Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Automatic Layer Selection for Hallucination Detection
Xinpeng Wang, William X. Cao, Andrew Gordon Wilson +1
Recent studies on hallucination detection have shown that hallucination-related signals are more strongly encoded in intermediate layers than in the final layer of large language m…
cs.AI2024
On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models
Xinpeng Wang, Shitong Duan, Xiaoyuan Yi +7
Big models have achieved revolutionary breakthroughs in the field of AI, but they might also pose potential concerns. Addressing such concerns, alignment technologies were introduc…