Large Language Models

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models ACL 2025 SAFE: Schema-Driven Approximate Distance Join for Efficient Knowledge Graph Querying EMNLP 2025 Safety Alignment Can Be Not Superficial With Explicit Safety Signals ICML 2025 Safety in Large Reasoning Models: A Survey EMNLP 2025 Safety of Embodied Navigation: A Survey IJCAI 2025 SafetyPrompts: A Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety AAAI 2025 SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025 SAGE: A Generic Framework for LLM Safety Evaluation EMNLP 2025 SAM Decoding: Speculative Decoding via Suffix Automaton ACL 2025 Same evaluation, more tokens: On the effect of input length for machine translation evaluation using Large Language Models EMNLP 2025 Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness EMNLP 2025 Sample-aware Adaptive Structured Pruning for Large Language Models AAAI 2025 Sample Efficient Alignment Learning With Episodic Control EMNLP 2025 Sample-Efficient Behavior Cloning Using General Domain Knowledge IJCAI 2025 Sample Efficient Demonstration Selection for In-Context Learning ICML 2025 Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition ACL 2025 SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity EMNLP 2025 Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification ICML 2025 Sam’s Fans at the Crypto Trading Challenge Task: A Threshold-Based Decision Approach Based on FinMem Framework COLING 2025 Samsung Research Poland at SemEval-2025 Task 8: LLM ensemble methods for QA over tabular data SemEval 2025 SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models’ Knowledge of Indian Culture ACL 2025 Sarang at FinCausal 2025: Contextual QA for Financial Causality Detection Combining Extractive and Generative Models COLING 2025 Sarc7: Evaluating Sarcasm Detection and Generation with Seven Types and Emotion-Informed Techniques EMNLP 2025 SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage ACL 2025 SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas EMNLP 2025