Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
Neural causal discovery methods have recently improved in terms of scalability and computational efficiency. However, our systematic evaluation highlights significant room for improvement in their accuracy when uncovering causal structures. We identify a fundamental limitation: neural networks cannot reliably distinguish between existing and non-existing causal relationships in the finite sample regime. Our experiments reveal that neural networks, as used in contemporary causal discovery approaches, lack the precision needed to recover ground-truth graphs, even for small graphs and relatively large sample sizes. Furthermore, we identify the faithfulness property as a critical bottleneck: (i) it is likely to be violated across any reasonable dataset size range, and (ii) its violation directly undermines the performance of neural discovery methods. These findings lead us to conclude that progress within the current paradigm is fundamentally constrained, necessitating a paradigm shift in this domain.
Code (0)
등록된 구현이 없습니다.
Tasks
Causal DiscoveryComputational EfficiencySimilar Papers 제목 키워드 기반
Statistical Undecidability in Linear, Non-Gaussian Causal Models in the Presence of Latent Confounders
If causal relationships are linear and acyclic and noise terms are independent and Gaussian, causal orientation is not identified from observational data --- even if faithfulness is satisfied (Spirtes et al., 2002). Shim…
dcFCI: Robust Causal Discovery Under Latent Confounding, Unfaithfulness, and Mixed Data
Causal discovery is central to inferring causal relationships from observational data. In the presence of latent confounding, algorithms such as Fast Causal Inference (FCI) learn a Partial Ancestral Graph (PAG) represent…
Causal DiscoveryCausal InferenceIs Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
Recent work, using the Biasing Features metric, labels a CoT as unfaithful if it omits a prompt-injected hint that affected the prediction. We argue this metric adopts a narrow notion of faithfulness and confuses unfaith…
CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
Large language models (LLMs) enable waveform-to-text ECG interpretation and interactive clinical questioning, yet most ECG-LLM systems still rely on weak signal-text alignment and retrieval without explicit physiological…
Representation LearningTowards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
Large Language Models (LLMs) are capable of generating persuasive Natural Language Explanations (NLEs) to justify their answers. However, the faithfulness of these explanations should not be readily trusted at face value…