相关论文: Neural Message-Passing on Attention Graphs for Hal…

Rapid progress in large vision-language models (LVLMs) has achieved unprecedented performance in vision-language tasks. However, due to the strong prior of large language models (LLMs) and misaligned attention across modalities, LVLMs often…

Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, where the model fabricates facts and produces non-factual…

Diffusion large language models (D-LLMs) have emerged as a promising alternative to auto-regressive models due to their iterative refinement capabilities. However, hallucinations remain a critical issue that hinders their reliability. To…

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…

This paper explores hallucination phenomena in large language models (LLMs) through the lens of language philosophy and psychoanalysis. By incorporating Lacan's concepts of the "chain of signifiers" and "suture points," we propose the…

Large Language Models (LLMs) often generate hallucinations, producing outputs that are contextually inaccurate or factually incorrect. We introduce HICD, a novel method designed to induce hallucinations for contrastive decoding to mitigate…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, yet they remain susceptible to hallucinations -- generating content that is factually incorrect, unfaithful to provided…

Despite the rapid success of Large Vision-Language Models (LVLMs), a persistent challenge is their tendency to generate hallucinated content, undermining reliability in real-world use. Existing training-free methods address hallucinations…

Large language models (LLMs) often exhibit Context Faithfulness Hallucinations, where outputs deviate from retrieved information due to incomplete context integration. Our analysis reveals a strong correlation between token-level…

Research on token-level reference-free hallucination detection has predominantly focused on English, primarily due to the scarcity of robust datasets in other languages. This has hindered systematic investigations into the effectiveness of…

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…

Large language models (LLMs) have demonstrated impressive performance in both research and real-world applications, but they still struggle with hallucination. Existing hallucination detection methods often perform poorly on sentence-level…

Hallucinations in Large Language Models (LLMs) -- generations that are plausible but factually unfaithful -- remain a critical barrier to high-stakes deployment. Current detection methods typically rely on computationally expensive external…

Large Language Models with transformer architecture have revolutionized the domain of text generation, setting unprecedented benchmarks. Despite their impressive capabilities, LLMs have been criticized for generating outcomes that deviate…

Neural machine translation (NMT) has become the de-facto standard in real-world machine translation applications. However, NMT models can unpredictably produce severely pathological translations, known as hallucinations, that seriously…

Neural sequence generation models are known to "hallucinate", by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions they arise and how to mitigate…

Large language models (LLMs) can generate fluent responses, but sometimes hallucinate facts. In this paper, we investigate whether LLMs can detect their own hallucinations. We formulate hallucination detection as a classification task of a…

High-stakes domains like cyber operations need responsible and trustworthy AI methods. While large language models (LLMs) are becoming increasingly popular in these domains, they still suffer from hallucinations. This research paper…

Hallucinations of vision-language models (VLMs), which are misalignments between visual content and generated text, undermine the reliability of VLMs. One common approach for detecting them employs the same VLM, or a different one, to…

Retrieval-Augmented Generation (RAG) integrates external knowledge to mitigate hallucinations, yet models often generate outputs inconsistent with retrieved content. Accurate hallucination detection requires disentangling the contributions…