Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models

TL;DR

This survey analyzes 134 papers on evidence-based text generation with LLMs, introduces a unified taxonomy, and investigates evaluation metrics to improve traceability and trustworthiness.

Contribution

It provides a comprehensive taxonomy and evaluation framework for evidence-based text generation with LLMs, addressing fragmentation in the field.

Findings

Analyzed 134 papers on evidence-based text generation.

Investigated 300 evaluation metrics across seven dimensions.

Highlighted open challenges and future research directions.

Abstract

The increasing adoption of large language models (LLMs) has raised serious concerns about their reliability and trustworthiness. As a result, a growing body of research focuses on evidence-based text generation with LLMs, aiming to link model outputs to supporting evidence to ensure traceability and verifiability. However, the field is fragmented due to inconsistent terminology, isolated evaluation practices, and a lack of unified benchmarks. To bridge this gap, we systematically analyze 134 papers, introduce a unified taxonomy of evidence-based text generation with LLMs, and investigate 300 evaluation metrics across seven key dimensions. Thereby, we focus on approaches that use citations, attribution, or quotations for evidence-based text generation. Building on this, we examine the distinctive characteristics and representative methods in the field. Finally, we highlight open challenges and outline promising directions for future work.