cs.CL（2025-06-21）

📊 共 7 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation	Step-Opt：通过迭代数据合成与结构化验证提升LLM在优化建模中的能力	large language model	✅
2	TyphoFormer: Language-Augmented Transformer for Accurate Typhoon Track Forecasting	提出TyphoFormer，利用语言增强Transformer提升台风路径预测精度	large language model
3	The Evolution of Natural Language Processing: How Prompt Optimization and Language Models are Shaping the Future	综述提示优化策略：提升大型语言模型在自然语言处理任务中的性能	large language model
4	Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs	揭示LLM中的潜在记忆锚点：答案中心还是推理驱动？	large language model
5	DuaShepherd: Integrating Stepwise Correctness and Potential Rewards for Mathematical Reasoning	DuaShepherd：融合逐步正确性和潜在奖励，提升LLM的数学推理能力	large language model

#	题目	一句话要点	标签	🔗	⭐
6	TPTT: Transforming Pretrained Transformers into Titans	TPTT框架：通过线性化注意力与内部记忆门控增强预训练Transformer模型	linear attention large language model	✅
7	AdaptGOT: A Pre-trained Model for Adaptive Contextual POI Representation Learning	AdaptGOT：一种用于自适应上下文POI表示学习的预训练模型	representation learning