相关论文: The First Token Knows: Single-Decode Confidence fo…

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on…

The popularity of automated news headline generation has surged with advancements in pre-trained language models. However, these models often suffer from the ``hallucination'' problem, where the generated headline is not fully supported by…

Audio and vision provide complementary evidence for audio-visual question answering, yet current audio-visual large language models may suffer from cross-modal interference: information from one modality misguides the interpretation of…

Large Language Models (LLMs) are known to hallucinate and generate non-factual outputs which can undermine user trust. Traditional methods to directly mitigate hallucinations, such as representation editing and contrastive decoding, often…

Probabilistic decoding in Large Language Models (LLMs) often yields inconsistent outputs, particularly on complex or long-form questions. Self-Consistency (SC) mitigates this for short-form QA by majority voting over exact strings, whereas…

Hallucination remains a key obstacle to the reliable deployment of large language models (LLMs) in real-world question answering tasks. A widely adopted strategy to detect hallucination, known as self-assessment, relies on the model's own…

Vision Language models (VLMs) often hallucinate non-existent objects. Detecting hallucination is analogous to detecting deception: a single final statement is insufficient, one must examine the underlying reasoning process. Yet existing…

We identify a previously unknown calibration property of large language models: providing one confirmed intermediate fact toward a multi-step reasoning chain increases the model's confident-wrong-answer rate before full evidence eliminates…

As vision-language models (VLMs) are increasingly deployed in clinical decision support, more than accuracy is required: knowing when to trust their predictions is equally critical. Yet, a comprehensive and systematic investigation into the…

Large Language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations. A significant type of this issue is the false premise hallucination, which we define as the phenomenon when LLMs generate…

Large vision-language models can produce object hallucinations in image descriptions, highlighting the need for effective detection and mitigation strategies. Prior work commonly relies on the model's attention weights on visual tokens as a…

Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detection frameworks, we propose a simple yet powerful method…

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

The detection of sophisticated hallucinations in Large Language Models (LLMs) is hampered by a ``Detection Dilemma'': methods probing internal states (Internal State Probing) excel at identifying factual inconsistencies but fail on logical…

Language generation maps a rich, high-dimensional internal state to a single token sequence. We study this many-to-one mapping through the lens of intention collapse: the projection from an internal intention space I to an external language…

There has been significant research on developing pretrained transformer architectures for multimodal-to-text generation tasks. Albeit performance improvements, such models are frequently overparameterized, hence suffer from hallucination…

Large Language Models (LLMs) have demonstrated impressive generative capabilities across diverse tasks but remain susceptible to hallucinations, confidently generated yet factually incorrect outputs. We introduce a reference-free,…

Self-consistency has emerged as a popular technique for improving large language model accuracy on reasoning tasks. The approach is straightforward: generate multiple reasoning paths and select the most common answer through majority…

Hallucinations in Large Language Model (LLM) outputs for Question Answering (QA) tasks can critically undermine their real-world reliability. This paper introduces a methodology for robust, one-shot hallucination detection, specifically…

We introduce FaithScore (Faithfulness to Atomic Image Facts Score), a reference-free and fine-grained evaluation metric that measures the faithfulness of the generated free-form answers from large vision-language models (LVLMs). The…