cs.CL（2023-12-06）

📊 共 7 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

#	题目	一句话要点	标签	🔗
1	Think from Words(TFW): Initiating Human-Like Cognition in Large Language Models Through Think from Words for Japanese Text-level Classification	提出Think from Words方法，提升LLM在日语文本分类任务中类人认知能力。	large language model chain-of-thought
2	Efficient Large Language Models: A Survey	综述高效大型语言模型，从模型、数据和框架三方面系统性地回顾和分析相关研究。	large language model	✅
3	Exploring the Reversal Curse and Other Deductive Logical Reasoning in BERT and GPT-Based Large Language Models	研究揭示BERT免疫反转诅咒，但复杂逻辑推理能力仍有局限	large language model
4	Teaching Specific Scientific Knowledge into Large Language Models through Additional Training	通过增量训练将特定科学知识注入大型语言模型	large language model
5	Improving Activation Steering in Language Models with Mean-Centring	提出基于均值中心化的激活向量引导方法，提升语言模型控制能力	large language model
6	Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment	Holmes：面向异构网卡集群的分布式LLM训练框架	large language model

#	题目	一句话要点	标签	🔗	⭐
7	DBCopilot: Natural Language Querying over Massive Databases via Schema Routing	DBCopilot：提出一种基于模式路由的大规模数据库自然语言查询框架。	semantic mapping semantic map large language model