cs.CL（2025-01-17）

📊 共 11 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#	题目	一句话要点	标签	🔗	⭐
1	The Geometry of Tokens in Internal Representations of Large Language Models	研究大型语言模型内部表征中token几何结构与next token预测的关系	large language model
2	Theme-Explanation Structure for Table Summarization using Large Language Models: A Case Study on Korean Tabular Data	提出基于主题-解释结构的表格摘要生成方法Tabular-TX，提升LLM在韩语表格数据上的可解释性。	large language model
3	Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models	提出注意力引导的自反思方法，用于大语言模型中的零样本幻觉检测	large language model
4	Adapting Large Language Models for Character-based Augmentative and Alternative Communication	提出一种基于Subword LLM的字符预测方法，提升AAC场景下的文本生成效率	large language model
5	Computational Protein Science in the Era of Large Language Models (LLMs)	利用大型语言模型赋能计算蛋白质科学，推动序列-结构-功能范式发展	large language model
6	MSTS: A Multimodal Safety Test Suite for Vision-Language Models	提出MSTS：一个用于评估视觉-语言模型安全性的多模态测试套件	multimodal
7	A Survey on Multi-Turn Interaction Capabilities of Large Language Models	综述大型语言模型在多轮交互能力上的研究进展与未来方向	large language model
8	Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval	提出一种多阶段训练的伊斯兰双语LLM，用于提升神经段落检索性能。	large language model
9	ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario	ComplexFuncBench：长程上下文下多步约束函数调用评测基准	large language model	✅
10	Agent-as-Judge for Factual Summarization of Long Narratives	提出 NarrativeFactScore，利用 Agent-as-Judge 评估长叙事文本摘要的事实准确性。	large language model
11	FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs	提出FRAG：一种灵活的基于知识图谱的检索增强生成模块化框架	large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页