{"total":24,"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":"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":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"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":"2310.16410","title":"Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero","created":"2023-10-25","cited_by_count":42,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"area":null},{"id":"2401.06416","title":"Mission: Impossible Language Models","created":"2024-01-12","cited_by_count":32,"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":"2310.19660","title":"Interpretable-by-Design Text Understanding with Iteratively Generated Concept Bottleneck","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2212.09897","title":"Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training","created":"2022-12-19","cited_by_count":16,"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":"2404.18533","title":"Evaluating Readability and Faithfulness of Concept-based Explanations","created":"2024-04-29","cited_by_count":10,"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":"2305.08572","title":"Estimating the Causal Effects of Natural Logic Features in Neural NLI Models","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2406.09458","title":"Updating CLIP to Prefer Descriptions Over Captions","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2406.09612","title":"Automated Molecular Concept Generation and Labeling with Large Language Models","created":"2024-06-13","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":"2312.08063","title":"Estimation of Concept Explanations Should be Uncertainty Aware","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2410.12439","title":"Beyond Attribution: Unified Concept-Level Explanations","created":"2024-10-16","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":"2311.09605","title":"Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2404.02622","title":"Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models","created":"2024-04-03","cited_by_count":0,"area":null},{"id":"2502.06398","title":"Learning Counterfactual Outcomes Under Rank Preservation","created":"2025-02-10","cited_by_count":0,"area":null}],"next_cursor":null}