Attribute First, then Generate: Locally-attributable Grounded Text Generation

TL;DR

This paper proposes a three-step method for grounded text generation that improves attribution precision, reduces verification effort, and maintains or enhances quality in multi-document summarization and long-form QA tasks.

Contribution

It introduces a locally-attributable generation approach that emphasizes concise, fine-grained source attributions by separating content selection, sentence planning, and generation.

Findings

More concise citations than baselines

Maintains or improves generation quality

Reduces human fact verification time

Abstract

Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections. Yet, these citations often point to entire documents or paragraphs, burdening users with extensive verification work. In this paper, we introduce a locally-attributable text generation approach, prioritizing concise attributions. Our method, named "Attribute First, then Generate", breaks down the conventional end-to-end generation process into three intuitive steps: content selection, sentence planning, and sequential sentence generation. By initially identifying relevant source segments ("select first") and then conditioning the generation process on them ("then generate"), we ensure these segments also act as the output's fine-grained attributions ("select" becomes "attribute"). Tested on Multi-document Summarization and Long-form Question-answering, our method not only yields more concise citations than the baselines but also maintains - and in some cases enhances - both generation quality and attribution accuracy. Furthermore, it significantly reduces the time required for fact verification by human assessors.