UCSC at SemEval-2025 task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output

Sicong Huang, Jincheng He, Shiyuan Huang, Karthik Raja Anandan, Arkajyoti Chakraborty, Ian Lane

Abstract

Our approach to SemEval-2025 Task 3 explores context-aware methods, model selection, and prompt optimization techniques for detecting hallucinations in large language model outputs.

Date
Aug 1, 2025
Event
The 19th International Workshop on Semantic Evaluation, ACL 2025
Location
Vienna, Austria
Vienna,

Presentation at The 19th International Workshop on Semantic Evaluation (SemEval), co-located with ACL 2025 in Vienna, Austria.

Authors: Sicong Huang, Jincheng He, Shiyuan Huang, Karthik Raja Anandan, Arkajyoti Chakraborty, and Ian Lane

Large Language Models Hallucination Detection SemEval Natural Language Processing
Shiyuan Huang
Shiyuan Huang
Ph.D. Student

I am a Ph.D. student in the Department of Computer Science and Engineering at UC Santa Cruz, under the supervision of Dr. Leilani Gilpin and Dr. Ian Lane. My research primarily revolves around the explainability of NLP models.