Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models
This addresses the need for reducing reliance on human annotations in neural-symbolic tasks, though it appears incremental as it extends self-training methods to a new scenario.
The paper tackles the problem of self-training for large language models in neural-symbolic scenarios, where there is a scarcity of symbolic data and limited LLM proficiency, by proposing the ENVISIONS framework, which demonstrates effectiveness across three distinct domains.
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}.