Research

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment, AAAI 2024

Align-Pro is a principled approach to prompt optimization for LLM alignment. It is a framework that uses reinforcement learning to optimize the prompts of LLMs to achieve better alignment with human values and goals.

Status: published

Multi-Objective Optimization in AI

Exploring new algorithms for multi-objective optimization in artificial intelligence.

Status: ongoing