相关论文: Faithful-Patchscopes: Understanding and Mitigating…

Understanding the internal representations of large language models (LLMs) can help explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose…

Understanding and interpreting the internal representations of large language models (LLMs) remains an open challenge. Patchscopes introduced a method for probing internal activations by patching them into new prompts, prompting models to…

Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failures, collectively referred to as "hallucinations". Recent studies have demonstrated that LLMs' internal states encode information…

Chain-of-thought (CoT) reasoning enhances performance of large language models, but questions remain about whether these reasoning traces faithfully reflect the internal processes of the model. We present the first comprehensive study of…

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge,…

Large Language Models are increasingly proposed as cognitive components for robotic systems, yet their opaque decision processes make it difficult to explain success or failure in closed-loop embodied tasks. Following an empirical AI…

Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opaque. This lack of transparency presents challenges such as…

The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…

The growing deployment of large language models (LLMs) across diverse cultural contexts necessitates a deeper understanding of LLMs' representations of different cultures. Prior work has focused on evaluating the cultural awareness of LLMs…

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Large language models (LLMs) are demonstrably capable of cross-lingual transfer, but can produce inconsistent output when prompted with the same queries written in different languages. To understand how language models are able to…

Language models (LMs) trained on raw texts have no direct access to the physical world. Gordon and Van Durme (2013) point out that LMs can thus suffer from reporting bias: texts rarely report on common facts, instead focusing on the unusual…

Advances in the general capabilities of large language models (LLMs) have led to their use for information retrieval, and as components in automated decision systems. A faithful representation of probabilistic reasoning in these models may…

Large Language Models (LLMs) demonstrate strong few-shot generalization through in-context learning, yet their reasoning in dynamic and stochastic environments remains opaque. Prior studies mainly focus on static tasks and overlook the…

Large Language Models (LLMs) are able to provide assistance on a wide range of information-seeking tasks. However, model outputs may be misleading, whether unintentionally or in cases of intentional deception. We investigate the ability of…

Understanding the latent space geometry of large language models (LLMs) is key to interpreting their behavior and improving alignment. Yet it remains unclear to what extent LLMs linearly organize representations related to semantic…

We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can…

Large Language Models (LLMs) are increasingly applied to automated software testing, yet their ability to generalize beyond memorized patterns and reason about natural language bug reports remains unclear. We present a systematic evaluation…

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…