arXiv AI
Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 19
RAW-Explainer: Post-hoc Explanations of Path Reasoning Graph Neural Networks for Knowledge Graph Completion
RAW-Explainer is a new explainability method designed for path reasoning graph neural networks used in knowledge graph completion. It produces connected, concise, and interpretable subgraph explanations for link prediction by leveraging heterogeneous information and a random walk objective. The approach also addresses distribution shift when evaluating small explanatory subgraphs with a robust evaluator, achieving a balance between explanation quality and computational efficiency on standard benchmarks.
arXiv Machine Learning
Jul 7
Measuring What Matters: A Unified Evaluation Framework for GNN Explainability
arXiv:2607. 04600v1 Announce Type: new Abstract: Graph eXplainable AI (G-XAI) is increasingly important for making Graph Neural Networks interpretable and accountable.
Hugging Face Trending Papers
Jul 6
Measuring What Matters: A Unified Evaluation Framework for GNN Explainability
Graph eXplainable AI (G-XAI) is increasingly important for making Graph Neural Networks interpretable and accountable. While a growing number of explainers are available, choosing the right method and assessing the trustworthiness of its outputs remains unclear.
arXiv AI
Jun 16
VeriGraph: Towards Verifiable Data-Analytic Agents
arXiv:2606. 16603v1 Announce Type: cross Abstract: LLM-based agents have demonstrated strong capabilities in data-intensive analytical tasks, yet their outputs are rarely verifiable: a reliance on linear text trajectories makes their reasoning difficult to audit.
arXiv AI
Jun 24
Rule2Text: A Framework for Generating and Evaluating Natural Language Explanations of Knowledge Graph Rules
arXiv:2508. 10971v2 Announce Type: replace-cross Abstract: Knowledge graphs (KGs) can be enhanced through rule mining; however, the resulting logical rules are often difficult for humans to interpret due to their inherent complexity and the idiosyncratic labeling conventions of individual KGs.
arXiv Computation and Language
Sep 22
Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics
Euston is an 8‑B parameter mathematical claim‑verification model that resists producing false derivations when presented with corrupted theorems. It was trained on 3,026 matched true/corrupted statement pairs generated by GraphSynth, a probabilistic factor‑graph generator, and fine‑tuned from DeepSeek‑R1‑8B using GRPO. On a balanced held‑out split, Euston’s balanced accuracy rose from 29.50 % to 63.75 %, and its discrimination gap improved from –0.5 % to +27.5 %, while maintaining comparable general mathematical ability and reducing response length and truncation rates.