{"total":18,"rows":[{"id":"2305.08809","title":"Interpretability at Scale: Identifying Causal Mechanisms in Alpaca","created":"2023-05-15","cited_by_count":103,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"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":"2407.14662","title":"Relational Composition in Neural Networks: A Survey and Call to Action","created":"2024-07-19","cited_by_count":23,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2212.04273","title":"Better Hit the Nail on the Head than Beat around the Bush: Removing Protected Attributes with a Single Projection","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2306.08193","title":"Operationalising Representation in Natural Language Processing","created":"2023-06-14","cited_by_count":14,"area":null},{"id":"2304.05967","title":"Angler: Helping Machine Translation Practitioners Prioritize Model Improvements","created":"2023-04-12","cited_by_count":12,"area":null},{"id":"2406.18534","title":"Towards Compositionality in Concept Learning","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2502.06536","title":"Sample-efficient Learning of Concepts with Theoretical Guarantees: from Data to Concepts without Interventions","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2210.10684","title":"Language Models Understand Us, Poorly","created":"2022-10-19","cited_by_count":3,"area":null},{"id":"2311.05754","title":"Deep Natural Language Feature Learning for Interpretable Prediction","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2406.09067","title":"Interpreting the structure of multi-object representations in vision encoders","created":"2024-06-13","cited_by_count":1,"area":null},{"id":"2507.18550","title":"On the Performance of Concept Probing: The Influence of the Data (Extended Version)","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2507.18681","title":"Concept Probing: Where to Find Human-Defined Concepts (Extended Version)","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2608.07353","title":"Geo-Spatial Concept Probing of Large Language Models: Abstraction, Compositionality, and Grounding","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}