SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking
This addresses the problem of integrating persona and commonsense knowledge in dialogue systems for NLP researchers, though it is incremental as it builds on existing LLM and dataset methods.
The paper tackled the challenge of retrieving commonsense persona knowledge for open-domain dialogue systems by introducing SynCPKL, a pipeline that uses LLMs to generate synthetic training data, resulting in a model that achieved a 16% F1 score improvement and first place in the CPKL challenge.
Understanding rich dialogues often requires NLP systems to access relevant commonsense persona knowledge, but retrieving this knowledge is challenging due to complex contexts and the implicit nature of commonsense. This paper presents our approach to the Commonsense Persona Knowledge Linking (CPKL) challenge, addressing the critical need for integrating persona and commonsense knowledge in open-domain dialogue systems. We introduce SynCPKL Pipeline, a pipeline that leverages Large Language Models to generate high-quality synthetic datasets for training commonsense persona knowledge linkers. To demonstrate the efficacy of our approach, we present SynCPKL, a new dataset specifically designed for this task. Our experiments validate the effectiveness of SynCPKL for training commonsense persona knowledge linkers. Additionally, our top-performing model, Derberta-SynCPKL, secured first place in the CPKL challenge by a 16% improvement in F1 score. We released both SynCPKL and Derberta-SynCPKL at https://github.com/irislin1006/CPKL.