{"total":45,"rows":[{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209,"area":null},{"id":"2308.13067","title":"Causal Parrots: Large Language Models May Talk Causality But Are Not Causal","created":"2023-08-24","cited_by_count":150,"area":null},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130,"area":null},{"id":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103,"area":null},{"id":"2312.12936","title":"Concept-based Explainable Artificial Intelligence: A Survey","created":"2023-12-20","cited_by_count":98,"area":null},{"id":"2501.10970","title":"The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMs","created":"2025-01-19","cited_by_count":74,"area":null},{"id":"2311.08648","title":"Explore Spurious Correlations at the Concept Level in Language Models for Text Classification","created":"2023-11-15","cited_by_count":48,"area":null},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2310.00603","title":"Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals","created":"2023-10-01","cited_by_count":44,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"area":null},{"id":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"area":null},{"id":"2401.12631","title":"A Reply to Makelov et al. (2023)'s \"Interpretability Illusion\" Arguments","created":"2024-01-23","cited_by_count":17,"area":null},{"id":"2407.15527","title":"Interpretable Concept-Based Memory Reasoning","created":"2024-07-22","cited_by_count":17,"area":null},{"id":"2302.06975","title":"A Review of the Role of Causality in Developing Trustworthy AI Systems","created":"2023-02-14","cited_by_count":14,"area":null},{"id":"2310.12803","title":"Data Augmentations for Improved (Large) Language Model Generalization","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2407.12519","title":"Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition","created":"2024-07-17","cited_by_count":14,"area":null},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13,"area":null},{"id":"2405.05466","title":"Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals","created":"2024-05-08","cited_by_count":13,"area":null},{"id":"2403.05636","title":"Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach","created":"2024-03-08","cited_by_count":11,"area":null},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2303.00333","title":"Competence-Based Analysis of Language Models","created":"2023-03-01","cited_by_count":4,"area":null},{"id":"2402.00711","title":"Explaining Text Classifiers with Counterfactual Representations","created":"2024-02-01","cited_by_count":3,"area":null},{"id":"2406.14335","title":"Linearly-Interpretable Concept Embedding Models for Text Analysis","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2504.03978","title":"V-CEM: Bridging Performance and Intervenability in Concept-based Models","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2507.12341","title":"Nonlinear Concept Erasure: a Density Matching Approach","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2308.08407","title":"Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalities","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2601.10700","title":"LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals","created":"2026-01-15","cited_by_count":2,"area":null},{"id":"2606.03810","title":"Consistency Training Can Entrench Misalignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2403.08572","title":"Caformer: Rethinking Time Series Analysis from Causal Perspective","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2407.13765","title":"Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2410.13488","title":"Seeing Through VisualBERT: A Causal Adventure on Memetic Landscapes","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2410.15648","title":"Linking Model Intervention to Causal Interpretation in Model Explanation","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2505.20293","title":"Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discovery","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2512.06814","title":"CAuSE: Decoding Multimodal Classifiers using Faithful Natural Language Explanation","created":"2025-12-07","cited_by_count":1,"area":null},{"id":"2311.10905","title":"Flexible Model Interpretability through Natural Language Model Editing","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2406.02002","title":"Position Debiasing Fine-Tuning for Causal Perception in Long-Term Dialogue","created":"2024-06-04","cited_by_count":0,"area":null},{"id":"2604.24170","title":"Credal Concept Bottleneck Models for Epistemic-Aleatoric Uncertainty Decomposition","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.04326","title":"Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2609.08585","title":"Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.31857","title":"LLM Judge Validation Under Sparse Overlap: From Inference to Design","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32247","title":"Certifying Interventional Agreement Among Observationally Equivalent Causal Models","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.17399","title":"Learning to Detect Shifts in Unstructured Data Streams via Monitoring-by-Betting","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}