cs.CL（2023-12-04）

📊 共 13 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models	提出检索增强的多模态思维链推理方法，提升大语言模型在复杂推理任务上的性能。	large language model chain-of-thought
2	Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication	提出Exchange-of-Thought框架，通过跨模型通信增强LLM的复杂推理能力	large language model chain-of-thought
3	Zero- and Few-Shots Knowledge Graph Triplet Extraction with Large Language Models	利用大语言模型进行零样本和少样本知识图谱三元组抽取	large language model
4	Data Management For Training Large Language Models: A Survey	综述：面向大语言模型训练的数据管理方法研究	large language model	✅
5	A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video	提出多模态视频摘要任务，同步提取关键帧并生成对应标题，构建数据集并提供基线系统。	multimodal
6	Competition-Level Problems are Effective LLM Evaluators	利用竞赛级编程题评估大语言模型的推理能力与数据污染问题	large language model chain-of-thought
7	Measuring Distributional Shifts in Text: The Advantage of Language Model-Based Embeddings	提出基于LLM嵌入的文本分布偏移度量方法，提升模型监控中数据漂移的敏感性。	large language model
8	TPPoet: Transformer-Based Persian Poem Generation using Minimal Data and Advanced Decoding Techniques	TPPoet：提出一种基于Transformer的波斯语诗歌生成模型，利用少量数据和高级解码技术提升生成质量。	large language model
9	Magicoder: Empowering Code Generation with OSS-Instruct	Magicoder：利用OSS-Instruct赋能代码生成，媲美顶尖模型	large language model
10	A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia	提出Fakepedia数据集，用于评估和分析大型语言模型中的上下文信息采纳能力。	large language model
11	Know Your Audience: Do LLMs Adapt to Different Age and Education Levels?	评估LLM在不同年龄和教育水平下的文本适应性，揭示其在教育场景应用的局限性	large language model
12	Near-real-time Earthquake-induced Fatality Estimation using Crowdsourced Data and Large-Language Models	利用众包数据和大型语言模型，实现近实时地震伤亡估计	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	🔗	⭐
13	Expand BERT Representation with Visual Information via Grounded Language Learning with Multimodal Partial Alignment	GroundedBERT：利用多模态部分对齐扩展BERT的视觉信息表示	representation learning multimodal visual grounding

⬅️ 返回 cs.CL 首页 · 🏠 返回主页