{"total":26,"rows":[{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422,"area":null},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214,"area":null},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110,"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":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44,"area":null},{"id":"2211.00768","title":"Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality","created":"2022-11-01","cited_by_count":44,"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":"2209.14279","title":"Causal Proxy Models for Concept-Based Model Explanations","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2106.02559","title":"Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky Probing","created":"2021-06-04","cited_by_count":28,"area":null},{"id":"2412.05571","title":"A polar coordinate system represents syntax in large language models","created":"2024-12-07","cited_by_count":25,"area":null},{"id":"2407.04690","title":"Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks","created":"2024-07-05","cited_by_count":23,"area":null},{"id":"2106.01317","title":"Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization","created":"2021-06-02","cited_by_count":11,"area":null},{"id":"2210.03575","title":"Are Representations Built from the Ground Up? An Empirical Examination of Local Composition in Language Models","created":"2022-10-07","cited_by_count":9,"area":null},{"id":"2306.03882","title":"Causal interventions expose implicit situation models for commonsense language understanding","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2405.15164","title":"From Frege to chatGPT: Compositionality in language, cognition, and deep neural networks","created":"2024-05-24","cited_by_count":7,"area":null},{"id":"2208.06061","title":"Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages","created":"2022-08-11","cited_by_count":5,"area":null},{"id":"2306.00751","title":"Differentiable Tree Operations Promote Compositional Generalization","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2412.14076","title":"Compositional Generalization Across Distributional Shifts with Sparse Tree Operations","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2506.13253","title":"Distinct Computations Emerge From Compositional Curricula in In-Context Learning","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2504.12585","title":"Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2110.13229","title":"Distributionally Robust Recurrent Decoders with Random Network Distillation","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2109.08449","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2301.08998","title":"Syntax-guided Neural Module Distillation to Probe Compositionality in Sentence Embeddings","created":"2023-01-21","cited_by_count":1,"area":null},{"id":"2304.04330","title":"Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?","created":"2023-04-09","cited_by_count":1,"area":null},{"id":"2305.16328","title":"Semantic Composition in Visually Grounded Language Models","created":"2023-05-15","cited_by_count":1,"area":null},{"id":"2610.15843","title":"Binding Phoneme Identity to Position in Neural Models and the Human Brain","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}