Related papers: Concept Tokens: Learning Behavioral Embeddings Thr…

Large Vision-Language Models (LVLMs) usually generate texts which satisfy context coherence but don't match the visual input. Such a hallucination issue hinders LVLMs' applicability in the real world. The key to solving hallucination in…

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…

Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning about 2D object…

To utilize visual information, Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder. The completeness and accuracy of visual perception significantly influence the precision of spatial reasoning,…

Large vision-language models (LVLMs), designed to interpret and respond to human instructions, occasionally generate hallucinated or harmful content due to inappropriate instructions. This study uses linear probing to shed light on the…

The rapid development of Large Multimodal Models (LMMs) has significantly advanced multimodal understanding by harnessing the language abilities of Large Language Models (LLMs) and integrating modality-specific encoders. However, LMMs are…

The ability to judge whether a caption correctly describes an image is a critical part of vision-language understanding. However, state-of-the-art models often misinterpret the correctness of fine-grained details, leading to errors in…

Prior works have shown that fine-tuning on new knowledge can induce factual hallucinations in large language models (LLMs), leading to incorrect outputs when evaluated on previously known information. However, the specific manifestations of…

When asked to summarize articles or answer questions given a passage, large language models (LLMs) can hallucinate details and respond with unsubstantiated answers that are inaccurate with respect to the input context. This paper describes…

Large vision-language models (LVLMs) often hallucinate content that is fluent yet unsupported by the image, limiting their reliability in real-world deployment. We show that a key failure mode arises from route competition: even when visual…

Large Language Models are known to capture real-world knowledge, allowing them to excel in many downstream tasks. Despite recent advances, these models are still prone to what are commonly known as hallucinations, causing them to emit…

Large vision-language models (LVLMs) have demonstrated remarkable capabilities in multimodal understanding and generation tasks. However, these models occasionally generate hallucinatory texts, resulting in descriptions that seem reasonable…

Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring…

Humans can approach complex visual problems by mentally simulating intermediate visual steps, rather than reasoning through language alone. Inspired by this, several works on Vision-Language Models have recently explored chain-of-thought…

Existing Large Vision-Language Models (LVLMs) exhibit insufficient visual attention, leading to hallucinations. To alleviate this problem, some previous studies adjust and amplify visual attention. These methods present a limitation that…

Hallucination detection is critical for ensuring the reliability of large language models (LLMs) in context-based generation. Prior work has explored intrinsic signals available during generation, among which attention offers a direct view…

Large Language Models (LLMs) often hallucinate, generating content inconsistent with the input. Retrieval-Augmented Generation (RAG) and Reinforcement Learning with Human Feedback (RLHF) can mitigate hallucinations but require…

This project develops a self correcting framework for large language models (LLMs) that detects and mitigates hallucinations during multi-step reasoning. Rather than relying solely on final answer correctness, our approach leverages fine…

Our understanding of the visual world is centered around various concept axes, characterizing different aspects of visual entities. While different concept axes can be easily specified by language, e.g. color, the exact visual nuances along…

Despite their impressive capacities, Large language models (LLMs) often struggle with the hallucination issue of generating inaccurate or fabricated content even when they possess correct knowledge. In this paper, we extend the exploration…