Pith. sign in

REVIEW 1 cited by

Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.04690 v1 pith:4NOURMLE submitted 2024-07-05 cs.LG cs.CL

classification cs.LGcs.CL
keywords counterfactualcausesmethodsnetworksneuralcausalchallengescounterfactuals
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Interpretability research takes counterfactual theories of causality for granted. Most causal methods rely on counterfactual interventions to inputs or the activations of particular model components, followed by observations of the change in models' output logits or behaviors. While this yields more faithful evidence than correlational methods, counterfactuals nonetheless have key problems that bias our findings in specific and predictable ways. Specifically, (i) counterfactual theories do not effectively capture multiple independently sufficient causes of the same effect, which leads us to miss certain causes entirely; and (ii) counterfactual dependencies in neural networks are generally not transitive, which complicates methods for extracting and interpreting causal graphs from neural networks. We discuss the implications of these challenges for interpretability researchers and propose concrete suggestions for future work.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Stochastic Parameter Decomposition

    cs.LG 2025-06 conditional novelty 6.0 of 10

    SPD uses stochastic masking and a learned causal importance function to decompose neural network parameters into sparsely active rank-one subcomponents, recovering ground-truth mechanisms in toy models where APD struggled.

Pith tools