It is shown that intervention-based faithfulness can prefer an equally sized circuit that reproduces the model's behavior less well, and restoring selected intact-model signals reverses 96 of 100 selected persistent misrankings, demonstrating that context distortion contributes to these failures.
Chu-Qin Geng, Li Zhang, Hao-Lin Ye et al.· 0 citations
Neuro-Symbolic Graph Generative Modeling (NSGGM), a framework built on the principle of Neural Proposals, Symbolic Guarantees, is introduced, and is competitive with state-of-the-art methods on unconstrained tasks.
Chu-Qin Geng, Li Zhang, Mark Zhang et al.· 0 citations
Findings show circuits can preserve task success without adequately explaining model's failures, and support exact error reproduction as a necessary, but not sufficient, test of circuit-based explanations of model behaviour.
Li Zhang, Chu-Qin Geng, Mark Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.