{"total":22,"rows":[{"id":"2601.21571","title":"Shaping capabilities with token-level data filtering","created":"2026-01-29","cited_by_count":13,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2604.03058","title":"Verbalizing LLMs' assumptions to explain and control sycophancy","created":"2026-04-03","cited_by_count":5,"area":null},{"id":"2605.29601","title":"Training Deliberative Monitors for Black-Box Scheming Detection","created":"2026-05-28","cited_by_count":4,"area":null},{"id":"2609.15994","title":"Latent Undertow: How Ordinary Typos Break Probes","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2606.13892","title":"Crypto x AI, AI x Crypto: A Survey","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.21664","title":"Measuring Activation Control in Large Language Models","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2604.24801","title":"Architecture Determines Observability of Transformers","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.00874","title":"Latent Space Probing for Adult Content Detection in Video Generative Models","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.11093","title":"Enabling Performant and Flexible Model-Internal Observability for LLM Inference","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16035","title":"Who Owns This Agent? Tracing AI Agents Back to Their Owners","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.25893","title":"$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.29441","title":"Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.11414","title":"Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.10260","title":"Interpreting Language Model Hidden States at Scale","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.10795","title":"EvoMem: Memory-Augmented Evolution for Code Optimization","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.28099","title":"Speculative Probing: LLM Monitoring at Speculative-Decoding Cost","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.04721","title":"Locating and Steering Refusal Beyond Attention","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.22695","title":"A Survey on the Linear Representation Hypothesis","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.31796","title":"Same Probe, Different Numbers: Are Activation Probes Robust to Inference-Time Numerical Non-Determinism?","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36434","title":"The Safety Operator: Modulating the Expression of Safety Instructions via Spectral Optimization","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}