cs.CL（2024-07-29）

📊 共 19 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) (19 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models Genetic-Instruct：利用进化算法大规模合成高质量代码指令，提升LLM代码生成能力 large language model
2 Inference acceleration for large language models using "stairs" assisted greedy generation 提出“阶梯”辅助贪婪生成方法，加速大型语言模型推理。 large language model
3 Sentiment Analysis of Lithuanian Online Reviews Using Large Language Models 首次将Transformer模型应用于立陶宛语在线评论情感分析，显著优于GPT-4。 large language model
4 CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare CollectiveSFT：通过医疗领域集体指令微调，提升中文医疗基准下大语言模型性能 large language model ✅
5 What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models 提出基于知识图谱增强的大语言模型对话生成框架，提升RPG游戏角色互动沉浸感。 large language model
6 Exploring Large Language Models to generate Easy to Read content 利用大型语言模型生成易于阅读的内容，提升认知障碍人士的信息可访问性。 large language model
7 Comparative Analysis of Encoder-Based NER and Large Language Models for Skill Extraction from Russian Job Vacancies 对比Encoder与LLM，用于俄语招聘信息技能提取，发现传统NER模型更优 large language model
8 Cool-Fusion: Fuse Large Language Models without Training 提出Cool-Fusion，一种无需训练融合异构大语言模型的方法。 large language model
9 VolDoGer: LLM-assisted Datasets for Domain Generalization in Vision-Language Tasks 提出VolDoGer数据集，利用LLM辅助提升视觉-语言任务的领域泛化能力 large language model multimodal
10 Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost 提出Constrained-CoT，通过约束输出长度提升LLM推理效率与正确性 large language model chain-of-thought
11 QAEA-DR: A Unified Text Augmentation Framework for Dense Retrieval QAEA-DR：一种用于稠密检索的统一文本增强框架 large language model
12 MindSearch: Mimicking Human Minds Elicits Deep AI Searcher MindSearch：模仿人类思维模式的深度AI搜索引擎 large language model
13 Do LLMs Really Adapt to Domains? An Ontology Learning Perspective 探究LLM在本体学习中领域适应性：基于词汇语义的控制实验分析 large language model
14 ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation ATHAR：一个高质量、多样化的古阿拉伯语到英语翻译数据集 large language model ✅
15 Improving Retrieval Augmented Language Model with Self-Reasoning 提出基于自推理的检索增强语言模型框架，提升可靠性和可追溯性 large language model
16 APE: Active Learning-based Tooling for Finding Informative Few-shot Examples for LLM-based Entity Matching APE：基于主动学习的工具，用于为LLM实体匹配寻找信息量大的少量样本 large language model
17 Can Editing LLMs Inject Harm? 提出编辑攻击，揭示LLM知识编辑中注入有害信息的新安全威胁 large language model
18 Legal Minds, Algorithmic Decisions: How LLMs Apply Constitutional Principles in Complex Scenarios 评估LLM在复杂法律场景中的宪法原则应用能力，揭示GPT-4的倾向性 large language model
19 Do Text-to-Vis Benchmarks Test Real Use of Visualisations? 评估文本到可视化基准测试是否反映真实用户需求，揭示现有基准与实际应用的差距 large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页