cs.CL（2025-08-21）

📊 共 7 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following	提出CoLVLM-Agent以解决复杂多轮视觉对话问题	large language model instruction following
2	Self-Guided Function Calling in Large Language Models via Stepwise Experience Recall	提出自指导函数调用方法以解决多步骤工具使用问题	large language model
3	SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning	提出SparK以解决长上下文推理中的KV缓存瓶颈问题	large language model	✅
4	SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling	提出SemToken以解决长文本语言建模中的语义感知分词问题	large language model
5	Identifying and Answering Questions with False Assumptions: An Interpretable Approach	提出一种可解释的方法以识别和回答带有错误假设的问题	large language model

#	题目	一句话要点	标签	🔗	⭐
6	CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning	提出CARFT以解决大语言模型推理能力不足的问题	reinforcement learning contrastive learning large language model	✅
7	Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models	提出Fin-PRM以解决金融领域推理模型不足问题	reinforcement learning distillation large language model	✅