{"total":73,"rows":[{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94,"area":null},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87,"area":null},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2501.00070","title":"ICLR: In-Context Learning of Representations","created":"2024-12-29","cited_by_count":50,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"area":null},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2410.10014","title":"Safety-Aware Fine-Tuning of Large Language Models","created":"2024-10-13","cited_by_count":34,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2410.00153","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","created":"2024-09-30","cited_by_count":27,"area":null},{"id":"2412.01784","title":"Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models","created":"2024-12-02","cited_by_count":24,"area":null},{"id":"2601.16644","title":"Sycophancy Hides Linearly in the Attention Heads","created":"2026-01-23","cited_by_count":23,"area":null},{"id":"2502.06666","title":"Automatic Evaluation of Healthcare LLMs Beyond Question-Answering","created":"2025-02-10","cited_by_count":20,"area":null},{"id":"2502.11812","title":"Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis","created":"2025-02-17","cited_by_count":20,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2406.02378","title":"On the Intrinsic Self-Correction Capability of LLMs: Uncertainty and Latent Concept","created":"2024-06-04","cited_by_count":16,"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":"2407.15286","title":"Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis","created":"2024-07-21","cited_by_count":15,"area":null},{"id":"2505.18651","title":"On the Emergence of Linear Analogies in Word Embeddings","created":"2025-05-24","cited_by_count":13,"area":null},{"id":"2504.02904","title":"How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence","created":"2025-04-03","cited_by_count":12,"area":null},{"id":"2406.17969","title":"Encourage or Inhibit Monosemanticity? Revisit Monosemanticity from a Feature Decorrelation Perspective","created":"2024-06-25","cited_by_count":10,"area":null},{"id":"2505.18752","title":"Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning","created":"2025-05-24","cited_by_count":10,"area":null},{"id":"2402.19103","title":"Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models","created":"2024-02-29","cited_by_count":9,"area":null},{"id":"2404.10464","title":"DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion","created":"2024-04-16","cited_by_count":9,"area":null},{"id":"2502.09863","title":"Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models","created":"2025-02-14","cited_by_count":8,"area":null},{"id":"2404.03784","title":"A Layer Selection Approach to Test Time Adaptation","created":"2024-04-04","cited_by_count":7,"area":null},{"id":"2502.16770","title":"LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint","created":"2025-02-24","cited_by_count":7,"area":null},{"id":"2506.01790","title":"IF-GUIDE: Influence Function-Guided Detoxification of LLMs","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2605.13329","title":"Tracing Persona Vectors Through LLM Pretraining","created":"2026-05-13","cited_by_count":7,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2410.16672","title":"The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models","created":"2024-10-22","cited_by_count":5,"area":null},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2503.13390","title":"Aligned Probing: Relating Toxic Behavior and Model Internals","created":"2025-03-17","cited_by_count":5,"area":null},{"id":"2505.16722","title":"Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2507.00985","title":"Discourse Heuristics For Paradoxically Moral Self-Correction","created":"2025-07-01","cited_by_count":3,"area":null},{"id":"2508.11281","title":"ToxiFrench: Benchmarking and Enhancing Language Models via CoT Fine-Tuning for French Toxicity Detection","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2509.17866","title":"Understanding Post-Training Structural Changes in Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2509.24169","title":"Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.13183","title":"DSCD: Large Language Model Detoxification with Self-Constrained Decoding","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2604.14602","title":"CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2410.20513","title":"Self-correction is Not An Innate Capability in Language Models","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2412.18053","title":"Neuron Empirical Gradient: Discovering and Quantifying Neurons Global Linear Controllability","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2602.00533","title":"Convergent World Representations and Divergent Tasks","created":"2026-01-31","cited_by_count":2,"area":null},{"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":"2606.22676","title":"Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations","created":"2026-06-21","cited_by_count":2,"area":null},{"id":"2406.02577","title":"Are PPO-ed Language Models Hackable?","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2407.10949","title":"Representing Rule-based Chatbots with Transformers","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2503.12882","title":"DAPI: Domain Adaptive Toxicity Probe Vector Intervention for Fine-Grained Detoxification","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2508.15875","title":"NEAT: Concept driven Neuron Attribution in LLMs","created":"2025-08-21","cited_by_count":1,"area":null},{"id":"2510.07290","title":"On the Convergence of Moral Self-Correction in Large Language Models","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.17795","title":"What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2606.18656","title":"The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2606.19542","title":"Tracking Representation Dynamics in Large Language Models with Persistent Homology","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2610.05292","title":"Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State","created":"2026-10-04","cited_by_count":1,"area":null},{"id":"2504.09191","title":"Feature-Aware Malicious Output Detection and Mitigation","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2510.20428","title":"An Empirical Study of Sample Selection Strategies for Large Language Model Repair","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.03079","title":"Learning to Diagnose and Correct Moral Errors: Beyond Shallow Heuristics in Moral Alignment","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2603.21658","title":"A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.19124","title":"Detoxification for LLM: From Dataset Itself","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.24583","title":"Measuring Alignment-Induced Activation Shifts Correctly: A Template-Controlled Difference-in-Differences Protocol","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.03648","title":"Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.28959","title":"Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates","created":"2026-07-31","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":"2608.15772","title":"Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2610.17093","title":"SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}