Research map / Graph learning / Knowledge and temporal graphs
Reasoning on Knowledge Graphs with Debate Dynamics
Marcel Hildebrandt, Jorge Andres Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin, Volker Tresp
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 fixed pretrained TransE embeddings (ablation) | R2D2 · WN18RR | PR AUC: 0.821 -> 0.909 | Improved |
| add fixed pretrained TransE embeddings (ablation) | R2D2 · WN18RR | ROC AUC: 0.808 -> 0.893 | Improved |
| add fixed pretrained TransE embeddings (ablation) | R2D2 · FB15k-237 | accuracy: 0.751 -> 0.764 | Improved |
| add fixed pretrained TransE embeddings (ablation) | R2D2 · FB15k-237 | PR AUC: 0.86 -> 0.865 | Improved |
| add fixed pretrained TransE embeddings (ablation) | R2D2 · FB15k-237 | ROC AUC: 0.848 -> 0.857 | Improved |
| replace the judge's feed-forward processing of arguments with a recurrent neural network (ablation) | R2D2 · triple classification | classification performance | Hurt |
| ignore agent 2's arguments during testing (ablation) | R2D2 · FB15k-237 | positive predictions: +18.8% | Improved |
| ignore agent 1's arguments during testing (ablation) | R2D2 · FB15k-237 | positive predictions: -70.2% | Hurt |
Closest papers by meaning
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.87)
- When Debate Helps: Proposal Supply and Verification-Aware Readout in Multi-Agent Reasoning (NeurIPS 2026 · similarity 0.86)
- Multi-Agent Debate for LLM Judges with Adaptive Stability Detection (NeurIPS 2025 · similarity 0.86)
- Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains (NeurIPS 2026 · similarity 0.86)
- Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Exploration (AAAI 2025 · similarity 0.85)
- $\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning (NeurIPS 2025 · similarity 0.85)
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.
