cs.CL（2026-03-30）

📊 共 11 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Categorical Perception in Large Language Model Hidden States: Structural Warping at Digit-Count Boundaries	发现大语言模型隐藏状态中存在类别知觉现象，数字计数边界处结构扭曲	large language model
2	EpiScreen: Early Epilepsy Detection from Electronic Health Records with Large Language Models	EpiScreen：利用大型语言模型从电子病历中早期检测癫痫	large language model
3	Merge and Conquer: Instructing Multilingual Models by Adding Target Language Weights	提出模型合并方法以提升低资源语言的指令遵循能力	large language model instruction following
4	Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification	提出PROClaim框架，通过法庭辩论式多智能体和渐进式RAG提升争议性声明验证的可靠性。	large language model	✅
5	Adaptive Block-Scaled Data Types	提出自适应块缩放数据类型IF4，提升低比特量化语言模型性能	large language model	✅
6	EarlySciRev: A Dataset of Early-Stage Scientific Revisions Extracted from LaTeX Writing Traces	提出EarlySciRev数据集，用于研究科学写作早期修订行为和评估LLM在科学写作中的能力。	large language model
7	\textit{Versteasch du mi?} Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Language	探讨GenAI和LLM对非标准语言的公平性，并提出技术和社会语言学视角的解决方案。	large language model
8	From Reviews to Requirements: Can LLMs Generate Human-Like User Stories?	利用大型语言模型从用户评论生成高质量用户故事，提升软件需求工程效率。	large language model
9	Transfer Learning for an Endangered Slavic Variety: Dependency Parsing in Pomak Across Contact-Shaped Dialects	针对濒危斯拉夫语波马克语，提出跨方言迁移的依存句法分析方法	zero-shot transfer
10	EnsemJudge: Enhancing Reliability in Chinese LLM-Generated Text Detection through Diverse Model Ensembles	EnsemJudge：通过多样模型集成提升中文LLM生成文本检测的可靠性	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	DongYuan: An LLM-Based Framework for Integrative Chinese and Western Medicine Spleen-Stomach Disorders Diagnosis	DongYuan：一个基于LLM的中西医结合脾胃病诊断框架	DPO direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页