相关论文: Thought Purity: A Defense Framework For Chain-of-T…

Chain-of-thought (CoT) reasoning is useful for monitoring language models only when the reasoning trace faithfully reflects the computation that produces the final answer. However, models can rely on prompt-to-answer shortcuts that bypass…

Chain-of-thought (CoT) prompting has been widely adopted to enhance the reasoning capabilities of large language models (LLMs). However, the effectiveness of CoT reasoning is inconsistent across tasks with different reasoning types. This…

Recent studies have discovered that Chain-of-Thought prompting (CoT) can dramatically improve the performance of Large Language Models (LLMs), particularly when dealing with complex tasks involving mathematics or reasoning. Despite the…

Large Reasoning Models (LRMs) achieve promising performance but compromise token efficiency due to verbose reasoning processes. Unconscious Thought Theory (UTT) posits that complex problems can be solved more efficiently through…

Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning. However, CoT is not always faithful to the model's final output, undermining its reliability as a monitoring…

In information retrieval, large language models (LLMs) have demonstrated remarkable potential in text reranking tasks by leveraging their sophisticated natural language understanding and advanced reasoning capabilities. However,…

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in reasoning and generation tasks and are increasingly deployed in real-world applications. However, their explicit chain-of-thought (CoT) mechanism introduces new…

Chain-of-Thought (CoT) prompting has emerged as a foundational technique for eliciting reasoning from Large Language Models (LLMs), yet the robustness of this approach to corruptions in intermediate reasoning steps remains poorly…

Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased when a flawed premise…

Large language models (LLMs) excel at complex reasoning but can still exhibit harmful behaviors. Current alignment strategies typically embed safety into model weights, making these controls implicit, static, and difficult to modify. This…

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of large language models (LLMs), but have also introduced their computational efficiency as a new attack surface. In this paper, we…

Although Large Language Models (LLMs) have evolved from text generators into the cognitive core of modern AI systems, their inherent lack of authorization awareness exposes these systems to catastrophic risks, ranging from unintentional…

Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model…

Explanations are often promoted as tools for transparency, but they can also foster confirmation bias; users may assume reasoning is correct whenever outputs appear acceptable. We study this double-edged role of Chain-of-Thought (CoT)…

We develop a learning-theoretic framework for understanding Chain of Thought (CoT). We model CoT as the interaction between an answer map and a chain rule that generates intermediate questions autoregressively, and define the reasoning risk…

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

Recent progress in large reasoning models for challenging mathematical reasoning has been driven by reinforcement learning (RL). Incorporating long chain-of-thought (CoT) data during mid-training has also been shown to substantially improve…

Recent Vision-Language-Action (VLA) models increasingly adopt chain-of-thought (CoT) reasoning, generating a natural-language plan before decoding motor commands. This internal text channel between the reasoning module and the action…

Large language model (LLM) performance on reasoning problems typically does not generalize out of distribution. Previous work has claimed that this can be mitigated with chain of thought prompting-a method of demonstrating solution…

Large Reasoning Models (LRMs) face a distinct safety vulnerability: their internal reasoning chains may generate harmful content even when the final output appears benign. To address this overlooked risk, we first propose a novel attack…