{"total":10,"rows":[{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"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":"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":"2301.10884","title":"Break It Down: Evidence for Structural Compositionality in Neural Networks","created":"2023-01-26","cited_by_count":44,"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":"2406.15102","title":"HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization","created":"2024-06-21","cited_by_count":2,"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":"2305.16328","title":"Semantic Composition in Visually Grounded Language Models","created":"2023-05-15","cited_by_count":1,"area":null},{"id":"2503.14442","title":"Inducing Causal Structure for Interpretable Neural Networks Applied to Glucose Prediction for T1DM Patients","created":"2025-03-18","cited_by_count":0,"area":null}],"next_cursor":null}