Related papers: CHiP: Cross-modal Hierarchical Direct Preference O…

Large Language Models (LLMs) have demonstrated remarkable potential in automating software development tasks. While recent advances leverage Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) to align models with human…

Multimodal large language models (MLLMs) have recently shown significant advancements in video understanding, excelling in content reasoning and instruction-following tasks. However, hallucination, where models generate inaccurate or…

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

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…

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of…

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…

Multimodal Large Language Models (MLLMs) excel in generating responses based on visual inputs. However, they often suffer from a bias towards generating responses similar to their pretraining corpus, overshadowing the importance of visual…

Hallucinations in large language models (LLMs) present a growing challenge across real-world applications, from healthcare to law, where factual reliability is essential. Despite advances in alignment and instruction tuning, LLMs can still…

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

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…

This paper presents Perceptual Preference Optimization (PerPO), a perception alignment method aimed at addressing the visual discrimination challenges in generative pre-trained multimodal large language models (MLLMs). To align MLLMs with…

Recent alignment methods based on Direct Preference Optimization (DPO) reformulate preference learning as supervised optimization over pairwise comparisons, offering improved efficiency and stability over reinforcement learning from human…

Most Video Large Language Models (Video-LLMs) adopt preference alignment techniques, e.g., DPO~\citep{rafailov2024dpo}, to optimize the reward margin between a winning response ($y_w$) and a losing response ($y_l$). However, the likelihood…

Large Language Models (LLMs) have exhibited remarkable performance across a wide range of domains, motivating research into their potential for recommendation systems. Early efforts have leveraged LLMs' rich knowledge and strong…

Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models. However, there is no clear conclusion as to which part of the model…

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and…

Direct preference optimization (DPO), a widely adopted offline preference optimization algorithm, aims to align large language models (LLMs) with human-desired behaviors using pairwise preference data. However, the generation of the winning…

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Multimodal Large Language Models (MLLMs) achieve strong performance on tasks like image captioning and visual question answering, but remain prone to hallucinations, where generated text conflicts with the visual input. Prior work links…

We study the problem of aligning large language models (LLMs) with human preference data. Contrastive preference optimization has shown promising results in aligning LLMs with available preference data by optimizing the implicit reward…