Work

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

Year: 2025

Type: conference-paper

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 selftraining 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 neuralsymbolic scenarios.To this end, we propose an environment-guided neural-symbolic selftraining 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.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2025.acl-long.635

Authors: Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, Jun Liu, Yu Qiao, Zhiyong Wu

Institutions: University of Hong Kong, Nanjing University, Shanghai Artificial Intelligence Laboratory

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Natural Science Foundation of China, Xi’an Jiaotong University, Housing and Building National Research Center, National Key Research and Development Program of China