Pith. sign in

REVIEW 4 cited by

Causal Abstractions of 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 2106.02997 v2 pith:5IEDEVPE submitted 2021-06-06 cs.AI cs.LG

classification cs.AIcs.LG
keywords causalneuralmodelrepresentationsanalysismethodnaturalstructure
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Structural analysis methods (e.g., probing and feature attribution) are increasingly important tools for neural network analysis. We propose a new structural analysis method grounded in a formal theory of causal abstraction that provides rich characterizations of model-internal representations and their roles in input/output behavior. In this method, neural representations are aligned with variables in interpretable causal models, and then interchange interventions are used to experimentally verify that the neural representations have the causal properties of their aligned variables. We apply this method in a case study to analyze neural models trained on Multiply Quantified Natural Language Inference (MQNLI) corpus, a highly complex NLI dataset that was constructed with a tree-structured natural logic causal model. We discover that a BERT-based model with state-of-the-art performance successfully realizes parts of the natural logic model's causal structure, whereas a simpler baseline model fails to show any such structure, demonstrating that BERT representations encode the compositional structure of MQNLI.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. LAWFUL: Law-Aligned Witness for Faithful Use of Latents

    cs.LG 2026-07 conditional novelty 7.0 of 10

    LAWFUL defines coverage-aware physical-consistency scores and circuit tests, reporting that a MoCap-to-Radar transformer's 9-component temporal circuit carries Doppler-law consistency via attention patterns.

  2. Emergent Misalignment Recruits a Pre-existing Persona Subspace

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Fine-tuning on narrow bad data recruits a low-rank persona subspace already present in a frozen instruction-tuned model; holding that subspace out of activations prevents broad misalignment, and injecting it into the ...

  3. Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race

    cs.CL 2025-05 conditional novelty 7.0 of 10

    Alignment on Llama 3 reduces explicit bias but amplifies implicit bias, because aligned models no longer represent 'black' and 'white' as racial concepts in ambiguous contexts.

  4. Explaining Neural Networks with Reasons

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A new interpretability method computes 'reasons vectors' from neuron activations and measures how strongly each neuron supports propositions about the input, with experiments on MNIST, Adult, and SST2.

Pith tools