相关论文: Steering LVLMs via Sparse Autoencoder for Hallucin…

This survey presents a comprehensive analysis of the phenomenon of hallucination in multimodal large language models (MLLMs), also known as Large Vision-Language Models (LVLMs), which have demonstrated significant advancements and…

Large language models (LLMs) can generate executable code from natural language descriptions, but the resulting programs frequently contain bugs due to hallucinations. In the absence of formal specifications, existing approaches attempt to…

Understanding the internal representations of large language models (LLMs) remains a central challenge for interpretability research. Sparse autoencoders (SAEs) offer a promising solution by decomposing activations into interpretable…

Despite the great success of Large Vision-Language Models (LVLMs), they inevitably suffer from hallucination. As we know, both the visual encoder and the Large Language Model (LLM) decoder in LVLMs are Transformer-based, allowing the model…

Recent advancements in large vision-language models (LVLMs) have demonstrated impressive capability in visual information understanding with human language. Despite these advances, LVLMs still face challenges with multimodal hallucination,…

In-context learning, the ability to adapt based on a few examples in the input prompt, is a ubiquitous feature of large language models (LLMs). However, as LLMs' in-context learning abilities continue to improve, understanding this…

Hallucinations in large vision-language models (LVLMs) pose significant challenges for real-world applications, as LVLMs may generate responses that appear plausible yet remain inconsistent with the associated visual content. This issue…

Large language models (LLMs) have demonstrated exceptional proficiency in language understanding. However, when LLMs align their outputs with deceptive and/or misleading prompts, the generated responses could deviate from the de facto…

Hallucinations, generating responses inconsistent with the visual input, remain a critical limitation of large vision-language models (LVLMs), especially in open-ended tasks such as image captioning and visual reasoning. In this work, we…

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only…

Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing content that is fluent but inconsistent with visual evidence.…

Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language steering, a lightweight inference-time method that…

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) have succeeded in a variety of natural language processing tasks [Zha+25]. However, they have notable limitations. LLMs tend to generate hallucinations, a seemingly plausible yet factually unsupported output…

Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations, where they generate descriptions of nonexistent objects, actions, or concepts, posing significant risks in safety-critical…

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

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…

Large language models (LLMs) often generate fluent but factually incorrect statements despite having access to relevant evidence, a failure mode rooted in how they allocate attention between contextual and parametric knowledge.…

Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination…