相关论文: Towards Harmless Multimodal Assistants with Blind …

Evaluating preference optimization (PO) algorithms on LLM alignment is a challenging task that presents prohibitive costs, noise, and several variables like model size and hyper-parameters. In this work, we show that it is possible to gain…

Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reasoning in LLMs, applying it to MLLMs is tricky. Common issues…

Though reasoning abilities are considered language-agnostic, existing LLMs exhibit inconsistent reasoning abilities across different languages, e.g., reasoning in the dominant language like English is superior to other languages due to the…

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…

LLM generated code often contains security issues. We address two key challenges in improving secure code generation. First, obtaining high quality training data covering a broad set of security issues is critical. To address this, we…

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 model context protocol (MCP) has been widely adapted as an open standard enabling the seamless integration of generative AI agents. However, recent work has shown the MCP is susceptible to retrieval-based "falsely benign" attacks…

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…

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…

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…

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…

We study an LLM fine-tuning task for designing reward functions for sequential resource allocation problems in public health, guided by human preferences expressed in natural language. This setting presents a challenging testbed for…

Aligning large language models (LLMs) is a central objective of post-training, often achieved through reward modeling and reinforcement learning methods. Among these, direct preference optimization (DPO) has emerged as a widely adopted…

Smart contract vulnerability detection remains a major challenge in blockchain security. Existing vulnerability detection methods face two main issues: (1) Existing datasets lack comprehensive coverage and high-quality explanations for…

Large Language Models (LLMs) have demonstrated remarkable capabilities through pretraining and alignment. However, superior short-context LLMs may underperform in long-context scenarios due to insufficient long-context alignment. This…

Large reasoning models (LRMs) generate intermediate reasoning traces before producing final answers, yielding strong gains on multi-step and mathematical tasks. Yet aligning LRMs with human preferences, a crucial prerequisite for model…

Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallucinations. Existing training-based methods typically…

Recent advances in large vision-language models (LVLMs) have shown promise for embodied task planning, yet they struggle with fundamental challenges like dependency constraints and efficiency. Existing approaches either solely optimize…

In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…