lrp

This paper introduces MemExplainer, a method to explain predictions of Temporal Graph Networks (TGNs) by attributing contributions through topology attribution trees and memory backtracking trees, using Layer-wise Relevance Propagation (LRP) for faithful explanations.

Researchers apply contrastive LRP-based attribution to analyze why LLMs fail on realistic benchmarks, finding the method gives useful signals in some cases but is not universally reliable.