values are not comparable across ββ: runs with nearly identical loss curves can differ several-fold in KL divergence from the reference model. This entanglement obscures the role of ββ, increases sensitivity to hyperparameter choices, and complicates learning-rate scheduling. We propose a centered-softplus reformulation that is argmin-equivalent to DPO for β>0β>0, while making the inverse preference-noise-scale and learning-rate effects explicit and independently tunable. The normalized centered-softplus objective also admits a continuous β→0β\to0 endpoint that reduces to a linear preference-margin objective.

Ivan Kruzhilov

Direct Preference OptimizationPreference LearningDeep Learning OptimizationRL for Language Models
AskPDF
Aug 25, 2026

Preference Optimization for Non-Verbal Vocalization Synthesis

Non-verbal vocalizations (NVs), such as laughter, coughs, and sighs, are essential for expressive TTS, but the effectiveness of preference optimization for NV generation remains poorly understood. We systematically study preference optimization for NV-capable TTS, focusing on preference signals, preference-pair construction, and DPO-based optimization objectives. We formulate an NV-aware character error rate (NV-CER) by treating NV tags as distinct output symbols and computing a weighted pinyin-based CER over both verbal and non-verbal content, enabling controllable optimization of NV realization without modifying the underlying optimization algorithm. Experiments on Emilia-NV and the augmented NV-Bench covering 18 NV types reveal how different design choices affect NV realization and lexical fidelity, and establish an effective setup using standard DPO. Objective, LLM-based, and human evaluations provide converging evidence for our findings, offering practical insights into NV-aware post-training for expressive TTS.

Haoyang Li, Chenglin Xu, Junchuan Zhao +4

Nanyang Technological University, Singapore · LIGHTSPEED, Singapore · National University of Singapore, Singapore +2

Nonverbal Vocalization GenerationPreference OptimizationAudio GenerationDirect Preference OptimizationSpeech Generation Evaluation
AskPDF
Aug 20, 2026

FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Design

Cyclic peptides are emerging as promising molecular scaffolds in drug discovery due to their high binding affinity and structural stability. However, extending generative models from linear to cyclic peptide design remains challenging, as cyclization sharply restricts the feasible design space through coupled geometric and biophysical constraints. Moreover, limited training data has led existing approaches to rely largely on zero-shot generation or post hoc filtering, resulting in low yields of feasible designs and limited control over multi-objective trade-offs. To address these limitations, we propose FAR-DPO (Feasibility-Aware and Robust Direct Preference Optimization), an architecture-agnostic framework that steers generative models toward structurally and biophysically feasible cyclic peptide designs, particularly for challenging targets. FAR-DPO integrates feasibility-aware preference construction with difficulty-aware group-robust optimization. Specifically, it constructs within-target preference pairs through feasibility-gated multi-objective dominance and adaptively reweights predefined difficulty groups according to their current preference losses. On the CPSea LNR benchmark, under a fixed generation budget, FAR-DPO increases overall success rate from 46.89% to 57.79% on PepGLAD and from 47.96% to 49.57% on PepFlow. These gains also extend to the hardest target quartile and are accompanied by more favorable best-per-target binding scores. Together, these results demonstrate FAR-DPO's effectiveness in improving feasibility and target-wise robustness.

Guofeng Zhang, Rong Han, Xiaoyu Wang +4

Beijing University of Posts and Telecommunications, Beijing, China · Shenzhen University, Shenzhen, China · Tsinghua University, Beijing, China

Molecular GenerationConstrained Generative ModelingDirect Preference OptimizationProtein DesignProtein Binder Design
AskPDF
Aug 20, 2026

PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment

Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its adaptation to multimodal settings remains unexplored. Through representational analysis, we identify a key limitation in multimodal preference optimization, which we term visual insensitivity: models often fail to distinguish between images and those with critical visual context removed. Our theoretical analysis further uncovers two manifestations of this problem, namely Across-Image Insensitivity and Within-Image Insensitivity. To address these challenges, we propose Perception-Enhanced Alignment DPO (PEA-DPO), a framework for multimodal LLMs alignment, which explicitly leverages visual preference signals to overcome visual insensitivity. We further provide a theoretical analysis demonstrating that PEA-DPO provably mitigates both failure modes. Empirical results demonstrate that PEA-DPO enhances sensitivity to visual context while preserving the language modeling capacity of the base model. Evaluations across three hallucination benchmarks using MLLMs of varying scales show that PEA-DPO effectively mitigates visual insensitivity, achieves stronger multimodal alignment, and substantially reduces hallucinations.

Jiawei Feng, Jiancan Wu, Xingyu Zhu +3

University of Science and Technology of China Hefei, China · National University of Singapore Kent Ridge, Singapore

Multimodal Large Language ModelsVision-Language AlignmentDirect Preference OptimizationMultimodal Hallucination
AskPDF
Aug 14, 2026

BICPO-VLA: Behavior-Identified Continuation Preference Optimization for Smooth Asynchronous Vision-Language-Action Control

The request-to-handoff gap has three coupled sources: ambiguity about the behavior intended at request time, physical-state drift accumulated during action generation, and residual incompatibility when the new action finally assumes control. BICPO-VLA addresses them in sequence. First, an instruction-aware causal history encoder identifies the behavior supported by the command and current task progress. Second, sequential Haar subspace generation decomposes each action chunk into complementary pairwise scaffold and residual coefficients, enabling two specialized generation stages followed by exact reconstruction. By reducing iterative refinement in the original action space, it shortens the interval over which the robot continues moving before the new chunk becomes available. Finally, BICPO rolls the known outgoing actions to the actual handoff state and applies reference-relative Flow-DPO among behaviorally matched candidates, adapting the generated chunk to the remaining request-to-handoff mismatch without changing its intended behavior.

Ming Shang, Yuchen Huang, Jiaoyang Chen +8

Beihang University, Beijing, China · Beijing Institute of Technology, Beijing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China +4

Vision-Language-Action ModelsEfficient VLA Model InferenceAction ChunkingDirect Preference Optimization
AskPDF
Aug 12, 2026

Context Blindness in DPO: Mitigating Object Hallucination in MLLMs via Context-Calibrated Preference Optimization

Multimodal large language models (MLLMs) have made rapid progress, yet they still exhibit object hallucination, generating plausible but incorrect descriptions that are inconsistent with the visual input. Direct Preference Optimization (DPO) mitigates this by training models to prefer non-hallucinated responses over hallucinated ones, and recent efforts further enrich the preference data with relevant context. However, it remains unclear whether DPO actually leverages such context. To investigate this, we propose Contextual Preference Gain (CPG), a simple metric that measures how much a model's preference strengthens when relevant context is provided. We find that higher CPG consistently corresponds to lower hallucination, yet standard DPO and its variants exhibit only limited CPG, indicating that they underutilize contextual information and thus remain prone to hallucination. To address this, we propose Context-Calibrated DPO (C2^2-DPO), which directly maximizes CPG while preserving the original preference ordering. Across multiple benchmarks, C2^2-DPO substantially reduces hallucination without compromising general reasoning, relatively reducing the Object HalBench hallucination rate of Qwen2-VL-Instruct-2B by 36%. Code is available at https://github.com/mlvlab/C2-DPO

Byungoh Ko, Jinyoung Park, Jongha Kim +3

Korea University, Seoul, Republic of Korea · KAIST, Daejeon, Republic of Korea

Direct Preference OptimizationObject Hallucination in VLMsMultimodal Large Language ModelsVLM Hallucination Mitigation
AskPDF
Aug 12, 2026

Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs

Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs). In this work, we propose Self-Fix Step-DPO (SFS-DPO), a reinforcement learning based, two-stage framework for step-level self-verification and self-correction. The first stage strengthens step-level reasoning via step-level preference optimization, while the second stage explicitly trains models to self-verify and self-correct. We further introduce a teacher-assisted variant, SFS-DPO-R, which incorporates explanatory rationales for error verification to provide stronger corrective signals. Comprehensive in-domain and out-of-domain evaluations across multiple LLMs demonstrate that SFS-DPO and SFS-DPO-R consistently outperform prior step-level training baselines. Our analysis further reveals improvements in self-correction frequency and effectiveness, highlighting the importance of strengthening step-level reasoning for robust performance.

Vu Duc Anh, Nhat M. Hoang, Do Xuan Long +3

Nanyang Technological University, Singapore · National University of Singapore · Institute for Infocomm Research (I2R), A*STAR +1

LLM Self-CorrectionDirect Preference OptimizationRL for Language Model ReasoningLanguage Model Self-Assessment
AskPDF
Aug 10, 2026

Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization

Direct Preference Optimization (DPO) aggregates token-level log-probability ratios via uniform summation, implicitly treating all tokens as contributing equally to the preference signal. However, the contribution of individual tokens to the preference signal varies. We introduce token credit, which modulates each token's KL regularization based on its contribution to the preference outcome. We derive that effective token credit is proportional to the magnitude of each token's implicit reward, and observe that this quantity evolves substantially during training. This implies that static token credit becomes increasingly misaligned as training progresses. In this work, we propose Se-DPO (Self-Evolving Token Credit for DPO), a live mechanism that derives token credit from the model's own evolving internal signals during DPO training. Since the reward signal varies in reliability across positions, Se-DPO calibrates token credit based on both the strength and the confidence of each token's contribution. Se-DPO requires no external models, adding only a lightweight calibration network with minimal computational overhead. Experiments show that Se-DPO improves over DPO by up to 9.8 points on AlpacaEval~2 and 12.2 points on Arena-Hard.

Wenxiao Zhao, Shu Wang, Ying Nian Wu

University of California, Los Angeles · Shanghai AI Laboratory

LLM AlignmentDirect Preference OptimizationToken-Level Credit AssignmentPreference-Based RL
AskPDF
Aug 9, 2026

Linguistically-Aligned and Visually-Grounded Preference Optimization for Clinically-Augmented Medical Report Generation

Despite significant advances in Medical Report Generation (MRG), the reliability remains constrained by the prevalence of factual errors. While Direct Preference Optimization (DPO) has emerged as a promising post-training paradigm to enhance the performance of Supervised Fine-Tuned (SFT) MRG models, existing DPO-based MRG methods typically adopt a naive preference construction that directly pairs model-generated reports with ground truth reports. This strategy inadvertently entangles critical clinical findings with clinically irrelevant linguistic characteristics, and fundamentally lacks explicit vision-language alignment. To address these challenges, we propose DPO-Clin, a novel post-training framework that focuses preference optimization on clinical findings and cross-modal alignment. First, we introduce the Entity-level Clinical Diagnostic (ECD) module to perform a precise entity-level factual diagnosis. ECD guides the generation of linguistically-aligned report preference pairs, isolating clinical discrepancies from linguistic variations. Second, to achieve fine-grained cross-modal alignment, we develop M2DPO, a retrieval-augmented multi-modal DPO variant that enforces textual preference inversion triggered by visual context switches. Third, we locate correct yet highly uncertain predicted entities and apply counterfactual modifications to construct targeted preference data for latent risk mitigation, thereby further enhancing the model reliability. Extensive experiments on two public chest X-ray datasets (MIMIC-CXR and IU X-Ray) and an in-house endoscopy dataset demonstrate that DPO-Clin significantly improves the SFT baselines on clinical-aware metrics. Furthermore, it achieves superior performance over existing DPO-based MRG methods, exhibiting robust generalizability across distinct baseline architectures and diverse medical imaging modalities.

Qiang Hu, Yuxuan Luo, Yingjie Guo +4

Huazhong University of Science and Technology

Radiology Report GenerationMedical Report GenerationDirect Preference OptimizationCross-Modal Alignment
AskPDF
Aug 6, 2026

SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models

Language models for low-resource languages still make frequent grammatical errors. Alignment methods such as RLHF and DPO can correct them. However, they require human judgements, which are scarce for languages such as Icelandic. Automatic rewards offer an alternative, yet models can learn to exploit them without improving (reward hacking). We present SAGA (Score-weighted Adaptive Generation Alignment), which builds preference pairs using dependency parsers. Such parsers already exist for many low-resource languages. SAGA's reward combines parse quality with lexical diversity. It keeps only pairs whose reward gap reaches a threshold and trains on them with DPO. On Danish, Icelandic and Norwegian Bokmål, SAGA raises reward-parser success by 18 to 28 points. It improves all four model families we test, although one Icelandic run is flagged for reward hacking. An independent parser confirms the gains, and native speakers prefer SAGA outputs in Danish (69%) and Icelandic (80%). Online RL methods exploit the Icelandic reward. On the same base model, SAGA scores higher on both parsers. Existing linguistic resources, combined with safeguards against reward hacking, can therefore stand in for human judgements. This makes grammatical alignment possible for the many languages that have parsers but no such data.

Hoda Fakharzadehjahromy, Emil Wiman, Andreas Bueff +2

Linköping University · University of Iceland

LLM AlignmentDirect Preference OptimizationControllable Text GenerationLow-Resource Language Processing
AskPDF
Aug 5, 2026

Positive-Unlabeled Preference Optimization For Chest X-ray Report Generation

Vision-Language Models (VLMs) for radiology report generation are typically trained on retrospective clinical reports, which suffer from omission noise: clinically present findings are left unreported due to the omission of subtle findings. For example, prior studies show that cardiomegaly may be omitted from ICU chest X-ray reports when the imaging request is focused on monitoring support device placement. As a result, models trained with standard approaches inherit these omissions, learning to under-report findings themselves. We propose PU-DPO, a preference optimization framework to prevent omission noise from corrupting the preference signal. We reformulate the objective under a positive-unlabeled (PU) learning framework, treating absent mentions as unlabeled rather than truly negative. Our framework provides preference supervision using constructed contrastive pairs, generated using edits to model responses, producing variants that explicitly mention or omit a specific finding. Generated responses that mention the finding are naturally preferred in the context of visual evidence. Across semi-synthetic experiments and analyses on real-world chest radiograph benchmarks where adjudicated labels are available, PU-DPO yields consistent gains in detection rates and recovery of hidden positives across multiple pathologies, and is more robust to omission noise than prior approaches.

Yuta Kobayashi, Pradyun Ramesh, Muhammad Ahmed Chaudhry +5

Columbia University · Stanford University · Emory University

Radiology Report GenerationRadiology VLMsDirect Preference OptimizationPositive-Unlabeled Learning
AskPDF
Aug 2, 2026

AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimization

Vision-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) requires rapid and reactive control in complex 3D environments. Recent minimalist end-to-end paradigms show great promise but typically rely on massive language models containing billions of parameters, incurring prohibitive latency for real-world edge deployment. In this paper, we challenge this parameter-heavy reliance. Comprehensive cross-scale evaluations reveal the critical insight that perception quality fundamentally outweighs language reasoning capacity. We demonstrate that a lightweight 2B model equipped with high-fidelity visual inputs completely matches the overall success rates of massive 7B baselines. However, this minimalist policy exposes a fundamental robustness flaw inherent to pure Behavior Cloning (BC). Lacking explicit negative feedback, the agent fails to internalize robust spatial constraints and exhibits alarming collision rates in out-of-distribution (OOD) scenarios. To overcome this vulnerability without relying on unscalable human annotations, we propose AeroDPO, a zero-cost automated Direct Preference Optimization pipeline driven by deterministic physical simulation state rollback. Upon detecting collisions, the system autonomously rewinds the environment to extract causal reasoning errors as rejected actions, applies decoupled privileged interventions to synthesize collision-avoidance preferred maneuvers, and leverages an offline vision language inspector to filter visual ambiguities. By equipping our 2B model with this automated data flywheel, AeroDPO boosts success rates to 49.16% on unmapped scenarios while drastically suppressing collision rates, establishing a new SOTA for autonomous aerial agents.

Peng Xu, Chengcheng Wang, Shaohua Wan

University of Electronic Science and Technology of China, Chengdu, China · 2Shenzhen Institute for Advanced Study, UESTC, Shenzhen, China

Collision AvoidanceDirect Preference OptimizationUAV NavigationVision-Language NavigationAerial VLN
AskPDF
Jul 30, 2026

Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing

In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that can fail in two opposite ways: capitulation (abandoning the change agenda to preserve rapport) or confrontation (arguing or directing, overriding the client's autonomy). We introduce a two-axis evaluation of counselor responses, anchored in the Motivational Interviewing Treatment Integrity (MITI) code, Goal Persistence (GP) and Relational Attunement (RA), yielding a four-quadrant framing in which rolling with resistance is high on both, and we ask whether penalizing one failure through preference optimization teaches rolling with resistance or provokes its opposite. From the expert-annotated AnnoMI corpus we build topic-disjoint Direct Preference Optimization data whose preference sets differ only in which failure is rejected, using on-policy negatives. An automatic judge, validated against AnnoMI's expert labels and rechecked by trained human coders, scores blind pairwise win-rates against each base under a firewall in which disjoint model families generate, label, and judge. Across three aligned instruction models spanning the Qwen and Llama families, penalizing confrontation reliably lowers goal persistence below parity, on every base and in every seed run, a robust cost, whereas the attunement gain is base-dependent, present on two of the three bases but absent on the third. Penalizing capitulation is inert, because these models rarely capitulate on-policy, so the trade is gated by each base's failure profile. A prompt-only control raises attunement without the goal-persistence cost, locating the cost in the optimization rather than in attunement itself.

Weiying Chen, Junlong Shen, Zhexuan Tang

University of Alberta · University of Shanghai for Science and Technology

Direct Preference OptimizationPreference Optimization
AskPDF
Jul 29, 2026

TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking

Entity linking in tables matches short and ambiguous cell mentions to their corresponding knowledge-base entities. Existing approaches typically rely on data preprocessing pipelines that retain either compact or extensive table content as contextual evidence, and then formulate entity linking as a language generation task for instruction-tuned models; recent systems further incorporate explicit reasoning to disambiguate challenging mentions. However, their training supervision is usually static: fixed preference data cannot adapt to the residual errors of an evolving model, while variations in reasoning length can bias sequence-level preference learning. To address these limitations, we present TELLER: Table Entity Linking through Learning from Errors and Reasoning. We first retrieve and rank Wikidata candidates and retain reduced table evidence in the prompt. The direct-answer path applies iterative direct preference optimization and refreshes its preference data with residual errors from the updated model. The reasoning path uses filtered and compressed chain-of-thought rationales for supervised fine-tuning, followed by our iterative length-normalized regularized preference optimization. On the TableInstruct entity-linking subset, the direct-answer path improves accuracy from 94.35% to 94.50%; on the MammoTab V2 evaluation set, it improves accuracy from 87.59% to 88.20%. The reasoning path improves accuracy from 92.90% to 92.95% on TableInstruct and from 79.09% to 81.85% on MammoTab V2, while maintaining high rates of complete reasoning generation. These results show that iterative preference learning benefits both concise entity prediction and explicit reasoning.

Yixin Peng, Kehao Li, Stefan Decker

RWTH Aachen, Ahornstraße 55, 52074 Aachen, Germany

Direct Preference OptimizationPreference OptimizationLLM Information ExtractionEntity Linking
AskPDF
Jul 20, 2026

SciForma: Structure-Faithful Generation of Scientific Diagrams

Structural fidelity is essential to scientific methodology diagrams. To communicate research logic, these diagrams must faithfully render components, directional relations, and textual annotations. Since a single error, such as a reversed arrow or an unreadable equation, can invalidate the entire figure, structural fidelity is inherently conjunctive: correctness on one axis cannot compensate for failure on another. Current open-source models fail to satisfy this criterion. Supervised fine-tuning (SFT) learns plausible layouts but cannot reliably ensure structural correctness, while scalar reward-based post-training obscures which structural dimension has failed. To address this, we introduce SciForma, a framework for the structure faithful generation of scientific methodology diagrams. Specifically, SciForma decomposes diagram quality into three structural axes: Component, Arrow, and Text, guided by a structural inventory. Built on this foundation, we curate SciFormaData-700K for structured training and SciFormaBench-2K for logic-verified evaluation. To close the gap left by SFT, we develop Multi-Dimensional Conjunctive Preference Optimization (M-DPO), which enforces simultaneous correctness across all axes and adaptively routes gradients to the most deficient dimension in post-training. The same structural inventory also enables iterative editing at inference time to correct residual errors. This combination allows SciForma-9B to exceed all open-source baselines and GPT-Image-1.5 on both SciFormaBench-2K and AIBench, bringing open scientific diagram generation close to proprietary-level structural fidelity. Our code and data will be available at: https://github.com/microsoft/SciForma.

Yuxuan Luo, Peng Zhang, Xinjie Zhang +3

Wangxuan Institute of Computer Technology, Peking University, China · State Key Lab of CAD & CG, Zhejiang University, China · Microsoft Research Asia

Scientific VisualizationDirect Preference Optimization
AskPDF
Jul 18, 2026

When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Video Generation

Text-to-video (T2V) generation models have achieved strong visual realism, but improving physical plausibility can come at the cost of semantic consistency with the input text. This tension arises because physical preference is typically determined by comparing dynamics between two videos, without accounting for whether either video faithfully depicts the scene specified by the prompt, making physical-semantic conflict a systematic tendency under this supervision paradigm. We formulate this challenge as a constrained preference optimization problem and propose Physical and Semantic Direct Preference Optimization (PSDPO), which modulates each preference pair's contribution based on the agreement between its physical and semantic signals. A gradient-level analysis shows that PSDPO bounds the semantic drift from conflicting pairs to a controllable residual, and further motivates a staged optimization protocol that provably reduces cumulative drift. The resulting method operates entirely within the standard DPO framework, requiring no auxiliary models or additional loss terms. Experiments show that PSDPO improves physical plausibility by up to 2×2\times over the baseline on VideoPhy-2, while maintaining strong semantic consistency on VBench, achieving a more reliable balance than existing preference-based methods.

Siwei Meng, Yawei Luo, Shu Zhang +1

Computer Science and Engineering · University of Nevada, Reno · Reno, NV, USA +5

Physical Consistency in Video GenerationDirect Preference OptimizationT2V GenerationVision-Language Alignment
AskPDF
Jul 17, 2026

TD-DPO: Difference-Aware Preference Optimization for Mitigating Sycophancy in Clinical Autism Intervention Dialogue

The sycophancy of large language models can increase the safety risk in intervention dialogue for autistic children. Supervised fine-tuning can somewhat reduce sycophancy, but relying solely on positive examples is often insufficient to identify and correct failure patterns. We observe that sycophancy behaviors can often be localized to a limited span within the model response. In this regime, sequence-level preference optimization can over-update preference-irrelevant tokens and degrade intervention ability. To address this, we propose the Minimal Edit Data Augmentation (MEDA) strategy to construct controlled, stable, minimal edit preference pairs and Token-level Difference Direct Preference Optimization (TD-DPO), which upweights difference tokens between chosen and rejected responses while downweighting shared tokens to suppress background drift. Extensive experiments across multiple backbones and evaluators show that TD-DPO achieves a better trade-off between sycophancy mitigation and intervention ability retention in our offline settings, highlighting its potential as a practical alignment approach for autism intervention.

Shuzhong Lai, Junhong Lai, Chenxi Li +5

1Nanhu Brain-Computer Interface Institute · 2MOE Frontiers Science Center for Brain and Brain-Machine Integration, Zhejiang University · College of Computer Science and Technology, Zhejiang University +3

LLM SycophancyDirect Preference OptimizationLLM Safety AlignmentPreference Optimization
AskPDF
Jul 13, 2026

Direct Image-to-Modern Vietnamese Translation of Han-Nom Manuscripts via Multimodal RLHF Preference Alignment

Translating Han-Nom manuscripts into modern Vietnamese is challenging because historical pages are often degraded, the script contains rare logographic characters, and parallel supervision is limited. We propose a multimodal RLHF preference-alignment framework that conditions Vietnamese generation on manuscript images and aligned Han-Nom source text. The model combines four streams: CLIP ViT-L/14@336 for visual features, bert-base-chinese for Han-Nom representations, vinai/phobert-base for Vietnamese representations, and T5-small encoder states. Modality-specific projections and a fusion block compress the resulting 2,048-dimensional concatenation into a shared 512-dimensional representation. Starting from the same supervised fine-tuned policy, we compare PPO, DPO, and KTO under matched work-level macro-averaged evaluation. DPO achieves the best BLEU-4, ROUGE-L, BERTScore, semantic similarity, CER, WER, and token accuracy, whereas PPO obtains the highest precision, recall, and F1. KTO remains competitive through its desirable-undesirable utility objective. All preference-aligned policies improve the BLEU-4 and semantic-similarity scores available for the SFT baseline. These results indicate that multimodal preference optimization complements supervised learning by improving lexical and semantic quality in low-resource historical translation.

Thi Kim Trang Vo, Nghia Hieu Nguyen, Ha Minh Tan

University of Information Technology, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam

Direct Preference OptimizationPreference OptimizationMultimodal MTMachine TranslationMultimodal Learning
AskPDF
Jul 12, 2026

Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories

Large Language Model (LLM) agents are commonly trained from expert trajectories using supervised fine-tuning (SFT), which treats multi-turn agent behavior as ordinary text imitation. This recipe is simple and low-cost, but it only learns to imitate the sequence of expert actions, rather than training the agent to choose the right action against plausible mistakes at each state. Existing methods to mitigate this problem include preference learning or reinforcement learning, but they usually need high-cost environment rollouts and reward models. We propose Agentic-DPO, a lightweight offline agent policy optimization method that turns expert trajectories into state-conditioned preference supervision. At each expert action state, Agentic-DPO samples a one-step action from the current state, treats plausible wrong actions as negatives, and contrasts them with the expert action using a DPO-style preference objective. To avoid mixing both policy and schema in preference learning, we introduce Policy-Preserving Augmentation (PPA), which renders the same latent trajectory under multiple schemas while keeping the expert policy fixed. Agentic-DPO requires no online environment rollout, reward model, or full-trajectory student exploration. We conduct experiments across StableToolBench, tau-bench retail, and Mind2Web, where Agentic-DPO consistently improves agents at different model scales beyond imitation. In particular, it raises tau-bench accuracy from 21.7% (SFT) to 41.4% for a 9B model, matching online GRPO under the same backbone with only step-level rollouts and without environment interaction during gradient steps. The results suggest that expert trajectories can support low-cost agentic policy optimization when converted from demonstrations into state-level action preferences. Code for Agentic-DPO is released at https://github.com/Schuture/Agentic-DPO.

Yixiong Chen, Alan Yuille

Johns Hopkins University

Direct Preference OptimizationLLM AgentsLLM Agent TrainingOffline Preference Optimization
AskPDF
Jul 9, 2026

Metadata-Free Meta-Reweighted Direct Preference Optimization under Noisy Preference Labels

Direct Preference Optimization (DPO) has become an important method for aligning large language models (LLMs) with human preferences because it removes the need for explicit reward modeling and reinforcement learning optimization. However, its performance depends heavily on the quality of preference data, and noisy preference data in real-world settings can weaken alignment performance. To address this issue, we propose a bilevel optimization framework and prove, under certain assumptions, that this framework can recover the DPO optimum under clean data. We further derive a prior form for the learnable weighting function under asymmetric label-flipping noise. Considering that high-quality metadata may be difficult to obtain, we propose a task-agnostic meta-knowledge-driven method that enables meta-learning even when metadata is completely unavailable. To reduce the high cost of higher-order gradients in LLM meta-learning, we combine central-difference approximation with LoRA fine-tuning and develop a scalable training scheme. Experiments on TL;DR summarization and Anthropic HH single-turn dialogue show that the proposed method improves training performance over multiple DPO baselines under different noise rates.

Hua Qu, Yifan Li, Xiaodong Yuan

Xi’an Jiaotong University

LLM AlignmentMeta-LearningDirect Preference OptimizationNoisy-Label Learning
AskPDF
Jul 7, 2026

D2PO: Optimizing Diffusion Samplers via Dynamic Preference

We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diffusion sampling policies with respect to timestep schedules and classifier-free guidance (CFG) weights. Our work is motivated by a fundamental limitation of existing student-teacher regression frameworks; low-NFE student samplers are trained to mimic high-NFEteachers, often sacrificing high-frequency texture fidelity while preserving coarse global structures, thereby misaligning the sampler with perceptual quality. D2PO addresses this challenge by reformulating sampler optimization as a preference-based alignment problem, leveraging the Direct Preference Optimization (DPO) framework. To make DPO applicable to diffusion samplers, we model the sampling policy as an energy-based model (EBM), transforming preference comparisons into tractable energy differences. We further introduce a novel energy formulation derived directly from the pretrained score network, enabling preference evaluation in perturbed spaces that jointly capture structural consistency and fine-grained details. Moreover, we introduce dynamic preferences, where the preferred samples used for alignment progressively improve as the sampling policies are learned. This self-improving mechanism replaces rigid static teacher supervision with an iterative, preference-guided refinement process, providing progressively stronger alignment signals. Extensive experiments demonstrate that D2PO aligns diffusion samplers with perceptual quality more faithfully, unlocking the full potential of high-quality teachers and consistently outperforming conventional regression-based schedulers under low-NFE constraints.

Jinkyu Kim, Jinyoung Choi, Bohyung Han

1ECE & 2IPAI, Seoul National University, Korea · 3AIGS, Ulsan National Institute of Science and Technology, Korea

Diffusion Model AlignmentDirect Preference OptimizationDiffusion GuidanceDiffusion SamplingFew-Step Diffusion SamplingDiffusion Timestep Scheduling
AskPDF