{"total":179,"rows":[{"id":"2503.23037","title":"Agentic Large Language Models, a survey","created":"2025-03-29","cited_by_count":108,"area":"agents"},{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2511.08579","title":"Training Language Models to Explain Their Own Computations","created":"2025-11-11","cited_by_count":30,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2506.11976","title":"How Visual Representations Map to Language Feature Space in Multimodal LLMs","created":"2025-06-13","cited_by_count":25,"area":"lr"},{"id":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","cited_by_count":25,"area":"mechinterp"},{"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":"2502.11196","title":"How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training","created":"2025-02-16","cited_by_count":23,"area":null},{"id":"2505.11581","title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","created":"2025-05-16","cited_by_count":22,"area":null},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2605.11887","title":"Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models","created":"2026-05-12","cited_by_count":21,"area":"mechinterp"},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19,"area":"mechinterp"},{"id":"2508.05687","title":"Risk Analysis Techniques for Governed LLM-based Multi-Agent Systems","created":"2025-08-06","cited_by_count":18,"area":"agents"},{"id":"2505.17495","title":"ProxySPEX: Inference-Efficient Interpretability via Sparse Feature Interactions in LLMs","created":"2025-05-23","cited_by_count":16,"area":null},{"id":"2506.12152","title":"Because we have LLMs, we Can and Should Pursue Agentic Interpretability","created":"2025-06-13","cited_by_count":16,"area":"agents"},{"id":"2502.14258","title":"Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information","created":"2025-02-20","cited_by_count":15,"area":null},{"id":"2506.06489","title":"Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"area":null},{"id":"2508.21258","title":"RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching","created":"2025-08-28","cited_by_count":13,"area":"mechinterp"},{"id":"2512.16856","title":"Distributional AGI Safety","created":"2025-12-18","cited_by_count":12,"area":null},{"id":"2601.05679","title":"Do Sparse Autoencoders Identify Reasoning Features in Language Models?","created":"2026-01-09","cited_by_count":12,"area":"lr"},{"id":"2603.20432","title":"Coding Agents are Effective Long-Context Processors","created":"2026-03-20","cited_by_count":12,"area":"agents"},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2602.16823","title":"Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees","created":"2026-02-18","cited_by_count":11,"area":"mechinterp"},{"id":"2506.15538","title":"Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework","created":"2025-06-18","cited_by_count":10,"area":null},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2509.23799","title":"Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement","created":"2025-09-28","cited_by_count":10,"area":"mechinterp"},{"id":"2602.03655","title":"Sequential Group Composition: A Window into the Mechanics of Deep Learning","created":"2026-02-03","cited_by_count":10,"area":null},{"id":"2602.06286","title":"When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs","created":"2026-02-06","cited_by_count":10,"area":"agents"},{"id":"2505.14071","title":"Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2605.12671","title":"All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs","created":"2026-05-12","cited_by_count":9,"area":"lr"},{"id":"2507.08017","title":"Mechanistic Indicators of Understanding in Large Language Models","created":"2025-07-07","cited_by_count":8,"area":null},{"id":"2507.12464","title":"CytoSAE: Interpretable Cell Embeddings for Hematology","created":"2025-07-16","cited_by_count":8,"area":"mechinterp"},{"id":"2506.06382","title":"On the Fundamental Impossibility of Hallucination Control in Large Language Models","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2508.00161","title":"Watch the Weights: Unsupervised monitoring and control of fine-tuned LLMs","created":"2025-07-31","cited_by_count":7,"area":"safety"},{"id":"2604.02178","title":"The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level","created":"2026-04-02","cited_by_count":7,"area":"moe"},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","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":"2506.18852","title":"Mechanistic Interpretability Needs Philosophy","created":"2025-06-23","cited_by_count":6,"area":"mechinterp"},{"id":"2510.27044","title":"Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning","created":"2025-10-30","cited_by_count":6,"area":"lr"},{"id":"2603.15121","title":"Establishing Construct Validity in LLM Capability Benchmarks Requires Nomological Networks","created":"2026-03-16","cited_by_count":6,"area":null},{"id":"2603.17199","title":"Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing","created":"2026-03-17","cited_by_count":6,"area":"lr"},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2601.22257","title":"Symmetry Breaking in Transformers for Efficient and Interpretable Training","created":"2026-01-29","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2607.03358","title":"Pathways of Visual Information Flow in Vision-Language Models","created":"2026-07-03","cited_by_count":5,"area":"mllm"},{"id":"2505.15811","title":"On the creation of narrow AI: hierarchy and nonlocality of neural network skills","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.24293","title":"Equivalent Linear Mappings of Large Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2506.01042","title":"Probing Neural Topology of Large Language Models","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.17052","title":"From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2510.00468","title":"Feature Identification via the Empirical NTK","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2510.03186","title":"Superposition disentanglement of neural representations reveals hidden alignment","created":"2025-10-03","cited_by_count":4,"area":"mechinterp"},{"id":"2510.03282","title":"Discovering Transformer Circuits via a Hybrid Attribution and Pruning Framework","created":"2025-09-28","cited_by_count":4,"area":"mechinterp"},{"id":"2511.00124","title":"Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models","created":"2025-10-31","cited_by_count":4,"area":"diffusion"},{"id":"2603.07343","title":"Learning Concept Bottleneck Models from Mechanistic Explanations","created":"2026-03-07","cited_by_count":4,"area":null},{"id":"2605.05076","title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2502.06106","title":"Fine-Tuning is Subgraph Search: A New Lens on Learning Dynamics","created":"2025-02-10","cited_by_count":3,"area":"mechinterp"},{"id":"2505.16077","title":"Ensembling Sparse Autoencoders","created":"2025-05-21","cited_by_count":3,"area":"mechinterp"},{"id":"2505.17769","title":"Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2506.17846","title":"Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack)","created":"2025-06-21","cited_by_count":3,"area":null},{"id":"2508.09363","title":"Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders","created":"2025-08-12","cited_by_count":3,"area":"lr"},{"id":"2508.15847","title":"Mechanistic Exploration of Backdoored Large Language Model Attention Patterns","created":"2025-08-19","cited_by_count":3,"area":"safety"},{"id":"2509.02805","title":"Challenges in Understanding Modality Conflict in Vision-Language Models","created":"2025-09-02","cited_by_count":3,"area":"mllm"},{"id":"2510.01069","title":"Typed Chain-of-Thought: A Curry-Howard Framework for Verifying LLM Reasoning","created":"2025-10-01","cited_by_count":3,"area":"lr"},{"id":"2510.22099","title":"Generalization or Memorization: Dynamic Decoding for Mode Steering","created":"2025-10-25","cited_by_count":3,"area":"mechinterp"},{"id":"2511.06516","title":"You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations","created":"2025-11-09","cited_by_count":3,"area":null},{"id":"2511.12421","title":"From Black Box to Bijection: Interpreting Machine Learning to Build a Zeta Map Algorithm","created":"2025-11-16","cited_by_count":3,"area":null},{"id":"2511.21974","title":"Start Making Sense(s): A Developmental Probe of Attention Specialization Using Lexical Ambiguity","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2601.08837","title":"From Adversarial Poetry to Adversarial Tales: An Interpretability Research Agenda","created":"2025-12-16","cited_by_count":3,"area":"safety"},{"id":"2602.05532","title":"Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2602.07080","title":"CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2603.00063","title":"Measuring What AI Systems Might Do: Towards A Measurement Science in AI","created":"2026-02-10","cited_by_count":3,"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":"2603.02960","title":"Architecting Trust in Artificial Epistemic Agents","created":"2026-03-03","cited_by_count":3,"area":"agents"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2604.06005","title":"Disentangling MLP Neuron Weights in Vocabulary Space","created":"2026-04-07","cited_by_count":3,"area":"mechinterp"},{"id":"2604.11962","title":"The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2605.18882","title":"To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents","created":"2026-05-16","cited_by_count":3,"area":"agents"},{"id":"2606.09899","title":"When Attribution Patching Lies: Diagnosis and a Second-Order Correction","created":"2026-06-05","cited_by_count":3,"area":"mechinterp"},{"id":"2607.14943","title":"Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control","created":"2026-07-16","cited_by_count":3,"area":"wm"},{"id":"2502.21123","title":"Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation Models","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2504.09387","title":"On Language Models' Sensitivity to Suspicious Coincidences","created":"2025-04-13","cited_by_count":2,"area":null},{"id":"2505.10375","title":"Are Sparse Autoencoders Useful for Java Function Bug Detection?","created":"2025-05-15","cited_by_count":2,"area":"mechinterp"},{"id":"2505.21399","title":"Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2505.22664","title":"Zero-Shot Vision Encoder Grafting via LLM Surrogates","created":"2025-05-28","cited_by_count":2,"area":"mllm"},{"id":"2506.07406","title":"InverseScope: Scalable Activation Inversion for Interpreting Large Language Models","created":"2025-06-09","cited_by_count":2,"area":"mechinterp"},{"id":"2508.05463","title":"Task complexity shapes internal representations and robustness in neural networks","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2508.16325","title":"ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2509.11398","title":"From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming","created":"2025-09-14","cited_by_count":2,"area":null},{"id":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2601.03657","title":"In Search of Grandmother Cells: Tracing Interpretable Neurons in Tabular Representations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.08693","title":"Reasoning aligns language models to human cognition","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2605.15164","title":"Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2605.24024","title":"Mitigating Hallucinations in Large Vision-Language Models via Causal Route Gating","created":"2026-05-20","cited_by_count":2,"area":"mllm"},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.16920","title":"Demystifying Variance in Circuit Discovery of LLMs","created":"2026-06-15","cited_by_count":2,"area":"mechinterp"}],"next_cursor":"100"}