cs.CL（2024-09-23）

📊 共 26 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) (23 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models 利用多模态大语言模型探索声音象征主义现象，分析模型“听觉”能力 large language model multimodal
2 Lost in the Logic: An Evaluation of Large Language Models' Reasoning Capabilities on LSAT Logic Games 评估大语言模型在LSAT逻辑游戏中的推理能力，并提出改进方案。 large language model chain-of-thought
3 OmniBench: Towards The Future of Universal Omni-Language Models OmniBench：面向通用全语言模型的综合性多模态评测基准 large language model multimodal instruction following
4 PALLM: Evaluating and Enhancing PALLiative Care Conversations with Large Language Models PALLM：利用大型语言模型评估并提升姑息治疗对话质量 large language model
5 Enhancing Aspect-based Sentiment Analysis in Tourism Using Large Language Models and Positional Information 提出ACOS_LLM模型，利用大语言模型和位置信息增强旅游领域面向属性的情感分析。 large language model
6 Knowledge Planning in Large Language Models for Domain-Aligned Counseling Summarization 提出PIECE框架，利用知识规划增强LLM在心理咨询总结中的领域对齐能力 large language model
7 End-to-End Graph Flattening Method for Large Language Models 提出端到端有向无环图路径提示方法以提升长距离推理能力 large language model
8 Past Meets Present: Creating Historical Analogy with Large Language Models 提出基于大语言模型的历史类比方法，并引入自反思机制缓解幻觉与刻板印象 large language model
9 Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method 提出基于发散校准的方法以改进大语言模型预训练数据检测 large language model ✅
10 Do Large Language Models have Problem-Solving Capability under Incomplete Information Scenarios? 提出BrainKing游戏，评估LLM在不完备信息下的问题解决能力 large language model
11 Privacy Policy Analysis through Prompt Engineering for LLMs 提出PAPEL框架，利用Prompt工程和LLM自动分析隐私政策，提升可理解性。 large language model chain-of-thought
12 MTP: A Dataset for Multi-Modal Turning Points in Casual Conversations 提出MTP多模态数据集，用于识别对话中情绪、决策等转变的关键转折点。 large language model TAMP
13 In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models 揭示大语言模型在情境学习中存在类似婴儿的A-Not-B错误 large language model
14 CUTE: Measuring LLMs' Understanding of Their Tokens CUTE：评估大型语言模型对其tokens的正字法理解能力 large language model
15 Fully automatic extraction of morphological traits from the Web: utopia or reality? 利用大型语言模型自动从网络提取植物形态特征 large language model
16 Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from Publications 提出基于RAG的BCO助手，自动化生成BioCompute Object以提升科研可重复性。 large language model ✅
17 Evaluating the Usability of LLMs in Threat Intelligence Enrichment 评估大型语言模型在威胁情报增强中的可用性，提升安全专业人员的工作效率。 large language model
18 Brotherhood at WMT 2024: Leveraging LLM-Generated Contextual Conversations for Cross-Lingual Image Captioning 利用LLM生成上下文对话，Brotherhood团队在WMT 2024跨语言图像描述任务中取得佳绩。 large language model
19 Generative LLM Powered Conversational AI Application for Personalized Risk Assessment: A Case Study in COVID-19 提出基于生成式LLM的会话式AI应用，用于COVID-19个性化风险评估，无需编程。 large language model
20 Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely 提出RAG任务分类法，综述增强LLM利用外部数据的技术，助力LLM在专业领域更有效应用。 large language model
21 OMPar: Automatic Parallelization with AI-Driven Source-to-Source Compilation OMPar：利用AI驱动的源到源编译实现自动并行化 large language model
22 Parse Trees Guided LLM Prompt Compression 提出PartPrompt，一种基于句法树引导的大语言模型提示压缩方法，提升效率并保持性能。 large language model
23 ERABAL: Enhancing Role-Playing Agents through Boundary-Aware Learning ERABAL：通过边界感知学习增强角色扮演Agent 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🔗⭐
24 A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor? 初步研究o1在医学领域的应用，探索AI医生可能性 reinforcement learning large language model chain-of-thought ✅
25 Orthogonal Finetuning for Direct Preference Optimization 提出正交微调方法RoPO，解决DPO模型过拟合问题，提升生成多样性。 DPO direct preference optimization
26 ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback ToolPlanner：通过工具增强的LLM，利用多粒度指令、路径规划和反馈机制 reinforcement learning instruction following

⬅️ 返回 cs.CL 首页 · 🏠 返回主页