Related papers: SAFE: A Sparse Autoencoder-Based Framework for Rob…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for language model steering. Prior work has explored top-k SAE latents for steering, but we observe that many dimensions among the top-k latents capture non-semantic…

Large language models (LLMs) are increasingly being adopted as the cognitive core of embodied agents. However, inherited hallucinations, which stem from failures to ground user instructions in the observed physical environment, can lead to…

Large language models and vision transformers have demonstrated impressive zero-shot capabilities, enabling significant transferability in downstream tasks. The fusion of these models has resulted in multi-modal architectures with enhanced…

Hallucinations in large language models (LLMs) refer to the phenomenon of LLMs producing responses that are coherent yet factually inaccurate. This issue undermines the effectiveness of LLMs in practical applications, necessitating research…

As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded. This issue of…

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

This work introduces a novel methodology for the automatic detection of hallucinations generated during large language model (LLM) inference. The proposed approach is based on a systematic taxonomy and controlled reproduction of diverse…

Vision-language models (VLMs) have great potential for medical image understanding, particularly in Visual Report Generation (VRG) and Visual Question Answering (VQA), but they may generate hallucinated responses that contradict visual…

Hallucination, or the generation of incorrect or fabricated information, remains a critical challenge in large language models (LLMs), particularly in high-stake domains such as legal question answering (QA). In order to mitigate the…

Large Vision-Language Models (LVLMs) have recently achieved impressive results in multimodal tasks such as image captioning and visual question answering. However, they remain prone to object hallucination -- generating descriptions of…

Large Language Models (LLMs) are widely used to generate plausible text on online platforms, without revealing the generation process. As users increasingly encounter such black-box outputs, detecting hallucinations has become a critical…

Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world applicability. While several methods for hallucination…

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

The hallucination problem in multimodal large language models (MLLMs) remains a common issue. Although image tokens occupy a majority of the input sequence of MLLMs, there is limited research to explore the relationship between image tokens…

The emergence of Large Language Models (LLMs) has revolutionized how users access information, shifting from traditional search engines to direct question-and-answer interactions with LLMs. However, the widespread adoption of LLMs has…

Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025) have highlighted instability across different initialization…

Detecting whether an LLM hallucinates is an important research challenge. One promising way of doing so is to estimate the semantic entropy (Farquhar et al., 2024) of the distribution of generated sequences. We propose a new algorithm for…

Despite recent advances in Large Vision Language Models (LVLMs), these models still suffer from generating hallucinatory responses that do not align with the visual input provided. To mitigate such hallucinations, we introduce Efficient…

Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational neurolinguistics, yet why remains mechanistically unexplained. We address this gap by…

Multimodal Large Language Models (MLLMs) often suffer from hallucinations, particularly errors in object existence, attributes, or relations, which undermine their reliability. We introduce TACO (Verified Atomic Confidence Estimation), a…