Citekit: A Modular Toolkit for Large Language Model Citation Generation

TL;DR

Citekit is an open-source, modular toolkit designed to standardize, evaluate, and improve citation generation methods in large language models, enhancing answer accuracy and citation quality in QA tasks.

Contribution

It provides a flexible framework for implementing and comparing citation methods, and introduces a new balanced approach called self-RAG.

Findings

Different modules have varying strengths in answer accuracy and citation quality.

Enhancing citation granularity remains challenging.

Self-RAG achieves a good balance between answer accuracy and citation quality.

Abstract

Enabling Large Language Models (LLMs) to generate citations in Question-Answering (QA) tasks is an emerging paradigm aimed at enhancing the verifiability of their responses when LLMs are utilizing external references to generate an answer. However, there is currently no unified framework to standardize and fairly compare different citation generation methods, leading to difficulties in reproducing different methods and a comprehensive assessment. To cope with the problems above, we introduce \name, an open-source and modular toolkit designed to facilitate the implementation and evaluation of existing citation generation methods, while also fostering the development of new approaches to improve citation quality in LLM outputs. This tool is highly extensible, allowing users to utilize 4 main modules and 14 components to construct a pipeline, evaluating an existing method or innovative designs. Our experiments with two state-of-the-art LLMs and 11 citation generation baselines demonstrate varying strengths of different modules in answer accuracy and citation quality improvement, as well as the challenge of enhancing granularity. Based on our analysis of the effectiveness of components, we propose a new method, self-RAG \snippet, obtaining a balanced answer accuracy and citation quality. Citekit is released at https://github.com/SjJ1017/Citekit.