FAPO automates LLM pipeline optimization via iterative diagnosis and prompt-or-structure edits, beating GEPA baseline by +14.1 pp mean across 18 comparisons and +33.8 pp when structural changes occur.
PAPILLON: Privacy preservation from Internet-based and local language model ensembles
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
AURA is an LLM mask-reconstruct anonymization method that improves resistance to agentic web-search re-identification on interview transcripts while retaining contextual utility.
GEPA outperforms GRPO by 6% on average (up to 20%) across six tasks using up to 35x fewer rollouts and beats MIPROv2 by over 10%.
citing papers explorer
-
FAPO: Fully Automated Prompt Optimization of Multi-Step LLM Pipelines
FAPO automates LLM pipeline optimization via iterative diagnosis and prompt-or-structure edits, beating GEPA baseline by +14.1 pp mean across 18 comparisons and +33.8 pp when structural changes occur.
-
LLM Anonymization Against Agentic Re-Identification
AURA is an LLM mask-reconstruct anonymization method that improves resistance to agentic web-search re-identification on interview transcripts while retaining contextual utility.
-
GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
GEPA outperforms GRPO by 6% on average (up to 20%) across six tasks using up to 35x fewer rollouts and beats MIPROv2 by over 10%.