TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models

TL;DR

TongGu is a specialized large language model designed for Classical Chinese understanding, utilizing a new dataset, a novel tuning method to retain knowledge, and retrieval-augmented generation to improve accuracy and reduce hallucinations.

Contribution

The paper introduces TongGu, the first CCU-specific LLM, with a new dataset, redundancy-aware tuning, and retrieval-augmented generation techniques for improved classical Chinese comprehension.

Findings

TongGu outperforms existing models on 24 CCU tasks.

Redundancy-Aware Tuning prevents catastrophic forgetting.

Retrieval-Augmented Generation reduces hallucinations in outputs.

Abstract

Classical Chinese is a gateway to the rich heritage and wisdom of ancient China, yet its complexities pose formidable comprehension barriers for most modern people without specialized knowledge. While Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), they struggle with Classical Chinese Understanding (CCU), especially in data-demanding and knowledge-intensive tasks. In response to this dilemma, we propose \textbf{TongGu} (mean understanding ancient and modern), the first CCU-specific LLM, underpinned by three core contributions. First, we construct a two-stage instruction-tuning dataset ACCN-INS derived from rich classical Chinese corpora, aiming to unlock the full CCU potential of LLMs. Second, we propose Redundancy-Aware Tuning (RAT) to prevent catastrophic forgetting, enabling TongGu to acquire new capabilities while preserving its foundational knowledge. Third, we present a CCU Retrieval-Augmented Generation (CCU-RAG) technique to reduce hallucinations based on knowledge-grounding. Extensive experiments across 24 diverse CCU tasks validate TongGu's superior ability, underscoring the effectiveness of RAT and CCU-RAG. The model and dataset are available at \url{https://github.com/SCUT-DLVCLab/TongGu-LLM}.