{"total":103,"rows":[{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691,"area":null},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876,"area":null},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293,"area":null},{"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":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178,"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":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"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":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81,"area":null},{"id":"2103.01378","title":"Contrastive Explanations for Model Interpretability","created":"2021-03-02","cited_by_count":75,"area":null},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62,"area":null},{"id":"2108.10539","title":"Counterfactual Explainable Recommendation","created":"2021-08-24","cited_by_count":60,"area":null},{"id":"2105.06965","title":"Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction","created":"2021-05-14","cited_by_count":59,"area":null},{"id":"2207.14251","title":"Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions","created":"2022-07-28","cited_by_count":57,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2205.14140","title":"CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behavior","created":"2022-05-27","cited_by_count":55,"area":null},{"id":"2312.01261","title":"TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models","created":"2023-12-03","cited_by_count":52,"area":null},{"id":"2402.09631","title":"Representation Surgery: Theory and Practice of Affine Steering","created":"2024-02-15","cited_by_count":50,"area":null},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"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":"2203.16747","title":"How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis","created":"2022-03-31","cited_by_count":42,"area":null},{"id":"2202.12350","title":"DoCoGen: Domain Counterfactual Generation for Low Resource Domain Adaptation","created":"2022-02-24","cited_by_count":37,"area":null},{"id":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34,"area":null},{"id":"2407.14962","title":"Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectives","created":"2024-07-20","cited_by_count":30,"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":"2206.02928","title":"Neuro-Symbolic Procedural Planning with Commonsense Prompting","created":"2022-06-06","cited_by_count":28,"area":null},{"id":"2403.05023","title":"Towards Multimodal Sentiment Analysis Debiasing via Bias Purification","created":"2024-03-08","cited_by_count":27,"area":null},{"id":"2503.21411","title":"Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap","created":"2025-03-27","cited_by_count":26,"area":null},{"id":"2202.01336","title":"Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimation","created":"2022-02-02","cited_by_count":25,"area":null},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25,"area":null},{"id":"2312.02073","title":"A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia","created":"2023-12-04","cited_by_count":24,"area":null},{"id":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","cited_by_count":21,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2401.12585","title":"SLANG: New Concept Comprehension of Large Language Models","created":"2024-01-23","cited_by_count":20,"area":null},{"id":"2112.02505","title":"Causal Distillation for Language Models","created":"2021-12-05","cited_by_count":19,"area":null},{"id":"2205.07043","title":"Naturalistic Causal Probing for Morpho-Syntax","created":"2022-05-14","cited_by_count":19,"area":null},{"id":"2210.12696","title":"On the Transformation of Latent Space in Fine-Tuned NLP Models","created":"2022-10-23","cited_by_count":19,"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":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2201.11239","title":"Diagnosing AI Explanation Methods with Folk Concepts of Behavior","created":"2022-01-27","cited_by_count":15,"area":null},{"id":"2104.06400","title":"Mediators in Determining what Processing BERT Performs First","created":"2021-04-13","cited_by_count":14,"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":"2306.08193","title":"Operationalising Representation in Natural Language Processing","created":"2023-06-14","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":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2112.04895","title":"Latent Space Explanation by Intervention","created":"2021-12-09","cited_by_count":13,"area":null},{"id":"2204.09722","title":"When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout Probes","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2303.03951","title":"Probing Graph Representations","created":"2023-03-07","cited_by_count":10,"area":null},{"id":"2109.11491","title":"Putting Words in BERT's Mouth: Navigating Contextualized Vector Spaces with Pseudowords","created":"2021-09-23","cited_by_count":9,"area":null},{"id":"2203.17081","title":"Interpretation of Black Box NLP Models: A Survey","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2504.10227","title":"Probing then Editing Response Personality of Large Language Models","created":"2025-04-14","cited_by_count":9,"area":null},{"id":"2312.16257","title":"More than Correlation: Do Large Language Models Learn Causal Representations of Space?","created":"2023-12-26","cited_by_count":7,"area":null},{"id":"2101.07086","title":"Model Compression for Domain Adaptation through Causal Effect Estimation","created":"2021-01-18","cited_by_count":6,"area":null},{"id":"2302.02997","title":"Erasure of Unaligned Attributes from Neural Representations","created":"2023-02-06","cited_by_count":6,"area":null},{"id":"2502.15277","title":"Analyzing the Inner Workings of Transformers in Compositional Generalization","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2503.06048","title":"Constructions are Revealed in Word Distributions","created":"2025-03-08","cited_by_count":6,"area":null},{"id":"2206.00416","title":"In the Eye of the Beholder: Robust Prediction with Causal User Modeling","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2304.10346","title":"Interventional Probing in High Dimensions: An NLI Case Study","created":"2023-04-20","cited_by_count":5,"area":null},{"id":"2311.05286","title":"Causal Inference from Text: Unveiling Interactions between Variables","created":"2023-11-09","cited_by_count":5,"area":null},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2402.11355","title":"A Practical Method for Generating String Counterfactuals","created":"2024-02-17","cited_by_count":4,"area":null},{"id":"2404.06201","title":"Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning","created":"2024-04-09","cited_by_count":4,"area":null},{"id":"2410.21474","title":"Estimating Causal Effects of Text Interventions Leveraging LLMs","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2506.10703","title":"Preserving Task-Relevant Information Under Linear Concept Removal","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2210.12206","title":"Probing with Noise: Unpicking the Warp and Weft of Embeddings","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2402.00711","title":"Explaining Text Classifiers with Counterfactual Representations","created":"2024-02-01","cited_by_count":3,"area":null},{"id":"2406.10885","title":"On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions","created":"2024-06-16","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":"2305.02321","title":"Entity-Based Evaluation of Political Bias in Automatic Summarization","created":"2023-05-03","cited_by_count":2,"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":"2310.06666","title":"Unlock the Potential of Counterfactually-Augmented Data in Out-Of-Distribution Generalization","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2402.01115","title":"Interpretation of Intracardiac Electrograms Through Textual Representations","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2405.10991","title":"Relative Counterfactual Contrastive Learning for Mitigating Pretrained Stance Bias in Stance Detection","created":"2024-05-16","cited_by_count":2,"area":null},{"id":"2406.00611","title":"DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation","created":"2024-06-02","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":"2606.05972","title":"LLM Explainability with Counterfactual Chains and Causal Graphs","created":"2026-06-04","cited_by_count":2,"area":null},{"id":"2209.03891","title":"IDIAPers @ Causal News Corpus 2022: Extracting Cause-Effect-Signal Triplets via Pre-trained Autoregressive Language Model","created":"2022-09-08","cited_by_count":1,"area":null},{"id":"2302.09488","title":"A Picture May Be Worth a Thousand Lives: An Interpretable Artificial Intelligence Strategy for Predictions of Suicide Risk from Social Media Images","created":"2023-02-19","cited_by_count":1,"area":null},{"id":"2303.03019","title":"NxPlain: Web-based Tool for Discovery of Latent Concepts","created":"2023-03-06","cited_by_count":1,"area":null},{"id":"2310.07588","title":"Accurate Use of Label Dependency in Multi-Label Text Classification Through the Lens of Causality","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2407.10949","title":"Representing Rule-based Chatbots with Transformers","created":"2024-07-15","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":"2411.16251","title":"Transparent Neighborhood Approximation for Text Classifier Explanation","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2506.07747","title":"E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time","created":"2025-06-06","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":"2605.25891","title":"Causal Tongue-Tie: LLMs Can Encode Causal Direction, But Their Yes/No Outputs Fail to Express","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.04286","title":"Using Text-Based Causal Inference to Disentangle Factors Influencing Online Review Ratings","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2107.06310","title":"What do writing features tell us about AI papers?","created":"2021-07-13","cited_by_count":0,"area":null},{"id":"2404.11819","title":"Utilizing Adversarial Examples for Bias Mitigation and Accuracy Enhancement","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2406.14459","title":"Healing Powers of BERT: How Task-Specific Fine-Tuning Recovers Corrupted Language Models","created":"2024-06-20","cited_by_count":0,"area":null},{"id":"2406.15940","title":"Beyond Individual Facts: Investigating Categorical Knowledge Locality of Taxonomy and Meronomy Concepts in GPT Models","created":"2024-06-22","cited_by_count":0,"area":null},{"id":"2410.05484","title":"Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2503.19394","title":"Quantifying Symptom Causality in Clinical Decision Making: An Exploration Using CausaLM","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2506.02147","title":"BabyLM's First Constructions: Causal probing provides a signal of learning","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2511.11600","title":"CausalGuard: A Smart System for Detecting and Preventing False Information in Large Language Models","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2512.03803","title":"Enhancing Instruction-Following Capabilities in Seq2Seq Models: DoLA Adaptations for T5","created":"2025-12-03","cited_by_count":0,"area":null}],"next_cursor":"100"}