Related papers: Calibrated Multi-Preference Optimization for Align…

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means…

Current alignment pipelines presume a single, universal notion of desirable behavior. However, human preferences often diverge across users, contexts, and cultures. As a result, disagreement collapses into the majority signal and minority…

Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability. To…

This paper introduces V2A-DPO, a novel Direct Preference Optimization (DPO) framework tailored for flow-based video-to-audio generation (V2A) models, incorporating key adaptations to effectively align generated audio with human preferences.…

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date. Despite their success, existing methods…

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play…

Diffusion models have become a central paradigm for image and multimodal generation, yet their deployment raises persistent questions about alignment, safety, preference satisfaction, and robustness to misuse. This survey reviews recent…

Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However, DPO requires high-quality preference data and suffers from…

Inference-time alignment provides an efficient alternative for aligning LLMs with humans. However, these approaches still face challenges, such as limited scalability due to policy-specific value functions and latency during the inference…

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm…

We study an LLM fine-tuning task for designing reward functions for sequential resource allocation problems in public health, guided by human preferences expressed in natural language. This setting presents a challenging testbed for…

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces…

In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…

Direct preference optimization (DPO) is a successful fine-tuning strategy for aligning large language models with human preferences without the need to train a reward model or employ reinforcement learning. DPO, as originally formulated,…

Offline multi-objective optimization aims to identify Pareto-optimal solutions given a dataset of designs and their objective values. In this work, we propose a preference-guided diffusion model that generates Pareto-optimal designs by…

Diffusion models excel at generating images conditioned on text prompts, but the resulting images often do not satisfy user-specific criteria measured by scalar rewards such as Aesthetic Scores. This alignment typically requires…

Aligning Diffusion models has achieved remarkable breakthroughs in generating high-quality, human preference-aligned images. Existing techniques, such as supervised fine-tuning (SFT) and DPO-style preference optimization, have become…

Enhancing the conformity of large language models (LLMs) to human preferences remains an ongoing research challenge. Recently, offline approaches such as Direct Preference Optimization (DPO) have gained prominence as attractive options due…

Recent works have demonstrated that using reinforcement learning (RL) with multiple quality rewards can improve the quality of generated images in text-to-image (T2I) generation. However, manually adjusting reward weights poses challenges…