cs.CL（2025-12-05）

📊 共 18 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation TeleTables：用于评估大语言模型在电信表格理解能力上的基准数据集 large language model multimodal
2 M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG 提出M4-RAG，一个大规模多语言多文化多模态RAG基准，用于评估跨语言和模态的检索增强VQA。 multimodal
3 Optimizing Medical Question-Answering Systems: A Comparative Study of Fine-Tuned and Zero-Shot Large Language Models with RAG Framework 提出基于RAG的医学问答系统，结合微调LLM提升准确率并减少幻觉 large language model
4 Interleaved Latent Visual Reasoning with Selective Perceptual Modeling 提出ILVR框架，通过交错潜在视觉推理提升多模态大语言模型性能。 large language model multimodal ✅
5 ArtistMus: A Globally Diverse, Artist-Centric Benchmark for Retrieval-Augmented Music Question Answering 提出ArtistMus：一个以艺术家为中心的、全局多样性的音乐问答检索增强基准。 large language model multimodal
6 Structured Reasoning with Tree-of-Thoughts for Bengali Math Word Problems 提出树状思维结构以解决孟加拉数学文字问题 large language model chain-of-thought
7 Exposing Pink Slime Journalism: Linguistic Signatures and Robust Detection Against LLM-Generated Threats 针对LLM生成的新型粉红泥新闻，提出一种鲁棒的检测框架，提升检测性能。 large language model
8 Efficient Text Classification with Conformal In-Context Learning 提出Conformal In-Context Learning (CICLe)框架，提升LLM文本分类效率与泛化性。 large language model
9 Attribute-Aware Controlled Product Generation with LLMs for E-commerce 提出一种基于LLM的属性感知控制产品生成框架，用于电商数据增强。 large language model
10 Dynamic Alignment for Collective Agency: Toward a Scalable Self-Improving Framework for Open-Ended LLM Alignment 提出动态对齐框架，实现LLM在集体能动性上的可扩展自改进对齐 large language model
11 A Greek Government Decisions Dataset for Public-Sector Analysis and Insight 构建希腊政府决策数据集，并探索其在公共部门信息检索与推理中的应用。 large language model
12 SEA-SafeguardBench: Evaluating AI Safety in SEA Languages and Cultures SEA-SafeguardBench：评估东南亚语言和文化背景下的人工智能安全性 large language model
13 LMSpell: Neural Spell Checking for Low-Resource Languages 提出LMSpell，用于低资源语言的神经拼写检查工具包 large language model
14 SQ-format: A Unified Sparse-Quantized Hardware-friendly Data Format for LLMs 提出SQ-format：一种统一的稀疏量化硬件友好型LLM数据格式 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
15 Empathy by Design: Aligning Large Language Models for Healthcare Dialogue 提出基于DPO的对齐框架，提升大型语言模型在医疗对话中的共情能力。 reinforcement learning DPO direct preference optimization ✅
16 Grounded Multilingual Medical Reasoning for Question Answering with Large Language Models 提出基于医学知识增强的多语言医学问答推理方法，提升大语言模型性能。 distillation large language model
17 MedTutor-R1: Socratic Personalized Medical Teaching with Multi-Agent Simulation MedTutor-R1：基于多智能体模拟的苏格拉底式个性化医学教学 reinforcement learning large language model multimodal
18 Learning from Self Critique and Refinement for Faithful LLM Summarization 提出SCRPO自监督框架，提升LLM在文本摘要任务中的忠实度 preference learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页