Related papers: Value-Conflict Diagnostics Reveal Widespread Align…

Large language models (LLMs) are increasingly adopted in clinical decision support, yet aligning them with the multifaceted reasoning pathways of real-world medicine remains a major challenge. Using more than 8,000 infertility treatment…

Vision-Language Models (VLMs) excel in integrating visual and textual information for vision-centric tasks, but their handling of inconsistencies between modalities is underexplored. We investigate VLMs' modality preferences when faced with…

Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs…

Existing research primarily evaluates the values of LLMs by examining their stated inclinations towards specific values. However, the "Value-Action Gap," a phenomenon rooted in environmental and social psychology, reveals discrepancies…

Reasoning Vision Language Action (VLA) models improve robotic instruction-following by generating step-by-step textual plans before low-level actions, an approach inspired by Chain-of-Thought (CoT) reasoning in language models. Yet even…

AI support of collaborative interactions entails mediating potential misalignment between interlocutor beliefs. Common preference alignment methods like DPO excel in static settings, but struggle in dynamic collaborative tasks where the…

AI Alignment, primarily in the form of Reinforcement Learning from Human Feedback (RLHF), has been a cornerstone of the post-training phase in developing Large Language Models (LLMs). It has also been a popular research topic across various…

We present the first systematic study of faithfulness in Vision-Language-Action (VLA) driving models, analyzing 300 Alpamayo-R1-10B inferences across 100 diverse PhysicalAI-AV scenarios. Our main finding is that output natural-language…

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

Current alignment evaluation mostly measures whether models encode dangerous concepts and whether they refuse harmful requests. Both miss the layer where alignment often operates: routing from concept detection to behavioral policy. We…

Vision-Language-Action (VLA) models have emerged as a promising framework that unifies perception, reasoning, and control for robot manipulation by adapting pretrained vision-language models (VLMs) to action prediction. However, VLM-derived…

With the wide application of large language models (LLMs), the problems of bias and value inconsistency in sensitive domains have gradually emerged, especially in terms of race, society and politics. In this paper, we propose an adversarial…

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…

Aligning Large Language Models (LLMs) is crucial for enhancing their safety and utility. However, existing methods, primarily based on preference datasets, face challenges such as noisy labels, high annotation costs, and privacy concerns.…

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are…

Large Language Models (LLMs) interact with millions of people worldwide in applications such as customer support, education and healthcare. However, their ability to produce deceptive outputs, whether intentionally or inadvertently, poses…

Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies have explored sycophantic behavior in general contexts, its impact on…

Large language models (LLMs) exhibit cultural bias from overrepresented viewpoints in training data, yet cultural alignment remains a challenge due to limited cultural knowledge and a lack of exploration into effective learning approaches.…

Recent studies on the safety alignment of large language models (LLMs) have revealed that existing approaches often operate superficially, leaving models vulnerable to various adversarial attacks. Despite their significance, these studies…