Research map / Probabilistic and scientific modeling / Causal discovery
CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| approximate-counterfactual baseline vs other concept explanation methods | concept-based explainers (CONEXP, TCAV, ConceptSHAP, INLP, CausaLM, S-Learner) · CEBaB, bert-base-uncased 5-way | ICaCE-Error (cosine, L2, normdiff) | Helped |
| give explainer intervention direction and predicted aspect labels at test time (Approx, S-Learner) | concept explainers · CEBaB, bert-base-uncased 5-way | ICaCE-Error | Helped |
| INLP vs approximate counterfactual baseline | INLP · CEBaB, bert-base-uncased 5-way | ICaCE-Error (cosine) | No clear effect |
| use CausaLM (adversarially retrained model) vs INLP probes on original model | concept explainers · CEBaB, bert-base-uncased 5-way | ICaCE-Error | Hurt |
Closest papers by meaning
- Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals (ICLR 2024 · similarity 0.88)
- Automated Assessment of Fidelity and Interpretability: An Evaluation Framework for Large Language Models’ Explanations (Student Abstract) (AAAI 2024 · similarity 0.86)
- Potemkin Understanding in Large Language Models (ICML 2025 · similarity 0.86)
- Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations (ICLR 2025 · similarity 0.85)
- Neither Valid nor Reliable? Investigating the Use of LLMs as Judges (NeurIPS 2025 · similarity 0.85)
- The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans (NeurIPS 2026 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.