# Context-Efficient Retrieval with Factual Decomposition

Source: [Context-Efficient Retrieval with Factual Decomposition](<https://www.sota2.com/research/paper/68fa779e1e209131cea7468f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:23:33.312Z

Authors: Yanhong Li, David Yunis, David McAllester, Jiawei Zhou

Published: 2025-03-25T11:48:22.000Z

## Abstract

There has recently been considerable interest in incorporating information retrieval into large language models (LLMs). Retrieval from a dynamically expanding external corpus of text allows a model to incorporate current events and can be viewed as a form of episodic memory. Here we demonstrate that pre-processing the external corpus into semi-structured ''atomic facts'' makes retrieval more efficient. More specifically, we demonstrate that our particular form of atomic facts improves performance on various question answering tasks when the amount of retrieved text is limited. Limiting the amount of retrieval reduces the size of the context and improves inference efficiency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2503.19574>)

[PDF](<https://arxiv.org/pdf/2503.19574.pdf>)
