cs.CL（2025-03-19）

📊 共 25 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (24 🔗6) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models MMDT：用于评估多模态大模型安全性与可信度的综合平台 foundation model multimodal ✅
2 SemEval-2025 Task 1: AdMIRe -- Advancing Multimodal Idiomaticity Representation AdMiRe任务旨在提升模型在多模态语境下对习语的理解和表征能力。 large language model multimodal
3 A Review on Large Language Models for Visual Analytics 综述：大型语言模型赋能可视化分析，提升数据洞察与交互能力 large language model multimodal
4 Exploring Large Language Models for Word Games:Who is the Spy? 提出基于CoT的调度框架，提升LLM在“谁是卧底”游戏中角色推断和身份伪装能力 large language model chain-of-thought ✅
5 ChatGPT or A Silent Everywhere Helper: A Survey of Large Language Models 全面分析大型语言模型ChatGPT的架构、训练及应用 large language model
6 Real-world validation of a multimodal LLM-powered pipeline for High-Accuracy Clinical Trial Patient Matching leveraging EHR data 提出基于多模态LLM的临床试验患者匹配流程，提升准确率和效率 multimodal
7 Benchmarking Open-Source Large Language Models on Healthcare Text Classification Tasks 评估开源大语言模型在医疗文本分类任务中的性能表现 large language model
8 MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models 提出MASS框架，利用技能图谱进行数学领域大语言模型预训练的数据选择。 large language model
9 Enhancing Pancreatic Cancer Staging with Large Language Models: The Role of Retrieval-Augmented Generation 利用检索增强生成提升胰腺癌分期准确性 large language model
10 SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Models 提出SPILL，一种基于大语言模型选择和池化的领域自适应意图聚类方法 large language model
11 A Foundational individual Mobility Prediction Model based on Open-Source Large Language Models 提出基于开源大语言模型的个体移动预测基础模型，提升城市适应性和用户泛化性 large language model
12 Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models Poly-FEVER：多语言事实核查基准，用于检测大型语言模型中的幻觉 large language model ✅
13 Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings 提出ContextualJudgeBench，用于评估LLM在上下文场景下的评判能力。 large language model instruction following
14 MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer MetaLadder：通过类比问题推理迁移提升数学问题求解质量 large language model chain-of-thought ✅
15 Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systems 评估并缓解检索增强医学问答系统中存在的偏见问题 large language model chain-of-thought
16 Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context Solla：一种面向语音、能理解声学上下文的大语言模型 large language model multimodal
17 From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment 提出AlignX框架，实现大规模个性化LLM对齐，解决用户偏好差异问题 large language model
18 Deep Contrastive Unlearning for Language Models 提出DeepCUT框架，通过对比学习优化LLM潜在空间，实现高效的机器遗忘。 large language model
19 ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant ECLAIR：增强企业AI助手中交互式响应的澄清能力 large language model
20 Inside-Out: Hidden Factual Knowledge in LLMs 揭示LLM内部隐藏知识：提出内外知识评估框架，发现模型内部知识远超外部表现。 large language model
21 Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification 提出基于模型编辑的LLM微调方法，高效解决面向方面的情感分类问题 large language model
22 SPADE: Structured Prompting Augmentation for Dialogue Enhancement in Machine-Generated Text Detection 提出SPADE框架以解决合成对话检测数据不足问题 large language model ✅
23 LLM Alignment for the Arabs: A Homogenous Culture or Diverse Ones? 强调阿拉伯文化多样性，呼吁NLP社区构建更具代表性的阿拉伯语LLM large language model
24 EmpathyAgent: Can Embodied Agents Conduct Empathetic Actions? 提出EmpathyAgent基准，评估和提升具身智能体在多场景下的共情行为能力 multimodal ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
25 The CLEF-2025 CheckThat! Lab: Subjectivity, Fact-Checking, Claim Normalization, and Retrieval CLEF-2025 CheckThat! Lab：多语言平台在线信息操纵与虚假信息识别技术 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页