← Search

Jia Yuan

2 accepted papers

2025

Chain-of-Thought Prompting Obscures Hallucination Cues in Large Language Models: An Empirical Evaluation

EMNLP 2025

Large Language Models (LLMs) often exhibit hallucinations, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging step-by-step reasoning, but its impact on hallucination detection remains u

2021

Superpoint Network for Point Cloud Oversegmentation

ICCV 2021poster

Superpoints are formed by grouping similar points with local geometric structures, which can effectively reduce the number of primitives of point clouds for subsequent point cloud processing. Existing superpoint methods mainly focus on employing clustering or graph partition to generate superpoints…

Cited by 42PDFcodeScholar