Related papers: Forward versus Backward: Comparing Reasoning Objec…

Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

Direct preference optimization (DPO) is a form of reinforcement learning from human feedback (RLHF) where the policy is learned directly from preferential feedback. Although many models of human preferences exist, the critical task of…

Preference learning extends the performance of Code LLMs beyond traditional supervised fine-tuning by leveraging relative quality comparisons. In existing approaches, a set of n candidate solutions is evaluated based on test case success…

Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative to approaches that use Reinforcement learning via Human…

Aligning large language models (LLMs) with human preferences in federated learning (FL) is challenging due to decentralized, privacy-sensitive, and highly non-IID preference data. Direct Preference Optimization (DPO) offers an efficient…

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…

Direct Alignment Algorithms (DAAs), such as Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO), have emerged as efficient alternatives to Reinforcement Learning from Human Feedback (RLHF) algorithms for aligning…

Direct Preference Optimization (DPO) has proven effective at improving the performance of large language models (LLMs) on downstream tasks such as reasoning and alignment. In this work, we propose Step-Controlled DPO (SCDPO), a method for…

Large Reasoning Models (LRMs) achieve explicit chain-of-thought expansion by imitating deep thinking behaviors of humans, demonstrating excellent performance in complex task scenarios. However, the deep-thinking mode often leads to…

Direct Preference Optimization (DPO) and its variants have become increasingly popular for aligning language models with human preferences. These methods aim to teach models to better distinguish between chosen (or preferred) and rejected…

Goals for reinforcement learning problems are typically defined through hand-specified rewards. To design such problems, developers of learning algorithms must inherently be aware of what the task goals are, yet we often require agents to…

Direct Preference Optimization (DPO) has emerged as a prominent algorithm for the direct and robust alignment of Large Language Models (LLMs) with human preferences, offering a more straightforward alternative to the complex Reinforcement…

Recent advances in generative vision-language models (VLMs) have exciting potential implications for AI in radiology, yet VLMs are also known to produce hallucinations, nonsensical text, and other unwanted behaviors that can waste…

Recently, preference optimization methods such as DPO have significantly enhanced large language models (LLMs) in wide tasks including dialogue and question-answering. However, current methods fail to account for the varying difficulty…

Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. In particular, batch packing is commonly used in pre-training and supervised fine-tuning…

Existing work has shown that o1-level performance can be achieved with limited data distillation, but most existing methods focus on unidirectional supervised fine-tuning (SFT), overlooking the intricate interplay between diverse reasoning…