Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
Shiyan Liu, Qifeng Xia, Qiyun Xia +3
Automatic prompt optimization (APO) has emerged as a powerful paradigm for improving LLM performance without manual prompt engineering. Reflective APO methods such as GEPA iterativ…
cs.AI2025
DICE: Discrete Interpretable Comparative Evaluation with Probabilistic Scoring for Retrieval-Augmented Generation
Shiyan Liu, Jian Ma, Rui Qu
As Retrieval-Augmented Generation (RAG) systems evolve toward more sophisticated architectures, ensuring their trustworthiness through explainable and robust evaluation becomes cri…