相关论文: Generating Faithful and Salient Text from Multimod…

The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…

Concerns regarding the propensity of Large Language Models (LLMs) to produce inaccurate outputs, also known as hallucinations, have escalated. Detecting them is vital for ensuring the reliability of applications relying on LLM-generated…

Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the image), undermining reliability in practice. Prior efforts…

Abstractive summarization using large language models (LLMs) has become an essential tool for condensing information. However, despite their ability to generate fluent summaries, these models sometimes produce unfaithful summaries,…

Large Multimodal Models (LMMs) often suffer from multimodal hallucinations, wherein they may create content that is not present in the visual inputs. In this paper, we explore a new angle of this issue: overly detailed training data hinders…

Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines incorrect details about an image in visual question answering. Existing studies find VH instances only in existing image datasets, which results in biased understanding…

The remarkable performance of Multimodal Large Language Models (MLLMs) has unequivocally demonstrated their proficient understanding capabilities in handling a wide array of visual tasks. Nevertheless, the opaque nature of their black-box…

Continual learning is essential for medical image classification systems to adapt to dynamically evolving clinical environments. The integration of multimodal information can significantly enhance continual learning of image classes.…

Neural text generation (data- or text-to-text) demonstrates remarkable performance when training data is abundant which for many applications is not the case. To collect a large corpus of parallel data, heuristic rules are often used but…

Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated text, a phenomenon…

Neural sequence models can generate highly fluent sentences, but recent studies have also shown that they are also prone to hallucinate additional content not supported by the input. These variety of fluent but wrong outputs are…

Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations. In this paper, we…

Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend…

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,…

With the rapid development of large language models (LLMs), LLM-as-a-judge has emerged as a widely adopted approach for text quality evaluation, including hallucination evaluation. While previous studies have focused exclusively on…

Large language models (LLMs), despite their remarkable text generation capabilities, often hallucinate and generate text that is factually incorrect and not grounded in real-world knowledge. This poses serious risks in domains like…

Large Vision-Language Models (LVLMs) integrate image encoders with Large Language Models (LLMs) to process multi-modal inputs and perform complex visual tasks. However, they often generate hallucinations by describing non-existent objects…

Existing large language models (LLMs) are known for generating "hallucinated" content, namely a fabricated text of plausibly looking, yet unfounded, facts. To identify when these hallucination scenarios occur, we examine the properties of…

Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains challenging. We first show that prompting MLLMs to reason before prediction does not…

Vision-Language Models (VLMs) are becoming increasingly popular in the medical domain, bridging the gap between medical images and clinical language. Existing VLMs demonstrate an impressive ability to comprehend medical images and text…