Related papers: MoRFI: Monotonic Sparse Autoencoder Feature Identi…

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…

Recent work has demonstrated state-of-the-art results in large language model (LLM) hallucination detection and mitigation through consistency-based approaches which involve aggregating multiple responses sampled from a single LLM for a…

The hallucination problem of Large Language Models (LLMs) significantly limits their reliability and trustworthiness. Humans have a self-awareness process that allows us to recognize what we don't know when faced with queries. Inspired by…

Large Vision-Language Models (LVLMs) have shown strong performance across multimodal tasks. However, they often produce hallucinations -- text that is inconsistent with visual input, due to the limited ability to verify information in…

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

The performance of Large Language Models (LLMs) on many tasks is greatly limited by the knowledge learned during pre-training and stored in the model's parameters. Low-rank adaptation (LoRA) is a popular and efficient training technique for…

As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning from third-party custom finetuning data. We explore the…

Despite their impressive capabilities, large language models (LLMs) have been observed to generate responses that include inaccurate or fabricated information, a phenomenon commonly known as ``hallucination''. In this work, we propose a…

Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigation methods either perturb the visual representation and…

Large Language Models (LLMs) are traditionally viewed as black-box algorithms, therefore reducing trustworthiness and obscuring potential approaches to increasing performance on downstream tasks. In this work, we apply an effective LLM…

How to alleviate the hallucinations of Large Language Models (LLMs) has always been the fundamental goal pursued by the LLMs research community. Looking through numerous hallucination-related studies, a mainstream category of methods is to…

This paper presents a study on strategies to enhance the translation capabilities of large language models (LLMs) in the context of machine translation (MT) tasks. The paper proposes a novel paradigm consisting of three stages: Secondary…

The emergence of large language models (LLMs) is a milestone in generative artificial intelligence, achieving significant success in text comprehension and generation tasks. Despite the tremendous success of LLMs in many downstream tasks,…

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement…

Hallucinations in Large Vision-Language Models (LVLMs) significantly undermine their reliability, motivating researchers to explore the causes of hallucination. However, most studies primarily focus on the language aspect rather than the…

Hallucination in Large Language Models (LLMs) refers to the generation of content that is not faithful to the input or the real-world facts. This paper provides a rigorous treatment of hallucination in LLMs, including formal definitions and…

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do…

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provided sources, remain a…

Large Language Models (LLMs) frequently prioritize conflicting in-context information over pre-existing parametric memory, a phenomenon often termed sycophancy or compliance. However, the mechanistic realization of this behavior remains…

Multimodal Large Language Models (MLLMs) have made significant strides by combining visual recognition and language understanding to generate content that is both coherent and contextually accurate. However, MLLMs continue to struggle with…