{"total":38,"rows":[{"id":"2411.13577","title":"WavChat: A Survey of Spoken Dialogue Models","created":"2024-11-15","cited_by_count":90,"area":null},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53,"area":null},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2412.18537","title":"Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation","created":"2024-12-24","cited_by_count":24,"area":null},{"id":"2405.14488","title":"MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2406.10311","title":"CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models","created":"2024-06-14","cited_by_count":15,"area":null},{"id":"2502.07577","title":"Automated Capability Discovery via Foundation Model Self-Exploration","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2408.04643","title":"Risks, Causes, and Mitigations of Widespread Deployments of Large Language Models (LLMs): A Survey","created":"2024-08-01","cited_by_count":8,"area":null},{"id":"2503.19540","title":"FLEX: A Benchmark for Evaluating Robustness of Fairness in Large Language Models","created":"2025-03-25","cited_by_count":8,"area":null},{"id":"2410.18491","title":"ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models","created":"2024-10-24","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":"2410.20016","title":"Vulnerability of LLMs to Vertically Aligned Text Manipulations","created":"2024-10-26","cited_by_count":6,"area":null},{"id":"2505.04673","title":"REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2406.04752","title":"CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models","created":"2024-06-07","cited_by_count":3,"area":null},{"id":"2411.07845","title":"Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements","created":"2024-11-12","cited_by_count":3,"area":null},{"id":"2504.21700","title":"XBreaking: Understanding how LLMs security alignment can be broken","created":"2025-04-30","cited_by_count":3,"area":null},{"id":"2511.22924","title":"MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2604.02359","title":"Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2509.06921","title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","created":"2025-09-08","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":"2506.23296","title":"Securing AI Systems: A Guide to Known Attacks and Impacts","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2508.20333","title":"Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2509.06807","title":"MoGU V2: Toward a Higher Pareto Frontier Between Model Usability and Security","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2604.16037","title":"Stochasticity in Tokenisation Improves Robustness","created":"2026-04-17","cited_by_count":1,"area":null},{"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":"2504.04981","title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2508.02279","title":"Dialogue Systems Engineering: A Survey and Future Directions","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2509.20381","title":"USB-Rec: An Effective Framework for Improving Conversational Recommendation Capability of Large Language Model","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2512.01514","title":"Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2601.09853","title":"MedRedFlag: Investigating how LLMs Redirect Misconceptions in Real-World Health Communication","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2607.16660","title":"From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development Practice","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2608.15893","title":"Breaking and Defending LLM-Powered Social Media Bot Detection Systems","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.00519","title":"The Safeguard Worked. Is the LLM System Safer?","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.26295","title":"On the security and privacy of LLMs in Mobility","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}