Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Semantic Energy: Detecting LLM Hallucination Beyond Entropy
Huan Ma, Jiadong Pan, Jing Liu +7
Large Language Models (LLMs) are being increasingly deployed in real-world applications, but they remain susceptible to hallucinations, which produce fluent yet incorrect responses…
cs.LG2023
Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Huan Ma, Changqing Zhang, Huazhu Fu +2
Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making…