AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Neural Message-Passing on Attention Graphs for Hallucination Detection

Fabrizio Frasca, Guy Bar-Shalom, Yftah Ziser, Haggai Maron

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: Brain and biological graph learning · 3 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
use CHARM (GNN on attention graphs) instead of Lookback Lenshallucination detector · NQ (token-level)AUPR (%): 34.3 -> 40.3Improved
use CHARM instead of Lookback Lenshallucination detector · CNN (token-level)AUROC (%): 74.4 -> 75.4Improved
add layer-24 activations to node features (ablation)CHARM · NQ (token-level)AUPR (%): 40.3 -> 35.5Hurt
add layer-24 activations to node features (ablation)CHARM · CNN (token-level)AUROC (%): 75.4 -> 70.9Hurt
add layer-24 activations to node features (ablation)CHARM · Winobias (response-level)AUROC (%): 70.4 -> 77.8Improved
add layer-24 activations to node features (ablation)CHARM · Math (response-level)AUROC (%): 76.5 -> 80.8Improved
add layer-24 activations to node features (ablation)CHARM · Movies (response-level)AUROC (%): 80.3 -> 79.7No clear effect
use message passing on the attention graph instead of dense layers over nodes (ablation)CHARM · CNN (token-level)AUROC (%): 70.8 -> 75.4Improved
use message passing on the attention graph instead of dense layers (ablation)CHARM · Math (response-level)AUROC (%): 80.6 -> 81.7Improved
sparsify attention graph with higher threshold tau 0.5 instead of 0.05 (ablation)CHARM · NQ (token-level)AUPR (%): 40.3 -> 38.4Hurt
sparsify with tau=0.05 instead of 0.001 (ablation)CHARM · NQ (token-level)AUPR (%): 40.1 -> 40.3No clear effect
use CHARM for zero-shot transfer instead of Lookback Lenshallucination detector · NQ -> CNN and CNN -> NQAUROC (%): NQ->CNN 68.6 -> 64.1; CNN->NQ 62.0 -> 65.5Mixed

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