{"total":21,"rows":[{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90,"area":"lr"},{"id":"2203.17271","title":"Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?","created":"2022-03-31","cited_by_count":31,"area":"lr"},{"id":"2403.14349","title":"On the Concept Trustworthiness in Concept Bottleneck Models","created":"2024-03-21","cited_by_count":22,"area":"lr"},{"id":"2409.17270","title":"Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning","created":"2024-09-25","cited_by_count":19,"area":"lr"},{"id":"2510.21323","title":"VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set","created":"2025-10-24","cited_by_count":13,"area":"lr"},{"id":"2410.03595","title":"Understanding Reasoning in Chain-of-Thought from the Hopfieldian View","created":"2024-10-04","cited_by_count":11,"area":"lr"},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2502.13329","title":"Language Models Can Predict Their Own Behavior","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2209.13710","title":"Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledge","created":"2022-09-27","cited_by_count":6,"area":"lr"},{"id":"2508.12140","title":"Exploring Efficiency Frontiers of Thinking Budget in Medical Reasoning: Scaling Laws between Computational Resources and Reasoning Quality","created":"2025-08-16","cited_by_count":6,"area":"lr"},{"id":"2509.17740","title":"WISE: Weak-Supervision-Guided Step-by-Step Explanations for Multimodal LLMs in Image Classification","created":"2025-09-22","cited_by_count":4,"area":"lr"},{"id":"2207.01916","title":"Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models","created":"2022-07-05","cited_by_count":3,"area":"lr"},{"id":"2308.03999","title":"Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoning","created":"2023-08-08","cited_by_count":2,"area":"lr"},{"id":"2511.12008","title":"Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models","created":"2025-11-15","cited_by_count":2,"area":"lr"},{"id":"2603.05629","title":"Rethinking Concept Bottleneck Models: From Pitfalls to Solutions","created":"2026-03-05","cited_by_count":2,"area":"lr"},{"id":"2509.10809","title":"Rethinking Sparse Autoencoders: Select-and-Project for Fairness and Control from Encoder Features Alone","created":"2025-09-13","cited_by_count":1,"area":"lr"},{"id":"2510.00185","title":"Object-Centric Case-Based Reasoning via Argumentation","created":"2025-09-30","cited_by_count":1,"area":"lr"},{"id":"2606.15779","title":"Faithful Action-unit Causal Reasoning for Counterfactually Faithful Emotion Explanations","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2606.27947","title":"Understanding How MLLMs Describe Artworks Using Token Activation Maps","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2609.00764","title":"Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures","created":"2026-09-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}