Natural Language Processing

Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output
Presentation on automated hallucination detection in large language model outputs using context, models, and prompt optimization techniques.
Oct 16, 2025 BayLearn 2025 Santa Clara University
Sicong Huang, Jincheng He, Shiyuan Huang, Karthik Raja Anandan, Arkajyoti Chakraborty, Ian Lane
UCSC at SemEval-2025 task 3: Context, Models and Prompt Optimization for Automated Hallucination Detection in LLM Output
UCSC’s submission to SemEval-2025 Task 3 focusing on automated hallucination detection in LLM outputs.
Aug 1, 2025 The 19th International Workshop on Semantic Evaluation, ACL 2025 Vienna, Austria
Sicong Huang, Jincheng He, Shiyuan Huang, Karthik Raja Anandan, Arkajyoti Chakraborty, Ian Lane
Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations
A study examining the ability of large language models to generate self-explanations and their quality.
Oct 10, 2024 BayLearn 2024 Apple, Cupertino, California
Shiyuan Huang, Siddarth Mamidanna, Shreedhar Jangam, Yilun Zhou, Leilani H. Gilpin
Exploring Explainability and Interpretability in Generative AI
Exploration of explainability and interpretability techniques for generative AI systems.
Sep 15, 2024 YRRSDS 2024; SIGDIAL 2024 Kyoto University, Kyoto, Japan
Shiyuan Huang