Home Knowledge Base Using Direct Preference Optimization

Using Direct Preference Optimization

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Backtranslation Augmented Direct Preference Optimization for Neural Machine Translation

arXiv:2604.25702v2 Announce Type: replace Abstract: Contemporary neural machine translation (NMT) systems are almost exclusively built by training on supervised parallel data. Despite the tremendous progress achieved, these systems still exhibit persistent translation errors. This paper proposes that a post-training paradigm based on reinforcement learning (RL) can effectively rectify such mistakes.

arXiv CS 8d ago

Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization

arXiv:2510.05342v2 Announce Type: replace Abstract: Direct Preference Optimization (DPO) has emerged as a simple and effective method for aligning large language models. However, its reliance on a fixed temperature parameter leads to suboptimal training on diverse preference data, causing overfitting on easy examples and under-learning from informative ones. Recent methods have emerged to counter this.

arXiv CS 8d ago

S-SPPO: Semantic-Calibrated Self-Play Preference Optimization

arXiv:2606.01561v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human preferences is often formulated via Direct Preference Optimization (DPO). However, the standard Bradley-Terry instantiation of DPO is limited in modeling common departures from transitivity in human preferences. To address this, recent work has introduced Self-Play Preference Optimization (SPPO), which iteratively refines the policy by training on self-generated win-lose pairs.

arXiv CS 8d ago

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

arXiv:2605.11134v2 Announce Type: replace Abstract: 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...

arXiv CS 9d ago

Drifting Preference Optimization for One-Step Generative Models

Announce Type: new Abstract: One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step generators. For each prompt,...

arXiv CS 8d ago

Drifting Preference Optimization for One-Step Generative Models

arXiv:2606.02521v3 Announce Type: replace Abstract: One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step...

arXiv CS 6d ago

Drifting Preference Optimization for One-Step Generative Models

arXiv:2606.02521v2 Announce Type: replace Abstract: One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step...

arXiv CS 7d ago

Macro: Enhancing Multilingual Counterfactual Explanations through Alignment-as-Preference Optimization

Announce Type: replace Abstract: Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains challenging: existing methods struggle to produce valid SCEs in non-dominant languages, and a persistent trade-off between validity and minimality undermines...

arXiv CS 5d ago

Letting Tutor Personas Speak Up for LLMs: Learning Steering Vectors from Dialogue via Preference Optimization

arXiv:2602.07639v2 Announce Type: replace Abstract: With the emergence of large language models (LLMs) as a powerful class of generative artificial intelligence (AI), their use in tutoring has become increasingly prominent. Prior works on LLM-based tutoring typically learn a single tutor policy and do not capture the diversity of tutoring styles. In real-world tutor-student interactions, pedagogical intent is realized through adaptive instructional strategies, with tutors varying the level...

arXiv CS 7d ago

Follow-Your-Preference++: Rethinking Preference Alignment for Image Inpainting

Announce Type: new Abstract: We study preference alignment for image inpainting. Rather than proposing yet another method, we revisit the problem from first principles and reassess its core challenges. We adopt the widely used direct preference optimization framework and construct preference training data with publicly available reward models.

arXiv CS 7d ago