Tag

CaPO

1 views collected around this technical thread.

Kuaishou Tech
Kuaishou Tech
Jul 23, 2024 · Artificial Intelligence

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.

AI researchCaPOMulti-turn Dialogue
0 likes · 9 min read
Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models