{"total":64,"rows":[{"id":"2505.23836","title":"Large Language Models Often Know When They Are Being Evaluated","created":"2025-05-28","cited_by_count":128,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2505.12038","title":"Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets","created":"2025-05-17","cited_by_count":18,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2412.06748","title":"Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models","created":"2024-12-09","cited_by_count":14,"area":null},{"id":"2506.24068","title":"STACK: Adversarial Attacks on LLM Safeguard Pipelines","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2511.22662","title":"Difficulties with Evaluating a Deception Detector for AIs","created":"2025-11-27","cited_by_count":13,"area":null},{"id":"2502.14828","title":"Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs","created":"2025-02-20","cited_by_count":10,"area":null},{"id":"2504.06011","title":"Llama-3-Nanda-10B-Chat: An Open Generative Large Language Model for Hindi","created":"2025-04-08","cited_by_count":10,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2501.05396","title":"FairCoder: Probing LLM Bias in High-Stakes Decision Making via Coding Tasks","created":"2025-01-09","cited_by_count":9,"area":null},{"id":"2506.00643","title":"SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questions","created":"2025-05-31","cited_by_count":9,"area":null},{"id":"2412.15035","title":"LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2412.06843","title":"Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs","created":"2024-12-07","cited_by_count":4,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2406.04220","title":"BEADs: Bias Evaluation Across Domains","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2603.26676","title":"Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2606.03330","title":"FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2505.17131","title":"Relative Bias: A Comparative Framework for Quantifying Bias in LLMs","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2512.11986","title":"Learning to Extract Context for Context-Aware LLM Inference","created":"2025-12-12","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2604.06233","title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2504.03822","title":"Arti-\"fickle\" Intelligence: Using LLMs as a Tool for Inference in the Political and Social Sciences","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2602.04521","title":"$C$-$\\Delta\\Theta$: Circuit-Restricted Weight Arithmetic for Selective Refusal","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.16149","title":"Toward Trustworthy Portrait Editing: Evaluation of Demographic Misrepresentation in I2I Models","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2602.21556","title":"Power and Limitations of Aggregation in Compound AI Systems","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2605.16364","title":"WASIL: In-the-Wild Arabic Spoken Interactions with LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.21545","title":"RefusalBench: Why Refusal Rate Misranks Frontier LLMs on Biological Research Prompts","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.05177","title":"MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2606.12429","title":"Muse Spark Safety & Preparedness Report","created":"2026-05-14","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":"2607.05842","title":"Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2607.10455","title":"ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm","created":"2026-07-11","cited_by_count":1,"area":null},{"id":"2607.13039","title":"Safeguard-Conditioned Uplift: Measuring Utility-Risk Frontiers for Dual-Use Biology Assistants","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2607.13346","title":"The Refusal Residue: When Probes Catch Alignment Faking and When They Don't","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2506.06391","title":"From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2509.09043","title":"Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation","created":"2025-09-10","cited_by_count":0,"area":null},{"id":"2510.11834","title":"Don't Walk the Line: Boundary Guidance for Filtered Generation","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2602.14529","title":"Disentangling Deception and Hallucination Failures in LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.07709","title":"IatroBench: A Pre-Registered Benchmark of Clinical Omission in Language Models","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.12875","title":"AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.20262","title":"Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.23974","title":"AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.27747","title":"Soft Specialists: $\\alpha$-R\\'enyi Ensembles for Uncertainty-Aware LLM Post-Training","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.05356","title":"ReCal3R: Reliability-Calibrated Learning Rates for Streaming 3D Reconstruction","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.11292","title":"The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.00180","title":"C-Instrument: Automating RL Data Generation and Hillclimbing with a Constitution-Grid Instrument","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.06578","title":"From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.06898","title":"How Should I Pick a Foundation Model for My Robot? In Favor of a Community Evaluation Framework for Social Robots","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.21570","title":"A Reproducible, License-Aware Distillation Recipe for CPUDeployable Safety Classification","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.22887","title":"Proxy reliance in large language model decisions is uncalibrated to predictive evidence","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.01210","title":"Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02707","title":"Door-in-the-Face Requests and Refusal Behaviour in Large Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.35028","title":"VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01170","title":"HeadEdit: Calibrating Language Model Behavior Through the Frozen Unembedding Matrix","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.01535","title":"False Floors: LLM Safety Routing Evaluations Break Under Distribution Shift","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15415","title":"Sensitivity or Criterion? Measuring and Moving When Language Models Act","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.19948","title":"When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}