{"total":57,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2503.01917","title":"Steer LLM Latents for Hallucination Detection","created":"2025-03-01","cited_by_count":50,"area":null},{"id":"2502.06975","title":"Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents","created":"2025-02-10","cited_by_count":36,"area":"agents"},{"id":"2509.12886","title":"The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representations","created":"2025-09-16","cited_by_count":29,"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":"2502.04506","title":"When One LLM Drools, Multi-LLM Collaboration Rules","created":"2025-02-06","cited_by_count":28,"area":null},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2507.04250","title":"Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning","created":"2025-07-06","cited_by_count":24,"area":"alignment"},{"id":"2602.08169","title":"Spherical Steering: Geometry-Aware Activation Rotation for Language Models","created":"2026-02-09","cited_by_count":21,"area":null},{"id":"2505.13737","title":"Causal Head Gating: A Framework for Interpreting Roles of Attention Heads in Transformers","created":"2025-05-19","cited_by_count":16,"area":null},{"id":"2508.10599","title":"Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models","created":"2025-08-14","cited_by_count":16,"area":"mechinterp"},{"id":"2602.00359","title":"Position: Agentic Evolution is the Path to Evolving LLMs","created":"2026-01-30","cited_by_count":16,"area":"agents"},{"id":"2503.10679","title":"LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss","created":"2025-03-11","cited_by_count":14,"area":"mechinterp"},{"id":"2602.01654","title":"Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models","created":"2026-02-02","cited_by_count":13,"area":"mechinterp"},{"id":"2507.08799","title":"KV Cache Steering for Controlling Frozen LLMs","created":"2025-07-11","cited_by_count":11,"area":"inference"},{"id":"2410.16930","title":"Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes","created":"2024-10-22","cited_by_count":10,"area":"lr"},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"area":null},{"id":"2502.01179","title":"Joint Localization and Activation Editing for Low-Resource Fine-Tuning","created":"2025-02-03","cited_by_count":8,"area":null},{"id":"2505.22860","title":"Permissioned LLMs: Enforcing Access Control in Large Language Models","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2502.04043","title":"Probe-Free Low-Rank Activation Intervention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2509.16820","title":"DISCO: Disentangled Communication Steering for Large Language Models","created":"2025-09-20","cited_by_count":5,"area":"mechinterp"},{"id":"2512.07890","title":"CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models","created":"2025-12-02","cited_by_count":5,"area":null},{"id":"2504.11381","title":"RankAlign: A Ranking View of the Generator-Validator Gap in Large Language Models","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2505.23808","title":"DenseLoRA: Dense Low-Rank Adaptation of Large Language Models","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2506.06686","title":"Learning Distribution-Wise Control in Representation Space for Language Models","created":"2025-06-07","cited_by_count":4,"area":null},{"id":"2505.22635","title":"Learning Composable Chains-of-Thought","created":"2025-05-28","cited_by_count":3,"area":"lr"},{"id":"2506.20746","title":"Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2510.21834","title":"Restoring Pruned Large Language Models via Lost Component Compensation","created":"2025-10-22","cited_by_count":3,"area":null},{"id":"2603.00425","title":"Weight Updates as Activation Shifts: A Principled Framework for Steering","created":"2026-02-28","cited_by_count":3,"area":"mechinterp"},{"id":"2501.15758","title":"Distributional Surgery for Language Model Activations","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2502.05242","title":"Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2510.17882","title":"Does GenAI Rewrite How We Write? An Empirical Study on Two-Million Preprints","created":"2025-10-18","cited_by_count":2,"area":null},{"id":"2601.21003","title":"Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2602.22175","title":"DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2510.02528","title":"Multimodal Function Vectors for Visual Relations","created":"2025-10-02","cited_by_count":1,"area":"mllm"},{"id":"2604.06393","title":"ART: Attention Replacement Technique to Improve Factuality in LLMs","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.15294","title":"How Do LLMs and VLMs Understand Viewpoint Rotation Without Vision? An Interpretability Study","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2607.18130","title":"Manifold-Constrained Hyper-Connections for Parameter-Efficient Finetuning","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2505.18672","title":"Concept Concentration for Faithful Representation Intervention","created":"2025-05-24","cited_by_count":0,"area":"safety"},{"id":"2601.08169","title":"Relational Knowledge Distillation Using Fine-tuned Function Vectors","created":"2026-01-13","cited_by_count":0,"area":"distill"},{"id":"2602.06924","title":"Rank-Constrained Adaptation for Reliable Real-World Performance","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.11201","title":"Representation Finetuning for Continual Learning","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2604.14174","title":"Correcting Suppressed Log-Probabilities in Language Models with Post-Transformer Adapters","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.21558","title":"From Parameters to Data: A Task-Parameter-Guided Fine-Tuning Pipeline for Efficient LLM Alignment","created":"2026-05-20","cited_by_count":0,"area":"alignment"},{"id":"2607.07128","title":"Distributed Sparse Interventions in Language Models","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.02957","title":"Inverted Detection and Control in Steering Vectors","created":"2026-08-03","cited_by_count":0,"area":"mechinterp"},{"id":"2608.24482","title":"Beyond Static Interpretability: Anticipating Post-SFT Mechanisms from Pre-SFT Parameters for Better Tuning","created":"2026-08-25","cited_by_count":0,"area":"mechinterp"},{"id":"2609.23979","title":"AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32519","title":"STR: Supervised Transcoder Replacement for Reducing Steering Side Effects","created":"2026-09-26","cited_by_count":0,"area":"mechinterp"},{"id":"2609.33298","title":"Direct Hidden-State Alignment: Mapping and Controlling Preference Expression in LLMs","created":"2026-09-27","cited_by_count":0,"area":"alignment"},{"id":"2609.36585","title":"Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.19113","title":"From Copying to Composition: How Language Models Develop In-Context Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}