{"total":24,"rows":[{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"area":null},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2503.01751","title":"SAKE: Steering Activations for Knowledge Editing","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2510.15804","title":"Emergence of Linear Truth Encodings in Language Models","created":"2025-10-17","cited_by_count":12,"area":null},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2605.26242","title":"Can LLMs Introspect? A Reality Check","created":"2026-05-25","cited_by_count":12,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2509.14814","title":"ReCoVeR the Target Language: Language Steering without Sacrificing Task Performance","created":"2025-09-18","cited_by_count":6,"area":null},{"id":"2502.16385","title":"Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation","created":"2025-02-22","cited_by_count":3,"area":null},{"id":"2507.12341","title":"Nonlinear Concept Erasure: a Density Matching Approach","created":"2025-07-16","cited_by_count":3,"area":null},{"id":"2509.16660","title":"Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2605.04980","title":"Conceptors for Semantic Steering","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2501.15758","title":"Distributional Surgery for Language Model Activations","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2601.06437","title":"Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models","created":"2026-01-10","cited_by_count":2,"area":null},{"id":"2508.11258","title":"Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2509.12939","title":"Sy-FAR: Symmetry-based Fair Adversarial Robustness","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2607.03973","title":"MANCE: Manifold Aware Concept Erasure","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2609.11253","title":"MUtE: A Dual Framework for Concept Erasure and Counterfactual Interventions","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.22243","title":"Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.39892","title":"Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01054","title":"Capturing In-Context Learning Dynamics with Task Operators","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}