相关论文: TRACE: Trajectory Correction from Cross-layer Evid…

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Contextual hallucinations -- statements unsupported by given context -- remain a significant challenge in AI. We demonstrate a practical interpretability insight: a generator-agnostic observer model detects hallucinations via a single…

Modern neural recording techniques such as two-photon imaging or Neuropixel probes allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework…

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…

Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. However, the continual learning aspect of these aligned LLMs has been largely overlooked. Existing…

In an era of AI-generated misinformation flooding the web, existing tools struggle to empower users with nuanced, transparent assessments of content credibility. They often default to binary (true/false) classifications without contextual…

Automatic Speech Recognition (ASR) error correction aims to correct recognition errors while preserving accurate text. Although traditional approaches demonstrate moderate effectiveness, LLMs offer a paradigm that eliminates the need for…

We present TRACE (Transformer-based Risk Assessment for Clinical Evaluation), a novel method for clinical risk assessment based on clinical data, leveraging the self-attention mechanism for enhanced feature interaction and result…

Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning. Such a success of contrastive learning relies on two conditions, a sufficient number of positive pairs and adequate…

Mitigating hallucinations in large vision-language models (LVLMs) remains an open problem. Recent benchmarks do not address hallucinations in open-ended free-form responses, which we term "Type I hallucinations". Instead, they focus on…

An algorithm for solving nonconvex smooth optimization problems is proposed, analyzed, and tested. The algorithm is an extension of the Trust Region Algorithm with Contractions and Expansions (TRACE) [Math. Prog. 162(1):132, 2017]. In…

Stroke order and velocity are helpful features in the fields of signature verification, handwriting recognition, and handwriting synthesis. Recovering these features from offline handwritten text is a challenging and well-studied problem.…

The rapid evolution of large language models (LLMs) represents a substantial leap forward in natural language understanding and generation. However, alongside these advancements come significant challenges related to the accountability and…

Large language models (LLMs) excel at various natural language processing tasks, but their tendency to generate hallucinations undermines their reliability. Existing hallucination detection methods leveraging hidden states predominantly…

In this work, we introduce CHAIR (Classifier of Hallucination As ImproveR), a supervised framework for detecting hallucinations by analyzing internal logits from each layer of every token. Our method extracts a compact set of features such…

Large language models (LLMs) often generate hallucinated content that lacks factual or contextual grounding, limiting their reliability in critical applications. Existing approaches such as supervised fine-tuning and reinforcement learning…

Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing…

Large multimodal reasoning models solve challenging visual problems via explicit long-chain inference: they gather visual clues from images and decode clues into textual tokens. Yet this capability also increases hallucinations, where the…

Hallucination is a known issue for neural abstractive summarization models. Recent work suggests that the degree of hallucination may depend on errors in the training data. In this work, we propose a new method called Contrastive Parameter…

While Large Language Models have transformed how we interact with AI systems, they suffer from a critical flaw: they confidently generate false information that sounds entirely plausible. This hallucination problem has become a major…