Related papers: Atomic Consistency Preference Optimization for Lon…
Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely…
Advancements in large language models (LLMs) have demonstrated remarkable capabilities across a diverse range of applications. These models excel in generating text completions that are contextually coherent and cover an extensive array of…
Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…
Offline preference optimization offers a simpler and more stable alternative to RLHF for aligning language models. However, their effectiveness is critically dependent on ranking accuracy, a metric where further gains are highly impactful.…
While Audio-Visual Language Models (AVLMs) have achieved remarkable progress over recent years, their reliability is bottlenecked by cross-modal hallucination. A particularly pervasive manifestation is video-driven audio hallucination:…
While learning to align Large Language Models (LLMs) with human preferences has shown remarkable success, aligning these models to meet the diverse user preferences presents further challenges in preserving previous knowledge. This paper…
How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a…
The rapid development of large language model (LLM) alignment algorithms has resulted in a complex and fragmented landscape, with limited clarity on the effectiveness of different methods and their inter-connections. This paper introduces…
Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong…
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…
Direct alignment methods are increasingly used for aligning large language models (LLMs) with human preferences. However, these methods suffer from the issues of verbosity and likelihood displacement, which can be driven by the noisy…
The recent success in using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks, such as question answering, mathematical reasoning, and code generation. However,…
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…
Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and (2) reliance on auxiliary reward/reference models…
Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…
In abstractive summarization, the challenge of producing concise and accurate summaries arises from the vast amount of information contained in the source document. Consequently, although Large Language Models (LLMs) can generate fluent…
Preference alignment is an essential step in adapting large language models (LLMs) to human values, but existing approaches typically depend on costly human annotations or large-scale API-based models. We explore whether a weak LLM can…
Moderate-sized large language models (LLMs) -- those with 7B or 13B parameters -- exhibit promising machine translation (MT) performance. However, even the top-performing 13B LLM-based translation models, like ALMA, does not match the…
Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO), one of the most popular approaches, formulates RLHF as a…
We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer,…