Related papers: Towards Robust Alignment of Language Models: Distr…
Direct Preference Optimization (DPO) demonstrates the advantage of aligning a large language model with human preference using only an offline dataset. However, DPO has the limitation that the KL penalty, which prevents excessive deviation…
Aligning text-to-image (T2I) diffusion models with Direct Preference Optimization (DPO) has shown notable improvements in generation quality. However, applying DPO to T2I faces two challenges: the sensitivity of DPO to preference pairs and…
The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize the expected reward that reflects human preferences.…
Direct Preference Optimization (DPO), which aligns models with human preferences through win/lose data pairs, has achieved remarkable success in language and image generation. However, applying DPO to video diffusion models faces critical…
Direct Preference Optimization (DPO) has emerged as an important approach for learning from human preferences in aligning large language models (LLMs). However, collecting human preference data is costly and inefficient, motivating methods…
Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…
Aligning large language models (LLMs) with human preferences is commonly done via reinforcement learning from human feedback (RLHF) with Proximal Policy Optimization (PPO) or, more simply, via Direct Preference Optimization (DPO). While DPO…
Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have…
Reinforcement learning from human feedback (RLHF) has been extensively employed to align large language models with user intent. However, proximal policy optimization (PPO) based RLHF is occasionally unstable requiring significant…
When fine-tuning pre-trained Large Language Models (LLMs) to align with human values and intentions, maximizing the estimated reward can lead to superior performance, but it also introduces potential risks due to deviations from the…
Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…
Many algorithms for aligning LLMs with human preferences assume that human preferences are binary and deterministic. However, human preferences can vary across individuals, and therefore should be represented distributionally. In this work,…
Large Language Models (LLMs) tend to respond correctly to prompts that align well with the data they were trained and fine-tuned on. Yet, small shifts in wording, format, or language can trigger surprisingly large failures, especially on…
Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are…
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 advancements in human preference optimization, initially developed for Language Models (LMs), have shown promise for text-to-image Diffusion Models, enhancing prompt alignment, visual appeal, and user preference. Unlike LMs,…
Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can lead to biased model updates and suboptimal performance…
Large language model reasoning is often treated as a monolithic capability, relying on binary preference supervision that fails to capture partial progress or fine-grained reasoning quality. We introduce Continuous Utility Direct Preference…
Direct Preference Optimization (DPO) is an effective technique that leverages pairwise preference data (usually one chosen and rejected response pair per user prompt) to align LLMs to human preferences. In practice, multiple responses can…
Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be systematically biased compared to high-quality human feedback…