{"total":52,"rows":[{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19,"area":"alignment"},{"id":"2603.12277","title":"Prompt Injection as Role Confusion","created":"2026-02-22","cited_by_count":17,"area":"safety"},{"id":"2509.26238","title":"Beyond Linear Probes: Dynamic Safety Monitoring for Language Models","created":"2025-09-30","cited_by_count":16,"area":"safety"},{"id":"2601.18076","title":"Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming","created":"2026-01-26","cited_by_count":15,"area":"safety"},{"id":"2603.10521","title":"IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs","created":"2026-03-11","cited_by_count":15,"area":"safety"},{"id":"2510.08240","title":"The Alignment Waltz: Jointly Training Agents to Collaborate for Safety","created":"2025-10-09","cited_by_count":10,"area":"agents"},{"id":"2510.17017","title":"SafeSearch: Do Not Trade Safety for Utility in LLM Search Agents","created":"2025-10-19","cited_by_count":9,"area":"agents"},{"id":"2607.26115","title":"GPT-Red: Automated Red Teaming via Self-Play at Scale","created":"2026-07-28","cited_by_count":8,"area":"synth"},{"id":"2509.19212","title":"Steering Multimodal Large Language Models Decoding for Context-Aware Safety","created":"2025-09-23","cited_by_count":7,"area":"mllm"},{"id":"2601.07087","title":"When Should We Introduce Safety Interventions During Pretraining?","created":"2026-01-11","cited_by_count":7,"area":"safety"},{"id":"2510.04320","title":"Read the Scene, Not the Script: Outcome-Aware Safety for LLMs","created":"2025-10-05","cited_by_count":6,"area":"alignment"},{"id":"2510.10846","title":"DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models","created":"2025-10-12","cited_by_count":6,"area":"mllm"},{"id":"2602.22303","title":"Training Agents to Self-Report Misbehavior","created":"2026-02-25","cited_by_count":6,"area":"agents"},{"id":"2510.06915","title":"LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling","created":"2025-10-08","cited_by_count":5,"area":"alignment"},{"id":"2603.15800","title":"Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory","created":"2026-03-16","cited_by_count":5,"area":"lr"},{"id":"2604.18463","title":"Using large language models for embodied planning introduces systematic safety risks","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2509.09870","title":"Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks","created":"2025-09-11","cited_by_count":4,"area":"agents"},{"id":"2601.17642","title":"Health-ORSC-Bench: A Benchmark for Measuring Over-Refusal and Safety Completion in Health Context","created":"2026-01-25","cited_by_count":4,"area":"alignment"},{"id":"2605.31140","title":"EvoDefense: Co-Evolving Black-Box Defense with Large Language Models","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2510.08158","title":"Beyond Over-Refusal: Scenario-Based Diagnostics and Post-Hoc Mitigation for Exaggerated Refusals in LLMs","created":"2025-10-09","cited_by_count":3,"area":"safety"},{"id":"2512.20061","title":"Scaling Reinforcement Learning for Content Moderation with Large Language Models","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2512.20164","title":"AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2605.08930","title":"Internalizing Safety Understanding in Large Reasoning Models via Verification","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2510.01255","title":"Longitudinal Monitoring of LLM Content Moderation of Social Issues","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2602.06325","title":"Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent","created":"2026-02-06","cited_by_count":2,"area":"agents"},{"id":"2606.02423","title":"Investigating and Alleviating Harm Amplification in LLM Interactions","created":"2026-06-01","cited_by_count":2,"area":"safety"},{"id":"2607.02047","title":"OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2509.17177","title":"FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions","created":"2025-09-21","cited_by_count":1,"area":"lr"},{"id":"2510.10452","title":"Steering Over-refusals Towards Safety in Retrieval Augmented Generation","created":"2025-10-12","cited_by_count":1,"area":"rag"},{"id":"2602.05110","title":"Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2602.15689","title":"A Content-Based Framework for Cybersecurity Refusal Decisions in Large Language Models","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"id":"2604.17299","title":"Cat-DPO: Category-Adaptive Safety Alignment","created":"2026-04-19","cited_by_count":1,"area":"alignment"},{"id":"2605.05678","title":"Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.31381","title":"LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.19168","title":"Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflection","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2607.27951","title":"Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.30856","title":"You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals","created":"2026-08-31","cited_by_count":1,"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":"2604.01504","title":"Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Once","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.05179","title":"Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering","created":"2026-04-06","cited_by_count":0,"area":"safety"},{"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":"2604.24082","title":"Jailbreaking Frontier Foundation Models Through Intention Deception","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2605.22771","title":"Reducing Political Manipulation with Consistency Training","created":"2026-05-21","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":"2606.05614","title":"Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack","created":"2026-06-04","cited_by_count":0,"area":"safety"},{"id":"2607.02914","title":"Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models","created":"2026-07-03","cited_by_count":0,"area":"alignment"},{"id":"2607.14285","title":"ToolAlignBench: Investigating Alignment Conflicts in Tool-Calling Enabled LLMs","created":"2026-07-15","cited_by_count":0,"area":"agents"},{"id":"2607.26200","title":"Choosing Where and How to Moderate: End-to-End Trade-offs in Filter Placement and Response Rewriting","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.22490","title":"Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages","created":"2026-08-23","cited_by_count":0,"area":"alignment"},{"id":"2608.30197","title":"ALTSTEER: Selective Safety Steering for Moving Beyond Hard Refusals to Constructive Alternatives","created":"2026-08-31","cited_by_count":0,"area":"alignment"},{"id":"2609.29837","title":"PUBG Ally: A Conversational Embodied Agent as an AI Teammate","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.11005","title":"How Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense","created":"2026-10-07","cited_by_count":0,"area":"alignment"}],"next_cursor":null}