AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates

Shuaimin Li, Liyang Fan, Yufang Lin, Zeyang Li, Xian Wei, Shiwen Ni, Hamid Alinejad-Rokny, Min Yang

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add title node (ablation)ReViewGraph · ICLR 2025accuracy: 66.49 -> 71.65Improved
add title node (ablation)ReViewGraph · ICLR 2023accuracy: 67.03 -> 70.29Improved
add title node (ablation)ReViewGraph · ICLR 2024accuracy: 64.73 -> 66.10Improved
add evaluation dimension nodes (ablation)ReViewGraph · ICLR 2025accuracy: 68.30 -> 71.65Improved
add reviewer-author interaction edges (ablation)ReViewGraph · ICLR 2025accuracy: 70.36 -> 71.65Improved
add reviewer-author interaction edges (ablation)ReViewGraph · ICLR 2023accuracy: 69.57 -> 70.29Improved
add inter-reviewer relation edges (ablation)ReViewGraph · ICLR 2025accuracy: 69.59 -> 71.65Improved
use heterogeneous graph instead of homogeneous (ablation)ReViewGraph · ICLR 2025accuracy: 70.62 -> 71.65Improved
use heterogeneous graph instead of homogeneous (ablation)ReViewGraph · ICLR 2024accuracy: 65.75 -> 66.10No clear effect
ReViewGraph vs CycleReviewer-70B (fine-tuned) baselineReViewGraph · ICLR 2025 macro F1accuracy: 59.26 -> 71.65Improved
ReViewGraph vs ICL prompting baselineReViewGraph · ICLR 2023accuracy: 58.33 -> 70.29Improved
debate-graph model vs DeepReview-14B-StdReViewGraph · ICLR 2024accuracy: 59.93 -> 66.10Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy