cs.CL（2024-09-27）

📊 共 19 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models	Ruler：一种模型无关的方法，用于控制大型语言模型的生成长度	large language model instruction following	✅
2	Individuation in Neural Models with and without Visual Grounding	对比CLIP与文本模型在个体化信息编码上的差异，揭示CLIP更优的量化个体能力。	visual grounding
3	Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical education	AIPatient：基于大语言模型的模拟病人系统，革新医学教育	large language model
4	A Survey on the Honesty of Large Language Models	大型语言模型（LLMs）的诚实性研究综述：定义、评估与改进策略	large language model
5	Research on Predicting Public Opinion Event Heat Levels Based on Large Language Models	提出基于大语言模型的舆情事件热度预测方法，探索LLM在舆情分析中的应用潜力	large language model
6	Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications	利用长文本大语言模型解决企业应用中的多文档理解与摘要问题	large language model
7	SciDFM: A Large Language Model with Mixture-of-Experts for Science	SciDFM：一个面向科学领域，采用混合专家模型的大语言模型	large language model	✅
8	Hit the Sweet Spot! Span-Level Ensemble for Large Language Models	提出SweetSpan：一种面向大语言模型的跨度级集成方法，提升生成质量和鲁棒性。	large language model
9	LML-DAP: Language Model Learning a Dataset for Data-Augmented Prediction	提出LML-DAP框架，利用LLM进行数据增强预测，提升分类任务的可解释性和准确性。	large language model	✅
10	Soft Measures for Extracting Causal Collective Intelligence	提出基于LLM和软相似度量的方法，用于从文本中提取因果集体智能FCM。	large language model
11	On the Power of Decision Trees in Auto-Regressive Language Modeling	探索自回归决策树在语言建模中的潜力，实现复杂函数计算与文本生成。	chain-of-thought
12	Uncovering Differences in Persuasive Language in Russian versus English Wikipedia	利用大语言模型识别维基百科俄语和英语文章中的说服性语言差异，揭示文化视角差异	large language model
13	IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation	IDGen：通过项目区分度诱导的提示生成，用于大语言模型评估	large language model
14	"Why" Has the Least Side Effect on Model Editing	研究问题类型对模型编辑副作用的影响，并探索小模型洞察在大模型上的迁移性	large language model
15	A Survey on Complex Tasks for Goal-Directed Interactive Agents	综述：目标导向交互式Agent的复杂任务研究进展与挑战	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
16	LLMs4Synthesis: Leveraging Large Language Models for Scientific Synthesis	LLMs4Synthesis框架：利用大型语言模型促进科学文献的综合分析	reinforcement learning large language model
17	Model-based Preference Optimization in Abstractive Summarization without Human Feedback	提出基于模型偏好优化的无人工反馈摘要方法，提升摘要质量和忠实度。	DPO direct preference optimization large language model
18	HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documents	提出HiCuLR，通过层级课程学习解决法律文档修辞角色标注问题	curriculum learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in Conversations	提出多方对话诊断流程，评估LLM在对话结构复杂性下的表现，聚焦响应选择和指代识别。	MPC

⬅️ 返回 cs.CL 首页 · 🏠 返回主页