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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add graph-log multimodal alignment (ablation) | GARNET · AIT fox | F1: 0.4308 -> 0.7083 | Improved |
| add graph-log semantic alignment (ablation) | GARNET · AIT fox | F1: 0.5333 -> 0.7083 | Improved |
| use a reasoning base LLM instead of non-reasoning (ablation) | GARNET · AIT fox | F1: 0.1714 -> 0.7083 | Improved |
| add attack path reconstruction (ablation) | GARNET · AIT fox | FPR: 0.4194 -> 0.0000 | Improved |
| add abundant path removal (ablation) | GARNET · AIT fox | TPR / FPR: TPR 0.8065 -> 0.5484; FPR 0.0137 -> 0.0000 | Mixed |
| use GARNET instead of DS-r1 alone | DeepSeek-R1 reasoning · AIT wilson | F1: 0.6316 -> 0.4490 | Hurt |
| use GARNET instead of NoDoze | graph-based alert reduction · AIT fox | F1: 0.4364 -> 0.7083 | Improved |
| add reasoning mechanism to LLM baseline (DS-r1 vs DS-chat) | DeepSeek LLM baselines · AIT fox | F1: 0.2000 -> 0.4545 | Improved |
Closest papers by meaning
- Talk like a Graph: Encoding Graphs for Large Language Models (ICLR 2024 · similarity 0.83)
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning (ICLR 2024 · similarity 0.82)
- GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling (NeurIPS 2025 · similarity 0.82)
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph (ICLR 2024 · similarity 0.82)
- Interpreting Temporal Knowledge Graph Reasoning (Student Abstract) (AAAI 2024 · similarity 0.82)
- FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning (ICLR 2026 · similarity 0.82)
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.
