# PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews

arXiv: https://arxiv.org/abs/2609.11559 · HTML: https://mlsanity.com/paper/2609.11559/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 19 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 4 of 4)

- [The emergence of Large Language Models (LLM) as a tool in literature reviews: an LLM automated systematic review](https://mlsanity.com/paper/2409.04600/) (2024)
- [PRISMA-DFLLM: An Extension of PRISMA for Systematic Literature Reviews using Domain-specific Finetuned Large Language Models](https://mlsanity.com/paper/2306.14905/) (2023)
- [L-PRISMA: An Extension of PRISMA in the Era of Generative Artificial Intelligence (GenAI)](https://mlsanity.com/paper/2603.19236/) (2026)
- [SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews](https://mlsanity.com/paper/2609.05505/) (2026)

## Abstract (arXiv)

Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023, 38.0% of software/product papers reported no evaluation, compared with 9.3% of LLM papers. Reporting coverage increased with LLM workflow complexity, yet 52% of positive-only LLM evaluations still reported an unmet reliability or performance requirement. From these patterns, we introduce PRISMA-LLM, an empirically grounded framework separating implementation disclosure from consequence-sensitive evaluation and limitation reporting.