{"total":55,"rows":[{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"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":"2504.04635","title":"Steering off Course: Reliability Challenges in Steering Language Models","created":"2025-04-06","cited_by_count":34,"area":null},{"id":"2510.13290","title":"To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2511.05408","title":"Steering Language Models with Weight Arithmetic","created":"2025-11-07","cited_by_count":20,"area":null},{"id":"2502.02180","title":"The Elicitation Game: Evaluating Capability Elicitation Techniques","created":"2025-02-04","cited_by_count":18,"area":null},{"id":"2604.03147","title":"Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control","created":"2026-04-03","cited_by_count":16,"area":null},{"id":"2411.07213","title":"Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks","created":"2024-11-11","cited_by_count":14,"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":"2602.02343","title":"Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2602.04735","title":"From Data to Behavior: Predicting Unintended Model Behaviors Before Training","created":"2026-02-04","cited_by_count":8,"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":"2506.00653","title":"Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models","created":"2025-05-31","cited_by_count":7,"area":null},{"id":"2510.08506","title":"Neologism Learning for Controllability and Self-Verbalization","created":"2025-10-09","cited_by_count":6,"area":null},{"id":"2411.07965","title":"SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs","created":"2024-11-12","cited_by_count":5,"area":null},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2511.03738","title":"Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs","created":"2025-10-29","cited_by_count":5,"area":null},{"id":"2605.01844","title":"The Cylindrical Representation Hypothesis for Language Model Steering","created":"2026-05-03","cited_by_count":5,"area":null},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2606.02211","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","created":"2026-06-01","cited_by_count":4,"area":null},{"id":"2510.08734","title":"Transmuting prompts into weights","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2602.02712","title":"Towards Understanding Steering Strength","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2606.14388","title":"A Low-Rank Subspace Analysis of LLM Interventions","created":"2026-06-12","cited_by_count":3,"area":null},{"id":"2605.09760","title":"ConFit v3: Improving Resume-Job Matching with LLM-based Re-Ranking","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2510.09790","title":"Mapping Semantic & Syntactic Relationships with Geometric Rotation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.24772","title":"Confidence is Not Competence","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.00158","title":"RAPTOR: Ridge-Adaptive Logistic Probes","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2606.02528","title":"Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.29034","title":"The strength of clinical evidence is recoverable from language model representations but not from their stated grades","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2609.16247","title":"The Pain Axis: LLMs Represent Self-Directed Harm and Act on It","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2507.05235","title":"Logit Reweighting for Topic-Focused Summarization","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2512.12469","title":"Sparse Concept Anchoring for Interpretable and Controllable Neural Representations","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2512.18551","title":"Neologism Learning as a Parameter-Efficient Alternative to Fine-Tuning for Model Steering","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2602.01716","title":"Mechanistic Indicators of Steering Effectiveness in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2606.21078","title":"Validation-Gated Causal Interventions for Interpreting High-Stakes Large Language Model Behavior: A Case Study in Suicidality Detection","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.08526","title":"A Quantized Native Runtime for On-Device Semantic Audio Generation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.09156","title":"Activation Steering Transfer to Agents: One Gain Ratio Does Not Identify Potency and Efficacy","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.26411","title":"Do Unified Multimodal Models Think in One Space? A Lens Through Cross-Branch Steering","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.11822","title":"Located but Not Releasable: Silent Gate Inversion and Bounded Linear Release","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.16650","title":"PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.22852","title":"Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25315","title":"Activation-Space Order-Swap Geometry: A Site-Asymmetry Audit","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.16189","title":"Position: AI Is Not Ready for Strategic Conflicts","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.20614","title":"Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22522","title":"When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.38718","title":"MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04676","title":"Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.07798","title":"Thin Evidence, Thick Priors: How Language Models Substitute Identity for Missing Financial Facts","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.16325","title":"When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17117","title":"Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.20067","title":"Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}