{"total":26,"rows":[{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2602.19961","title":"Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval","created":"2026-02-23","cited_by_count":8,"area":null},{"id":"2602.05735","title":"CSRv2: Unlocking Ultra-Sparse Embeddings","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2606.11722","title":"ICA Lens: Interpreting Language Models Without Training Another Dictionary","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2505.19333","title":"Evaluating Steering Techniques using Human Similarity Judgments","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2505.21399","title":"Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2510.06378","title":"Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.23749","title":"Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2605.20612","title":"Matryoshka Concept Bottleneck Models","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2603.03319","title":"Automated Concept Discovery for LLM-as-a-Judge Preference Analysis","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.28870","title":"Representation Alignment Rests on Linear Structure","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2507.10106","title":"BlueGlass: A Framework for Composite AI Safety","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2510.24672","title":"Eigenfunction Extraction for Ordered Representation Learning","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2604.01619","title":"Automatic Image-Level Morphological Trait Annotation for Organismal Images","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.21511","title":"From Tokens to Concepts: Leveraging SAE for SPLADE","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.12055","title":"Do Language Models Encode Knowledge of Linguistic Constraint Violations?","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.17010","title":"From Tokens to Policy: Causal and Interpretable Heterogeneous Treatment Effects Identification","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.20347","title":"Critical Percolation as a Synthetic Data Model for Interpretability","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.12573","title":"Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37731","title":"Weights Read and Write Features: Scalable Parameter Decomposition Grounded in Activation Space","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00895","title":"Towards Fast and Disentangled Counterfactuals for Visual Foundation Models","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}