Related papers: Do Reasoning LLMs Refuse What They Infer in Long C…

Large Reasoning Models (LRMs) have significantly improved problem-solving through explicit Chain-of-Thought (CoT) reasoning. However, this capability creates a Safety-Helpfulness Paradox: the reasoning process itself can be misused to…

Recently, significant efforts have been devoted to enhancing the long-context capabilities of Large Language Models (LLMs), particularly in long-context reasoning. To facilitate this research, we propose \textbf{DetectiveQA}, a dataset…

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the…

Large Language Models (LLMs) are increasingly used as code assistants, yet their behavior when explicitly asked to generate insecure code remains poorly understood. While prior research has focused on unintended vulnerabilities, this study…

We discover a novel and surprising phenomenon of unintentional misalignment in reasoning language models (RLMs), which we call self-jailbreaking. Specifically, after benign reasoning training on math or code domains, RLMs will use multiple…

Instruction-following retrievers have been widely adopted alongside LLMs in real-world applications, but little work has investigated the safety risks surrounding their increasing search capabilities. We empirically study the ability of…

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can consume far more text than they can reliably use. On the other…

While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsistencies, and conflation between objective world states and…

The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers remain poorly understood. Prior work suggests that a single…

Large language models (LLMs) solve complex problems yet fail on simpler variants, suggesting they achieve correct outputs through mechanisms fundamentally different from human reasoning. To understand this gap, we synthesize cognitive…

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Recent claims of strong performance by Large Language Models (LLMs) on causal discovery are undermined by a key flaw: many evaluations rely on benchmarks likely included in pretraining corpora. Thus, apparent success suggests that LLM-only…

Large language models (LLMs) have exhibited remarkable capabilities in learning from explanations in prompts, but there has been limited understanding of exactly how these explanations function or why they are effective. This work aims to…

Precisely understanding users' contextual search intent has been an important challenge for conversational search. As conversational search sessions are much more diverse and long-tailed, existing methods trained on limited data still show…

Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden…

Multimodal large language models (MLLMs) have become the cornerstone of today's generative AI ecosystem, sparking intense competition among tech giants and startups. In particular, an MLLM generates a text response given a prompt consisting…

Large language models (LMs) such as GPT-3 have the surprising ability to do in-context learning, where the model learns to do a downstream task simply by conditioning on a prompt consisting of input-output examples. The LM learns from these…

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a…

Large language models (LLMs) and small language models (SLMs) are being adopted at remarkable speed, although their safety still remains a serious concern. With the advent of multilingual S/LLMs, the question now becomes a matter of scale:…

Large language models (LLMs) can be influenced by harmful or irrelevant context, which can significantly harm model performance on downstream tasks. This motivates principled designs in which LLM systems include built-in mechanisms to guard…