相关论文: The Truthfulness Spectrum Hypothesis

Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether large language models possess similar privileged knowledge about answer correctness,…

As Large Language Models (LLMs) become increasingly integrated into our daily lives, the potential harms from deceptive behavior underlie the need for faithfully interpreting their decision-making. While traditional probing methods have…

Large language models (LLMs) are known to struggle with consistently generating truthful responses. While various representation intervention techniques have been proposed, these methods typically apply a universal representation correction…

While the reasoning capabilities of Large Language Models (LLMs) excel in analytical tasks such as mathematics and code generation, their utility for abstractive summarization remains widely assumed but largely unverified. To bridge this…

Human languages are full of metaphorical expressions. Metaphors help people understand the world by connecting new concepts and domains to more familiar ones. Large pre-trained language models (PLMs) are therefore assumed to encode…

Can autoregressive large language models (LLMs) learn consistent probability distributions when trained on sequences in different token orders? We prove formally that for any well-defined probability distribution, sequence perplexity is…

Although large language models (LLMs) are highly interactive and extendable, current approaches to ensure reliability in deployments remain mostly limited to rejecting outputs with high uncertainty in order to avoid misinformation. This…

Informally, the 'linear representation hypothesis' is the idea that high-level concepts are represented linearly as directions in some representation space. In this paper, we address two closely related questions: What does "linear…

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual Probing, a novel…

Closed-source large language models (LLMs), such as ChatGPT and Gemini, are increasingly consulted for medical advice, yet their explanations may appear plausible while failing to reflect the model's underlying reasoning process. This gap…

When a language model is fed a wrong answer, what happens inside the network? Current understanding treats truthfulness as a static property of individual-layer representations-a direction to be probed, a feature to be extracted. Less is…

Large language models (LLMs) form implicit beliefs (posteriors over latent variables) from prompts, but we lack a mechanistic account of how these beliefs are encoded in representation space, how they update with new evidence, and how…

Despite the significant advances in domain generalized stereo matching, existing methods still exhibit domain-specific preferences when transferring from synthetic to real domains, hindering their practical applications in complex and…

Recent audio-aware large language models (ALLMs) have demonstrated strong capabilities across diverse audio understanding and reasoning tasks, but they still frequently produce hallucinated or overly confident outputs. While uncertainty…

Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…

While large pretrained language models (PLMs) demonstrate incredible fluency and performance on many natural language tasks, recent work has shown that well-performing PLMs are very sensitive to what prompts are feed into them. Even when…

Large language models (LLMs) have demonstrated impressive capabilities across a variety of tasks, but their increasing autonomy in real-world applications raises concerns about their trustworthiness. While hallucinations-unintentional…

Large language models (LLMs) increasingly solve difficult problems by producing "reasoning traces" before emitting a final response. However, it remains unclear how accuracy and decision commitment evolve along a reasoning trajectory, and…

We propose the Lattice Representation Hypothesis of large language models: a symbolic backbone that grounds conceptual hierarchies and logical operations in embedding geometry. Our framework unifies the Linear Representation Hypothesis with…

We find a mismatch between what large language models encode about a causal question and what they answer. On anti-commonsense CLadder items, a fixed linear probe recovers the evidence-supported answer from the model's hidden state…