{"total":35,"rows":[{"id":"2410.17196","title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","created":"2024-10-22","cited_by_count":200,"area":null},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86,"area":null},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"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":"2406.12975","title":"SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation","created":"2024-06-18","cited_by_count":34,"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":"2504.19373","title":"Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models","created":"2025-04-27","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":"2407.07412","title":"Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2502.16776","title":"AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement","created":"2025-02-24","cited_by_count":12,"area":null},{"id":"2410.10074","title":"Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2506.02573","title":"IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languages","created":"2025-06-03","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":"2410.19230","title":"Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2505.24621","title":"Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2511.00382","title":"Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs","created":"2025-11-01","cited_by_count":4,"area":null},{"id":"2510.13183","title":"DSCD: Large Language Model Detoxification with Self-Constrained Decoding","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2512.08946","title":"Large Language Models as Search Engines: Societal Challenges","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2512.19297","title":"Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2504.09026","title":"Detecting Instruction Fine-tuning Attacks using Influence Function","created":"2025-04-12","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":"2602.02498","title":"Test-Time Detoxification without Training or Learning Anything","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2410.04155","title":"Toxic Subword Pruning for Dialogue Response Generation on Large Language Models","created":"2024-10-05","cited_by_count":1,"area":null},{"id":"2410.14765","title":"What's New in My Data? Novelty Exploration via Contrastive Generation","created":"2024-10-18","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":"2605.27117","title":"Position: AI Safety Requires Effective Controllability","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.23394","title":"Inference-Time Consensus for Mitigating Hidden Behaviors from LLM Fine-Tuning","created":"2026-07-25","cited_by_count":1,"area":null},{"id":"2406.18002","title":"Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher","created":"2024-06-26","cited_by_count":0,"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":"2512.10234","title":"InFerActive: Interactive Tree-Based Exploration of LLM Sampling for Safety Evaluation","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2605.14746","title":"Selective Safety Steering via Value-Filtered Decoding","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.20791","title":"Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling","created":"2026-07-22","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}],"next_cursor":null}