Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models

This paper introduces Parrot, a system that enhances large language models' (LLMs) multi-turn instruction following capabilities through context-aware preference optimization (CaPO) and synthetic data generation, achieving significant performance improvements with limited training data.

CaPONLPdata synthesis

0 likes · 9 min read

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models