3 citations · 3 across the 4 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis
Shuzhi Gong, Hechuan Wen
Automated prompt optimization methods (e.g., DSpy, TextGrad) can substantially improve the performance of large language model (LLM), however, their generalization ability across d…
cs.AI2026
Multi-Sourced, Multi-Agent Evidence Retrieval for Fact-Checking
Shuzhi Gong, Richard O. Sinnott, Jianzhong Qi +3
Misinformation spreading over the Internet poses a significant threat to both societies and individuals, necessitating robust and scalable fact-checking that relies on retrieving a…