AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

GARNET: GoT-Based Alert Reduction and Narrative Event Tracing

Yiru Gong, Song Liu, Changzhi Zhao, Junrong Liu, Tian Tian, Xiaobo Yang, Bo Jiang, Zhigang Lu

AAAI 2026 · Large language models › Retrieval and knowledge · approach: Domain-specific QA datasets · 0 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 graph-log multimodal alignment (ablation)GARNET · AIT foxF1: 0.4308 -> 0.7083Improved
add graph-log semantic alignment (ablation)GARNET · AIT foxF1: 0.5333 -> 0.7083Improved
use a reasoning base LLM instead of non-reasoning (ablation)GARNET · AIT foxF1: 0.1714 -> 0.7083Improved
add attack path reconstruction (ablation)GARNET · AIT foxFPR: 0.4194 -> 0.0000Improved
add abundant path removal (ablation)GARNET · AIT foxTPR / FPR: TPR 0.8065 -> 0.5484; FPR 0.0137 -> 0.0000Mixed
use GARNET instead of DS-r1 aloneDeepSeek-R1 reasoning · AIT wilsonF1: 0.6316 -> 0.4490Hurt
use GARNET instead of NoDozegraph-based alert reduction · AIT foxF1: 0.4364 -> 0.7083Improved
add reasoning mechanism to LLM baseline (DS-r1 vs DS-chat)DeepSeek LLM baselines · AIT foxF1: 0.2000 -> 0.4545Improved

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