Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models

TL;DR

This paper introduces ENVISIONS, a neural-symbolic self-training framework that enhances large language models' ability to process symbolic language and addresses data scarcity, demonstrating effectiveness across multiple domains.

Contribution

The paper presents a novel environment-guided neural-symbolic self-training framework called ENVISIONS, specifically designed for improving LLMs in symbolic language scenarios.

Findings

Effective across three different domains

Addresses symbolic data scarcity and LLM proficiency issues

Provides insights into factors influencing success

Abstract

One of the primary driving forces contributing to the superior performance of Large Language Models (LLMs) is the extensive availability of human-annotated natural language data, which is used for alignment fine-tuning. This inspired researchers to investigate self-training methods to mitigate the extensive reliance on human annotations. However, the current success of self-training has been primarily observed in natural language scenarios, rather than in the increasingly important neural-symbolic scenarios. To this end, we propose an environment-guided neural-symbolic self-training framework named ENVISIONS. It aims to overcome two main challenges: (1) the scarcity of symbolic data, and (2) the limited proficiency of LLMs in processing symbolic language. Extensive evaluations conducted on three distinct domains demonstrate the effectiveness of our approach. Additionally, we have conducted a comprehensive analysis to uncover the factors contributing to ENVISIONS's success, thereby offering valuable insights for future research in this area. Code will be available at \url{https://github.com/xufangzhi/ENVISIONS}.