cs.CL（2025-12-20）

📊 共 8 篇论文

🎯 兴趣领域导航

#	题目	一句话要点	标签
1	AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3	AraToken：通过归一化和语言扩展优化Qwen3的阿拉伯语分词	large language model
2	LLM-based Few-Shot Early Rumor Detection with Imitation Agent	提出基于LLM和模仿Agent的少样本早期谣言检测框架，提升准确性和及时性。	large language model
3	SRS-Stories: Vocabulary-constrained multilingual story generation for language learning	提出基于词汇约束的多语言故事生成方法，用于语言学习。	large language model
4	DACE For Railway Acronym Disambiguation	DACE框架通过动态提示和知识注入解决铁路领域缩略语歧义问题	large language model
5	Towards Efficient Agents: A Co-Design of Inference Architecture and System	AgentInfer：推理架构与系统协同设计，提升LLM智能Agent效率	large language model
6	LIR$^3$AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation	提出LiR$^3$AG框架，通过重构检索证据链，提升RAG中非推理模型在多跳QA任务上的性能。	large language model

#	题目	一句话要点	标签	🔗	⭐
7	Resisting Correction: How RLHF Makes Language Models Ignore External Safety Signals in Natural Conversation	RLHF使语言模型在自然对话中忽略外部安全信号	RLHF
8	CTTA-T: Continual Test-Time Adaptation for Text Understanding via Teacher-Student with a Domain-aware and Generalized Teacher	提出CTTA-T框架，通过领域感知和泛化的Teacher-Student模型解决文本理解中的持续测试时自适应问题。	teacher-student