相关论文: Feedback-Enhanced Hallucination-Resistant Vision-L…

Large Visual Language Models (LVLMs) struggle with hallucinations in visual instruction following task(s), limiting their trustworthiness and real-world applicability. We propose Pelican -- a novel framework designed to detect and mitigate…

Large language models (LLMs) produce fluent but unsupported answers - hallucinations - limiting safe deployment in high-stakes domains. We propose ECLIPSE, a framework that treats hallucination as a mismatch between a model's semantic…

As students increasingly rely on large language models, hallucinations pose a growing threat to learning. To mitigate this, AI literacy must expand beyond prompt engineering to address how students should detect and respond to LLM…

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…

Large Language Models (LLMs) and Large Reasoning Models (LRMs) offer transformative potential for high-stakes domains like finance and law, but their tendency to hallucinate, generating factually incorrect or unsupported content, poses a…

Recent development of Large Vision-Language Models (LVLMs) has attracted growing attention within the AI landscape for its practical implementation potential. However, ``hallucination'', or more specifically, the misalignment between…

Mitigating object hallucination in large vision-language models (LVLMs) is critical to their safe deployment. Existing methods either are restricted to specific decoding methods, or demand sophisticated modifications to visual inputs, or…

While reinforcement learning has unlocked unprecedented complex reasoning in large language models, it has also amplified their propensity for hallucination, creating a critical trade-off between capability and reliability. This work…

Current popular Large Vision-Language Models (LVLMs) are suffering from Hallucinations on Object Attributes (HoOA), leading to incorrect determination of fine-grained attributes in the input images. Leveraging significant advancements in 3D…

With the advent of rich visual representations and pre-trained language models, video captioning has seen continuous improvement over time. Despite the performance improvement, video captioning models are prone to hallucination.…

Visual attention serves as the primary mechanism through which MLLMs interpret visual information; however, its limited localization capability often leads to hallucinations. We observe that although MLLMs can accurately extract visual…

Hallucinations present a significant challenge for large language models (LLMs). The utilization of parametric knowledge in generating factual content is constrained by the limited knowledge of LLMs, potentially resulting in internal…

Can we see it all? Do we know it All? These are questions thrown to human beings in our contemporary society to evaluate our tendency to solve problems. Recent studies have explored several models in object detection; however, most have…

Large vision-language models (LVMs) extend large language models (LLMs) with visual perception capabilities, enabling them to process and interpret visual information. A major challenge compromising their reliability is object hallucination…

Reasoning-augmented vision language models (VLMs) generate explicit chains of thought that promise greater capability and transparency but also introduce new failure modes: models may reach correct answers via visually unfaithful…

Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet physically inconsistent or visually ungrounded responses due to likelihood maximization…

Large language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we…

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal tasks, but remain susceptible to hallucinations, where generated text deviates from the underlying visual content. Existing hallucination detection methods…

Despite their remarkable progress in multimodal understanding tasks, large vision language models (LVLMs) often suffer from "hallucinations", generating texts misaligned with the visual context. Existing methods aimed at reducing…