Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA

TL;DR

This paper introduces Notes Writing, a method that enhances iterative retrieval-augmented generation by generating concise notes from retrieved documents, improving reasoning over large contexts in complex question answering tasks.

Contribution

It presents a scalable, model-agnostic notes writing approach that reduces irrelevant information and effectively increases context length for better reasoning in iterative RAG systems.

Findings

Average improvement of 15.6 percentage points across datasets

Effective integration with multiple RAG methods and models

Minimal increase in output tokens

Abstract

Iterative RAG for multi-hop question answering faces challenges with lengthy contexts and the buildup of irrelevant information. This hinders a model's capacity to process and reason over retrieved content and limits performance. While recent methods focus on compressing retrieved information, they are either restricted to single-round RAG, require finetuning or lack scalability in iterative RAG. To address these challenges, we propose Notes Writing, a method that generates concise and relevant notes from retrieved documents at each step, thereby reducing noise and retaining only essential information. This indirectly increases the effective context length of Large Language Models (LLMs), enabling them to reason and plan more effectively while processing larger volumes of input text. Notes Writing is framework agnostic and can be integrated with different iterative RAG methods. We demonstrate its effectiveness with three iterative RAG methods, across two models and four evaluation datasets. Notes writing yields an average improvement of 15.6 percentage points overall, with minimal increase in output tokens.