相关论文: Do I Know This Entity? Knowledge Awareness and Hal…

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

One of the major aspects contributing to the striking performance of large language models (LLMs) is the vast amount of factual knowledge accumulated during pre-training. Yet, many LLMs suffer from self-inconsistency, which raises doubts…

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques. Many existing unlearning methods aim to suppress…

We show that language models hallucinate not because they fail to detect uncertainty, but because of a failure to integrate it into output generation. Across architectures, uncertain inputs are reliably identified, occupying…

Although Multimodal Large Language Models (MLLMs) have advanced substantially, they remain vulnerable to object hallucination caused by language priors and visual information loss. To address this, we propose SAVE (Sparse Autoencoder-Driven…

Large Language Models (LLMs) can make up answers that are not real, and this is known as hallucination. This research aims to see if, how, and to what extent LLMs are aware of hallucination. More specifically, we check whether and how an…

We study how reliably sparse autoencoders (SAEs) support claims about reasoning-related internal features in large language models. We first give a stylized analysis showing that sparsity-regularized decoding can preferentially retain…

Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction. Subsequent stages of post-training often introduce new facts outwith the parametric knowledge, giving rise to…

Large language models are successful in answering factoid questions but are also prone to hallucination. We investigate the phenomenon of LLMs possessing correct answer knowledge yet still hallucinating from the perspective of inference…

Despite the recent advancement in large language models (LLMs) and their high performances across numerous benchmarks, recent research has unveiled that LLMs suffer from hallucinations and unfaithful reasoning. This work studies a specific…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

Recent developments in Large Language Model (LLM) capabilities have brought great potential but also posed new risks. For example, LLMs with knowledge of bioweapons, advanced chemistry, or cyberattacks could cause violence if placed in the…

Large language models (LLMs) have been shown to possess impressive capabilities, while also raising crucial concerns about the faithfulness of their responses. A primary issue arising in this context is the management of (un)answerable…

Large language models (LLMs) are susceptible to hallucinations -- factually incorrect outputs -- leading to a large body of work on detecting and mitigating such cases. We argue that it is important to distinguish between two types of…

In many reasoning tasks, large language models (LLMs) rely on structured external knowledge, such as graphs and tables, which is typically linearized into sequential token representations. However, even when sufficient knowledge is…

Refusal is a key safety behavior in aligned language models, yet the internal mechanisms driving refusals remain opaque. In this work, we conduct a mechanistic study of refusal in instruction-tuned LLMs using sparse autoencoders to identify…

Like students facing hard exam questions, large language models sometimes guess when uncertain, producing plausible yet incorrect statements instead of admitting uncertainty. Such "hallucinations" persist even in state-of-the-art systems…

Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection methods have made notable progress, we find most of them…