{"total":94,"rows":[{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322,"area":"safety"},{"id":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2402.14020","title":"Coercing LLMs to do and reveal (almost) anything","created":"2024-02-21","cited_by_count":89,"area":"safety"},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63,"area":"safety"},{"id":"2505.24119","title":"The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It","created":"2025-05-30","cited_by_count":45,"area":"safety"},{"id":"2404.11553","title":"Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages","created":"2024-04-17","cited_by_count":38,"area":null},{"id":"2505.17306","title":"Refusal Direction is Universal Across Safety-Aligned Languages","created":"2025-05-22","cited_by_count":38,"area":null},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35,"area":null},{"id":"2402.15302","title":"How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries","created":"2024-02-23","cited_by_count":27,"area":"safety"},{"id":"2404.12318","title":"Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment","created":"2024-04-18","cited_by_count":26,"area":"alignment"},{"id":"2402.18120","title":"Exploring Multilingual Concepts of Human Value in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages?","created":"2024-02-28","cited_by_count":24,"area":"alignment"},{"id":"2404.04997","title":"Adapting LLMs for Efficient Context Processing through Soft Prompt Compression","created":"2024-04-07","cited_by_count":22,"area":"inference"},{"id":"2407.07342","title":"Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture","created":"2024-07-10","cited_by_count":22,"area":"alignment"},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2410.11459","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","created":"2024-10-15","cited_by_count":19,"area":"lr"},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19,"area":"safety"},{"id":"2502.14301","title":"SEA-HELM: Southeast Asian Holistic Evaluation of Language Models","created":"2025-02-20","cited_by_count":19,"area":null},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18,"area":null},{"id":"2411.11072","title":"Multilingual Large Language Models: A Systematic Survey","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2505.16869","title":"MPO: Multilingual Safety Alignment via Reward Gap Optimization","created":"2025-05-22","cited_by_count":18,"area":"alignment"},{"id":"2410.10801","title":"Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2410.17040","title":"Arabic Dataset for LLM Safeguard Evaluation","created":"2024-10-22","cited_by_count":17,"area":null},{"id":"2510.26418","title":"Chain-of-Thought Hijacking","created":"2025-10-30","cited_by_count":16,"area":"lr"},{"id":"2502.04322","title":"Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions","created":"2025-02-06","cited_by_count":15,"area":"alignment"},{"id":"2603.11510","title":"Tiny Aya: Bridging Scale and Multilingual Depth","created":"2026-03-12","cited_by_count":15,"area":null},{"id":"2505.00268","title":"Consistency in Language Models: Current Landscape, Challenges, and Future Directions","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13,"area":"alignment"},{"id":"2602.22983","title":"Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search","created":"2026-02-26","cited_by_count":13,"area":"safety"},{"id":"2406.13748","title":"Learn and Unlearn: Addressing Misinformation in Multilingual LLMs","created":"2024-06-19","cited_by_count":12,"area":"safety"},{"id":"2402.15727","title":"LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper","created":"2024-02-24","cited_by_count":10,"area":"safety"},{"id":"2505.21344","title":"The Multilingual Divide and Its Impact on Global AI Safety","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2506.22724","title":"The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure","created":"2025-06-28","cited_by_count":10,"area":null},{"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":"2602.16660","title":"Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment","created":"2026-02-18","cited_by_count":9,"area":"alignment"},{"id":"2506.02280","title":"The State of Large Language Models for African Languages: Progress and Challenges","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2510.15232","title":"FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domain","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2507.15339","title":"LionGuard 2: Building Lightweight, Data-Efficient & Localised Multilingual Content Moderators","created":"2025-07-21","cited_by_count":7,"area":null},{"id":"2509.13930","title":"Linguistic Nepotism: Trading-off Quality for Language Preference in Multilingual RAG","created":"2025-09-17","cited_by_count":7,"area":"rag"},{"id":"2503.07501","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2504.14452","title":"ParaPO: Aligning Language Models to Reduce Verbatim Reproduction of Pre-training Data","created":"2025-04-20","cited_by_count":6,"area":"alignment"},{"id":"2508.19089","title":"It's All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs","created":"2025-08-26","cited_by_count":6,"area":null},{"id":"2406.07971","title":"It Takes Two: On the Seamlessness between Reward and Policy Model in RLHF","created":"2024-06-12","cited_by_count":5,"area":"alignment"},{"id":"2505.24174","title":"Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2602.16201","title":"Long-Tail Knowledge in Large Language Models: Taxonomy, Mechanisms, Interventions and Implications","created":"2026-02-18","cited_by_count":5,"area":null},{"id":"2502.05568","title":"Large Multimodal Models for Low-Resource Languages: A Survey","created":"2025-02-08","cited_by_count":4,"area":"mllm"},{"id":"2602.11157","title":"Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety","created":"2025-12-08","cited_by_count":4,"area":"alignment"},{"id":"2502.09532","title":"Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2503.17932","title":"STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models","created":"2025-03-23","cited_by_count":3,"area":"safety"},{"id":"2505.19356","title":"Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrieval","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2510.13154","title":"The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs","created":"2025-10-15","cited_by_count":3,"area":"alignment"},{"id":"2511.01187","title":"Surfacing Subtle Stereotypes: A Multilingual, Debate-Oriented Evaluation of Modern LLMs","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2604.12710","title":"LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety","created":"2026-04-13","cited_by_count":3,"area":"alignment"},{"id":"2605.02971","title":"Multilingual Safety Alignment via Self-Distillation","created":"2026-05-03","cited_by_count":3,"area":"alignment"},{"id":"2409.13708","title":"Towards Safe Multilingual Frontier AI","created":"2024-09-06","cited_by_count":2,"area":"safety"},{"id":"2505.14226","title":"Phonetic Perturbations Reveal Tokenizer-Rooted Safety Gaps in LLMs","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2601.22620","title":"Layer-wise Swapping for Generalizable Multilingual Safety","created":"2026-01-30","cited_by_count":2,"area":"safety"},{"id":"2603.01211","title":"A Unified Framework to Quantify Cultural Intelligence of AI","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2606.01196","title":"Low-Resource Safety Failures Are Action Failures, Not Representation Failures","created":"2026-05-31","cited_by_count":2,"area":"alignment"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2502.02451","title":"Beyond English: Evaluating Automated Measurement of Moral Foundations in Non-English Discourse with a Chinese Case Study","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2503.13081","title":"A Framework to Assess Multilingual Vulnerabilities of LLMs","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2510.19616","title":"PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2512.16029","title":"Cross-Language Bias Examination in Large Language Models","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2605.18239","title":"Multilingual jailbreaking of LLMs using low-resource languages","created":"2026-05-18","cited_by_count":1,"area":"safety"},{"id":"2606.08451","title":"Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models","created":"2026-06-07","cited_by_count":1,"area":"alignment"},{"id":"2608.11146","title":"The Illusion of Cross-Lingual Safety in Low-Resource Languages","created":"2026-08-11","cited_by_count":1,"area":"safety"},{"id":"2608.22335","title":"Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded Harms","created":"2026-08-23","cited_by_count":1,"area":"safety"},{"id":"2609.22219","title":"Knowing, and Saying It Only When Asked: LLM Endognostics and the Schizognosis of Minerva-7B","created":"2026-09-02","cited_by_count":1,"area":"alignment"},{"id":"2506.06446","title":"Tokenization Multiplicity Leads to Arbitrary Price Variation in LLM-as-a-service","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2512.24556","title":"Safe in the Future, Dangerous in the Past: Dissecting Temporal and Linguistic Vulnerabilities in LLMs","created":"2025-12-31","cited_by_count":0,"area":"alignment"},{"id":"2601.10804","title":"BYOL: Bring Your Own Language Into LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.00497","title":"Culturally-Grounded Governance for Multilingual Language Models: Rights, Data Boundaries, and Accountable AI Design","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2603.04992","title":"ThaiSafetyBench: Assessing Language Model Safety in Thai Cultural Contexts","created":"2026-03-05","cited_by_count":0,"area":"safety"},{"id":"2604.02048","title":"Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models","created":"2026-04-02","cited_by_count":0,"area":"mllm"},{"id":"2604.08881","title":"Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models","created":"2026-04-10","cited_by_count":0,"area":"alignment"},{"id":"2604.25716","title":"Cross-Lingual Jailbreak Detection via Semantic Codebooks","created":"2026-04-28","cited_by_count":0,"area":"safety"},{"id":"2605.01224","title":"Lost in the Tower of Babel: The Adverse Effects of Incidental Multilingualism in LLMs","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.14152","title":"ROK-FORTRESS: Measuring the Effect of Geopolitical Transcreation for National Security and Public Safety","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"id":"2605.17173","title":"Why Do Safety Guardrails Degrade Across Languages?","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2605.23157","title":"Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMs","created":"2026-05-22","cited_by_count":0,"area":"mllm"},{"id":"2606.11082","title":"The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.25380","title":"A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models","created":"2026-06-24","cited_by_count":0,"area":"safety"},{"id":"2607.27917","title":"One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs","created":"2026-07-30","cited_by_count":0,"area":"mllm"},{"id":"2608.09095","title":"Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.14626","title":"LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review","created":"2026-07-20","cited_by_count":0,"area":"alignment"},{"id":"2608.18089","title":"Latent Space Refusal Anchoring for Low-Resource African Languages: Mechanistic Safety Recovery Without Retraining","created":"2026-06-05","cited_by_count":0,"area":"safety"},{"id":"2608.18131","title":"Safety Alignment Illusion: The Cross-Lingual Safety Gap in LLMs","created":"2026-07-26","cited_by_count":0,"area":"alignment"},{"id":"2608.21365","title":"KSE-Web: An Analysis of Hybrid Retrieval and LLM-Assisted Query Expansion for Low-Resource Khmer Semantic Search","created":"2026-06-17","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":"2609.06573","title":"A Translational Note on AI Safety Evaluation","created":"2026-09-06","cited_by_count":0,"area":"safety"},{"id":"2609.08515","title":"Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.29547","title":"When Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI","created":"2026-08-28","cited_by_count":0,"area":"agents"}],"next_cursor":null}