Related papers: sDPO: Don't Use Your Data All at Once

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

Direct Preference Optimization (DPO) is widely utilized in the Reinforcement Learning from Human Feedback (RLHF) phase to align Large Language Models (LLMs) with human preferences, thereby enhancing both their harmlessness and efficacy.…

With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from Human Feedback (RLHF) has been adopted to enhance the…

Safety and trustworthiness are indispensable requirements for real-world applications of AI systems using large language models (LLMs). This paper formulates human value alignment as an optimization problem of the language model policy to…

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…

We study the post-training of large language models (LLMs) with human preference data. Recently, direct preference optimization and its variants have shown considerable promise in aligning language models, eliminating the need for reward…

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.…

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human…

Fine-tuning is integral for aligning large language models (LLMs) with human preferences. Multiple-Reference Preference Optimization (MRPO) builds on Direct Preference Optimization (DPO) by fine-tuning LLMs on preference datasets while…

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…

General-purpose large language models (LLMs) have demonstrated remarkable generative and reasoning capabilities but remain limited in healthcare and caregiving applications due to two key deficiencies: factual unreliability and a lack of…

Language model alignment is crucial for ensuring that large language models (LLMs) align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential…

Direct Preference Optimization (DPO) has recently emerged as a simple and effective alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with user preferences. However, existing DPO…

The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides strong performance, the standard imitation objective may not fully capture the complex…

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference…

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with…

Direct preference optimization (DPO) is widely used as a simple and stable method for aligning large language models (LLMs) with human preferences. This paper investigates a generalized DPO loss that enables a policy model to match the…

Large Vision-Language Models (LVLMs) hold immense potential for complex multimodal instruction following, yet their development is often hindered by the high cost and inconsistency of human annotation required for effective fine-tuning and…

Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and non-preferred responses. In practice, user feedback on such…

Large Language Models (LLMs) can become outdated over time as they may lack updated world knowledge, leading to factual knowledge errors and gaps. Knowledge Editing (KE) aims to overcome this challenge using weight updates that do not…