{"total":70,"rows":[{"id":"2502.17424","title":"Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs","created":"2025-02-24","cited_by_count":172,"area":"safety"},{"id":"2412.04261","title":"Aya Expanse: Combining Research Breakthroughs for a New Multilingual Frontier","created":"2024-12-05","cited_by_count":129,"area":null},{"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":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2412.17686","title":"Large Language Model Safety: A Holistic Survey","created":"2024-12-23","cited_by_count":59,"area":"safety"},{"id":"2504.04377","title":"PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages","created":"2025-04-06","cited_by_count":59,"area":null},{"id":"2506.10805","title":"Detecting High-Stakes Interactions with Activation Probes","created":"2025-06-12","cited_by_count":53,"area":null},{"id":"2410.15522","title":"M-RewardBench: Evaluating Reward Models in Multilingual Settings","created":"2024-10-20","cited_by_count":50,"area":"alignment"},{"id":"2408.10914","title":"To Code, or Not To Code? Exploring Impact of Code in Pre-training","created":"2024-08-20","cited_by_count":47,"area":null},{"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":"2410.08968","title":"Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements","created":"2024-10-11","cited_by_count":36,"area":"alignment"},{"id":"2410.18210","title":"Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks","created":"2024-10-23","cited_by_count":33,"area":"safety"},{"id":"2508.01710","title":"CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications","created":"2025-08-03","cited_by_count":27,"area":"agents"},{"id":"2503.09347","title":"Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts","created":"2025-03-12","cited_by_count":26,"area":null},{"id":"2409.11564","title":"Preference Tuning with Human Feedback on Language, Speech, and Vision Tasks: A Survey","created":"2024-09-17","cited_by_count":23,"area":"alignment"},{"id":"2502.05163","title":"Enhancing LLM Safety Through a Theoretical Minimax Game Lens","created":"2025-02-07","cited_by_count":19,"area":"safety"},{"id":"2407.05694","title":"On the Limitations of Compute Thresholds as a Governance Strategy","created":"2024-07-08","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":"2408.03837","title":"WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models","created":"2024-08-07","cited_by_count":17,"area":null},{"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":"2409.17892","title":"EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Models","created":"2024-09-26","cited_by_count":16,"area":null},{"id":"2504.05154","title":"CARE: Multilingual Human Preference Learning for Cultural Awareness","created":"2025-04-07","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":"2408.16961","title":"The Future of Open Human Feedback","created":"2024-08-15","cited_by_count":10,"area":"alignment"},{"id":"2410.16527","title":"Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis","created":"2024-10-21","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":"2503.04647","title":"Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment","created":"2025-03-06","cited_by_count":9,"area":"alignment"},{"id":"2504.15241","title":"MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety","created":"2025-04-21","cited_by_count":9,"area":"lr"},{"id":"2506.20544","title":"When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs","created":"2025-06-25","cited_by_count":9,"area":"lr"},{"id":"2503.00069","title":"Societal Alignment Frameworks Can Improve LLM Alignment","created":"2025-02-27","cited_by_count":8,"area":"alignment"},{"id":"2605.01687","title":"MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety","created":"2026-05-03","cited_by_count":8,"area":"safety"},{"id":"2408.14960","title":"Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2410.01735","title":"LASeR: Learning to Adaptively Select Reward Models with Multi-Armed Bandits","created":"2024-10-02","cited_by_count":7,"area":"alignment"},{"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":"2505.15935","title":"MAPS: A Multilingual Benchmark for Agent Performance and Security","created":"2025-05-21","cited_by_count":7,"area":"agents"},{"id":"2505.23856","title":"OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2510.21285","title":"When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models","created":"2025-10-24","cited_by_count":6,"area":"lr"},{"id":"2601.11778","title":"Translation as a Scalable Proxy for Multilingual Evaluation","created":"2026-01-16","cited_by_count":6,"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":"2505.24672","title":"TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis","created":"2025-05-30","cited_by_count":4,"area":"synth"},{"id":"2506.00469","title":"Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Data","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2510.13434","title":"$M^2PO$: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation","created":"2025-10-15","cited_by_count":4,"area":"alignment"},{"id":"2602.20042","title":"AI Alignment Breaks at the Edge","created":"2026-02-23","cited_by_count":4,"area":"alignment"},{"id":"2410.12499","title":"With a Grain of SALT: Are LLMs Fair Across Social Dimensions?","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2511.07691","title":"CAPO: Confidence Aware Preference Optimization Learning for Multilingual Preferences","created":"2025-11-10","cited_by_count":3,"area":"alignment"},{"id":"2512.06201","title":"K2-V2: A 360-Open, Reasoning-Enhanced LLM","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2409.13708","title":"Towards Safe Multilingual Frontier AI","created":"2024-09-06","cited_by_count":2,"area":"safety"},{"id":"2508.20201","title":"Social Bias in Multilingual Language Models: A Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2512.02711","title":"CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer","created":"2025-12-02","cited_by_count":2,"area":"safety"},{"id":"2512.20293","title":"AprielGuard","created":"2025-12-23","cited_by_count":2,"area":"agents"},{"id":"2605.05662","title":"XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity","created":"2026-05-07","cited_by_count":2,"area":"safety"},{"id":"2606.07535","title":"Multilingual Refusal Alignment for Safer Large Language Models","created":"2026-04-24","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":"2507.21782","title":"The Problem with Safety Classification is not just the Models","created":"2025-07-29","cited_by_count":1,"area":null},{"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":"2606.18606","title":"Steerable Cultural Preference Optimization of Reward Models","created":"2026-06-17","cited_by_count":1,"area":"alignment"},{"id":"2608.16577","title":"BabelSteering: Multilingual Safety Alignment via English Steering Vectors","created":"2026-08-17","cited_by_count":1,"area":"alignment"},{"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":"2411.19038","title":"DIESEL -- Dynamic Inference-Guidance via Evasion of Semantic Embeddings in LLMs","created":"2024-11-28","cited_by_count":0,"area":null},{"id":"2505.16036","title":"OpenEthics: A Comprehensive Ethical Evaluation of Open-Source Generative Large Language Models","created":"2025-05-21","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":"2608.13695","title":"Language-Specific Gaps in AI Safety Training Datasets","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.27548","title":"Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2609.01046","title":"HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.03781","title":"IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks","created":"2026-09-03","cited_by_count":0,"area":"safety"},{"id":"2609.05117","title":"TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors","created":"2026-09-04","cited_by_count":0,"area":"safety"},{"id":"2609.22494","title":"CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25298","title":"FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.15134","title":"Lumen-bench: Cross-Lingual Safety Gaps and the Say-Do Problem in Tool-Calling Large Language Models","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}