相关论文: Adaptive Activation Cancellation for Hallucination…

Multimodal large language models (MLLMs) face an inherent trade-off between faithfulness and creativity, as different tasks require varying degrees of associative reasoning. However, existing methods lack the flexibility to modulate this…

Large language models are extensively applied across a wide range of tasks, such as customer support, content creation, educational tutoring, and providing financial guidance. However, a well-known drawback is their predisposition to…

Large Language Models (LLMs) exhibit remarkable capabilities in natural language understanding and reasoning, but suffer from hallucination: the generation of factually incorrect content. While numerous methods have been developed to reduce…

This work introduces a novel methodology for the automatic detection of hallucinations generated during large language model (LLM) inference. The proposed approach is based on a systematic taxonomy and controlled reproduction of diverse…

Despite remarkable progress in image quality and prompt fidelity, text-to-image (T2I) diffusion models continue to exhibit persistent "hallucinations", where generated content subtly or significantly diverges from the intended prompt…

Large Vision-Language Models (LVLMs) suffer from serious hallucination problems, where the model-generated responses are inconsistent with the visual inputs. Existing hallucination mitigation methods are mainly based on preference alignment…

Object hallucination remains a critical challenge in Large Vision-Language Models (LVLMs), where models generate content inconsistent with visual inputs. Existing language-decoder based mitigation approaches often regulate visual or textual…

Voice-controlled dialog systems have become immensely popular due to their ability to perform a wide range of actions in response to diverse user queries. These agents possess a predefined set of skills or intents to fulfill specific user…

To develop trustworthy Vision-Language Models (VLMs), it is essential to address adversarial robustness and hallucination mitigation, both of which impact factual accuracy in high-stakes applications such as defense and healthcare. Existing…

Large Vision-Language Models (LVLMs) exhibit strong multimodal capabilities but remain vulnerable to hallucinations from intrinsic errors and adversarial attacks from external exploitations, limiting their reliability in real-world…

Addressing the issue of hallucinations in large language models (LLMs) is a critical challenge. As the cognitive mechanisms of hallucination have been related to memory, here we explore hallucination for LLM that is enabled with explicit…

Despite their success, Large Vision-Language Models (LVLMs) remain vulnerable to hallucinations. While existing studies attribute the cause of hallucinations to insufficient visual attention to image tokens, our findings indicate that…

Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do…

Large Language Models (LLMs) require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay in multi-hop factual recall. This failure is particularly acute when edits…

Multimodal Large Language Models (MLLMs) achieve strong performance on tasks like image captioning and visual question answering, but remain prone to hallucinations, where generated text conflicts with the visual input. Prior work links…

Training large language representation models has become a standard in the natural language processing community. This allows for fine tuning on any number of specific tasks, however, these large high capacity models can continue to train…

Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, amplification of harmful content, and the propagation of unwanted patterns during extended…

Large Language Models (LLMs) have transformed natural language processing (NLP) tasks, but they suffer from hallucination, generating plausible yet factually incorrect content. This issue extends to Video-Language Models (VideoLLMs), where…

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal abilities but remain prone to multilingual object hallucination, with a higher likelihood of generating responses inconsistent with the visual input when utilizing…

Small language models (SLMs) are increasingly used for financial classification due to their fast inference and local deployability. However, compared with large language models, SLMs are more prone to factual hallucinations in reasoning…