---
format: "aidr-story-markdown/v1"
id: "d4491b2e5eb509cb96c17ea906580b3ee708bad8aa927ad513d35ff9f6692e2a"
canonical_url: "https://aidr.today/d4491b2e?lang=en"
title: "Automating literature screening and knowledge synthesis with large language models"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-17T05:00:00.000Z"
category: "Research"
topics: ["llm"]
source_urls: ["https://arxiv.org/abs/2611.18588"]
summary: "A new large language model (LLM)-powered framework automates literature screening, structured information extraction, and knowledge synthesis. In benchmarks across three materials science tasks, seven LLMs achieved balanced accuracies above 0.90, with the best performing model reaching 0.96--0.98. The framework screened 10,000 records in four minutes, compared to approximately 83 person-hours for manual screening."
---

# Automating literature screening and knowledge synthesis with large language models

> [Open the canonical story](<https://aidr.today/d4491b2e?lang=en>)

**Published:** 2026-11-17T05:00:00.000Z
**Category:** Research
**Topics:** llm

## Summary

A new large language model \(LLM\)\-powered framework automates literature screening, structured information extraction, and knowledge synthesis\. In benchmarks across three materials science tasks, seven LLMs achieved balanced accuracies above 0\.90, with the best performing model reaching 0\.96\-\-0\.98\. The framework screened 10,000 records in four minutes, compared to approximately 83 person\-hours for manual screening\.

## Sources

- [Story source](<https://arxiv.org/abs/2611.18588>)

