Related papers: MoRFI: Monotonic Sparse Autoencoder Feature Identi…

Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in developing industry applications of LLMs. However, LLMs are…

Vision Language models (VLMs) often hallucinate non-existent objects. Detecting hallucination is analogous to detecting deception: a single final statement is insufficient, one must examine the underlying reasoning process. Yet existing…

In recent years, unlearning techniques, which are methods for inducing a model to "forget" previously learned information, have attracted attention as a way to address privacy and copyright concerns in large language models (LLMs) and large…

Sparse Autoencoders (SAEs) have shown promise in improving the interpretability of neural network activations, but can learn features that are not features of the input, limiting their effectiveness. We propose \textsc{Mutual Feature…

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper presents a novel framework that leverages sparse autoencoders…

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…

Large language models (LLMs) hallucinate with confidence: their outputs can be fluent, authoritative, and simply wrong. In medical, legal, and scientific applications this failure causes direct harm, and detecting it from internal model…

Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main…

Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences. However, it carries the…

Understanding and mitigating hallucinations in Large Language Models (LLMs) is crucial for ensuring reliable content generation. While previous research has primarily focused on "when" LLMs hallucinate, our work explains "why" and directly…

The deployment of Large Language Models (LLMs) in customer support is constrained by hallucination (generating false information) and the high cost of proprietary models. To address these challenges, we propose a retrieval-augmented…

Existing Large Vision-Language Models (LVLMs) primarily align image features of vision encoder with Large Language Models (LLMs) to leverage their superior text generation capabilities. However, the scale disparity between vision encoder…

Recent advancements in Large Language Models (LLMs) have showcased their remarkable capabilities in text understanding and generation. However, even stronger LLMs are susceptible to acquiring erroneous or obsolete information from the…

Hallucination has emerged as the most vulnerable aspect of contemporary Large Language Models (LLMs). In this paper, we introduce the Sorry, Come Again (SCA) prompting, aimed to avoid LLM hallucinations by enhancing comprehension through:…

Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cross-modal interference: information from one modality misguides the interpretation of…

We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and…

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…

State-of-the-art language models (LMs) sometimes generate non-factual hallucinations that misalign with world knowledge. To explore the mechanistic causes of these hallucinations, we create diagnostic datasets with subject-relation queries…

Hallucinations, the generation of apparently convincing yet false statements, remain a major barrier to the safe deployment of LLMs. Building on the strong performance of self-detection methods, we examine the use of structured knowledge…

Large language models (LLMs) have revolutionized numerous domains with their impressive performance but still face their challenges. A predominant issue is the propensity for these models to generate non-existent facts, a concern termed…