Related papers: When Do LLM Preferences Predict Downstream Behavio…

As LLMs integrate into our daily lives, understanding their behavior becomes essential. In this work, we focus on behavioral dispositions$-$the underlying tendencies that shape responses in social contexts$-$and introduce a framework to…

The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancing LLMs with excellent applicability and effectiveness in a…

Vision Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs…

Can large language models (LLMs) learn a decision maker's preferences from observed choices and generate preference-consistent recommendations in new situations? We propose a portable Simulate-Recommend-Evaluate framework that tests…

Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they exhibit $\textbf{modality preference}$, a tendency to favor one modality over…

Alignment has quickly become a default ingredient in LLM development, with techniques such as reinforcement learning from human feedback making models act safely, follow instructions, and perform ever-better on complex tasks. While these…

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, which is called…

LLMs are now embedded in a wide range of everyday scenarios. However, their inherent hallucinations risk hiding misinformation in fluent responses, raising concerns about overreliance on AI. Detecting overreliance is challenging, as it…

For AI systems to be useful to humans, they must understand and act in accordance with our values and preferences. Since specifying preferences is a hard task, inverse reinforcement learning (IRL) aims to develop methods that allow for…

Large language models are increasingly used in decision-making tasks that require them to process information from a variety of sources, including both human experts and other algorithmic agents. How do LLMs weigh the information provided…

Refusal behavior in large language models (LLMs) enables them to decline responding to harmful, unethical, or inappropriate prompts, ensuring alignment with ethical standards. This paper investigates refusal behavior across six LLMs from…

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…

Large Language Models (LLMs) are increasingly employed in software engineering tasks such as requirements elicitation, design, and evaluation, raising critical questions regarding their alignment with human judgments on responsible AI…

LLM-based agents can complete tasks correctly yet still frustrate users through poor interaction patterns, such as excessive confirmations, opaque reasoning, or misaligned pacing. Current benchmarks evaluate task accuracy but overlook how…

Large Language Models (LLMs) exhibit remarkably powerful capabilities. One of the crucial factors to achieve success is aligning the LLM's output with human preferences. This alignment process often requires only a small amount of data to…

Large language models (LLMs) are increasingly employed for decision-support across multiple domains. We investigate whether these models display a systematic preferential bias in favor of artificial intelligence (AI) itself. Across three…

Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user…

Frontier LLMs are increasingly deployed as agents that pick the next action after a long log of prior tool calls produced by the same or a different model. We ask a simple safety question: if a prior step in that log was harmful, will the…

Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in…

System prompts in Large Language Models (LLMs) are predefined directives that guide model behaviour, taking precedence over user inputs in text processing and generation. LLM deployers increasingly use them to ensure consistent responses…