{"total":20,"rows":[{"id":"2511.06571","title":"Rep2Text: Decoding Full Text from a Single LLM Token Representation","created":"2025-11-09","cited_by_count":7,"area":null},{"id":"2606.07612","title":"Position: Anthropomorphic Misalignment Research Needs Stronger Evidence","created":"2026-05-29","cited_by_count":7,"area":null},{"id":"2505.16170","title":"When Do LLMs Admit Their Mistakes? Understanding The Role Of Model Belief In Retraction","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2603.02578","title":"How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities","created":"2026-03-03","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":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2508.19414","title":"Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2510.11235","title":"AI Alignment Strategies from a Risk Perspective: Independent Safety Mechanisms or Shared Failures?","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2605.17659","title":"Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2606.24997","title":"What's in an Earth Embedding? An Explainability Analysis of Location Encoders","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2509.15667","title":"VOX-KRIKRI: Unifying Speech and Language through Continuous Fusion","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2510.16565","title":"Language over Content: Tracing Cultural Understanding in Multilingual Large Language Models","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2511.12723","title":"LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2511.19264","title":"Interpreting GFlowNets for Drug Discovery: What probes can and cannot show","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.20638","title":"Uncovering Competency Gaps in Large Language Models and Their Benchmarks","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2601.11691","title":"Explainable histomorphology-based survival prediction of glioblastoma, IDH-wildtype","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2605.22532","title":"Relational Linear Properties in Language Models: An Empirical Investigation","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2608.15042","title":"Uncovering Hidden Leptonic Correlations with Flow Matching and Autoencoders","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.38205","title":"The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}