Research map / Large language models / Agents, code and math
Large Language Models as Topological Thinkers: A Benchmark on Graph Persistent Homology
Hao Li, Hao Wan, Yixue Huang, Yuzhou Chen, Yulia Gel, Hao Jiang
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 supervised fine-tuning on small graphs (ablation) | LLaMA-3.1-8B-Instruct · 1D Simplex Counting (medium graphs) | accuracy: 0.02 -> 0.20 | Improved |
| add supervised fine-tuning on small graphs (ablation) | LLaMA-3.1-8B-Instruct · Component Merge Time | accuracy: 0.09 -> 0.43 | Improved |
| add supervised fine-tuning on small graphs (ablation) | LLaMA-3.1-8B-Instruct · Component Count Under Filtration | accuracy: 0.16 -> 0.66 | Improved |
| transfer model tuned on small graphs to large graphs (ablation) | LLaMA-3.1-8B-Instruct · 1D Simplex Counting (large graphs) | accuracy: 0.005 -> 0.235 | Improved |
| use text-style graph input instead of matrix-based input (ablation) | LLMs · LLM4PH prompt ablation | accuracy | Improved |
| use graph-theoretic phrasing instead of topological phrasing (ablation) | LLMs · LLM4PH prompt ablation | accuracy | Mixed |
| use PH terminology instead of graph-theoretic terms (ablation) | GPT-4o · Component Count Under Filtration | accuracy | Hurt |
| add few-shot CoT or rule-emphasized prompting (ablation) | LLMs · Non-Uniform Filtration Generation | rank | No clear effect |
| increase number of sampled ego-Facebook subgraphs from 10 to 150 (ablation) | GPT-4.1-mini · 1D Simplex Counting | accuracy: 14% -> 24% | Improved |
| let model generate persistence diagrams instead of code (ablation) | LLM-PH hybrid pipeline · BZR classification | accuracy | Hurt |
| let model compare diagram distances in hybrid pipeline (ablation) | Claude and DS-V3 · BZR classification | accuracy: 0.840 | Improved |
| use direct classification instead of PH-guided filtration design | LLMs · real-world graph classification | accuracy: 0.98 to 1.0 | Improved |
Closest papers by meaning
- How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehension (ICLR 2025 · similarity 0.89)
- Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties (NeurIPS 2025 · similarity 0.89)
- Persistent Topological Features in Large Language Models (ICML 2025 · similarity 0.89)
- Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain (ICLR 2026 · similarity 0.88)
- Talk like a Graph: Encoding Graphs for Large Language Models (ICLR 2024 · similarity 0.88)
- Beyond Graphs: Can Large Language Models Comprehend Hypergraphs? (ICLR 2025 · similarity 0.88)
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.
