Related papers: NEST: Nascent Encoded Steganographic Thoughts

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) prompting to solve mathematical and logical reasoning tasks. Yet, a central question remains: to what extent are these generated rationales \emph{faithful} to the…

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

Trustworthy evaluations of dangerous capabilities are increasingly crucial for determining whether an AI system is safe to deploy. One empirically demonstrated threat is sandbagging - the strategic underperformance on evaluations by AI…

Large language models (LLMs) exhibit strong reasoning abilities, often attributed to few-shot or zero-shot chain-of-thought (CoT) prompting. While effective, these methods require labor-intensive prompt engineering, raising the question of…

Whether intermediate reasoning is computationally useful or merely explanatory depends on whether chain-of-thought (CoT) tokens contain task-relevant information. We present a mechanistic causal analysis of CoT on GSM8K using activation…

Chain of Thought (CoT) prompting can encourage language models to engage in multi-step logical reasoning. The quality of the provided demonstrations significantly influences the success of downstream inference tasks. Current unsupervised…

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…

Code deobfuscation is the task of recovering a readable version of a program while preserving its original behavior. In practice, this often requires days or even months of manual work with complex and expensive analysis tools. In this…

Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quantify such behaviours are lacking. Classical…

Chain-of-Thought (CoT) empowers Large Language Models (LLMs) to tackle complex problems, but remains constrained by the computational cost and reasoning path collapse when grounded in discrete token spaces. Recent latent reasoning…

Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning…

Chain-of-thought (CoT) reasoning has advanced medical visual question answering (VQA), yet most existing CoT rationales are free-form and fail to capture the structured reasoning process clinicians actually follow. This work asks: Can…

Large reasoning models (LRMs) like OpenAI-o1 have shown impressive capabilities in natural language reasoning. However, these models frequently demonstrate inefficiencies or inaccuracies when tackling complex mathematical operations. While…

Large language models (LLMs) are increasingly being applied to clinical care, a domain where both accuracy and transparent reasoning are critical for safe and trustworthy deployment. Chain-of-thought (CoT) prompting, which elicits…

Large Language Models (LLMs) achieve impressive accuracy on mathematical reasoning benchmarks, yet their performance drops when problems are modified with simple changes like different names or numbers. Code execution methods, which let…

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…

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by integrating powerful language backbones with large-scale visual encoders. Among these, latent Chain-of-Thought (CoT) methods enable implicit reasoning in…

Chain-of-Thought (CoT) holds a significant place in augmenting the reasoning performance for large language models (LLMs). While some studies focus on improving CoT accuracy through methods like retrieval enhancement, yet a rigorous…

Chain-of-thought (CoT) prompting has become central to mathematical reasoning in large language models, yet models remain brittle to early errors: a single arithmetic slip or unjustified inference typically propagates uncorrected to an…