Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models
This survey addresses the problem of inconsistent terminology and evaluation in evidence-based text generation for researchers and practitioners, but it is incremental as it synthesizes existing work rather than proposing new methods.
The paper tackles the fragmentation in evidence-based text generation with large language models by systematically analyzing 134 papers, introducing a unified taxonomy, and investigating 300 evaluation metrics across seven dimensions to improve traceability and verifiability.
The increasing adoption of large language models (LLMs) has been accompanied by growing concerns regarding 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.