cs.CL（2024-08-26）

📊 共 23 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) (19) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Surprisingly Fragile: Assessing and Addressing Prompt Instability in Multimodal Foundation Models	揭示多模态基础模型对Prompt的脆弱性并提出数据增强缓解方案	foundation model multimodal
2	Evaluating Large Language Models on Spatial Tasks: A Multi-Task Benchmarking Study	构建多任务空间评估基准，系统评估大型语言模型在空间任务上的能力	large language model chain-of-thought
3	LLM-3D Print: Large Language Models To Monitor and Control 3D Printing	提出LLM-3D Print框架，利用大语言模型监控和控制3D打印过程，实现缺陷检测与自主纠正。	large language model
4	Classification of Safety Events at Nuclear Sites using Large Language Models	利用大型语言模型对核电站安全事件进行分类，提升安全管理效率。	large language model
5	Question answering system of bridge design specification based on large language model	构建基于大语言模型的桥梁设计规范问答系统	large language model
6	Training-Free Activation Sparsity in Large Language Models	提出TEAL：一种免训练的大语言模型激活稀疏化方法，提升推理速度。	large language model
7	Claim Verification in the Age of Large Language Models: A Survey	综述：大型语言模型时代下的声明验证技术	large language model
8	Examining Independence in Ensemble Sentiment Analysis: A Study on the Limits of Large Language Models Using the Condorcet Jury Theorem	基于孔多塞陪审团定理，研究集成情感分析中大语言模型的独立性局限	large language model
9	Focused Large Language Models are Stable Many-Shot Learners	提出FocusICL，解决LLM在多示例学习中因注意力分散导致性能下降的问题	large language model
10	Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language Models	提出ID³动态解掩参数高效微调LLM，提升计算效率并兼顾性能。	large language model
11	Explicit Inductive Inference using Large Language Models	利用大语言模型中的归因偏差进行显式归纳推理	large language model
12	Epidemic Information Extraction for Event-Based Surveillance using Large Language Models	利用大型语言模型进行事件驱动的流行病信息抽取，实现疫情监控	large language model
13	Enhancing Depression Diagnosis with Chain-of-Thought Prompting	利用思维链提示增强抑郁症诊断的准确性	chain-of-thought
14	TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models	提出TF-Attack，加速并提升大语言模型对抗攻击的迁移性。	large language model
15	On the Limitations of Language Targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning	研究多语言LLM剪枝中校准语言的影响，揭示现有剪枝方法的局限性	large language model
16	LogProber: Disentangling confidence from contamination in LLM responses	提出LogProber算法，用于检测LLM响应中因数据泄露导致的污染问题。	large language model
17	DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification	DSTI提出基于语义塔的外部知识表示方法，用于本体学习中的类型分类。	large language model
18	Evaluating ChatGPT on Nuclear Domain-Specific Data	评估ChatGPT在核领域特定数据上的问答能力，并探索RAG的增强效果	large language model
19	MODOC: A Modular Interface for Flexible Interlinking of Text Retrieval and Text Generation Functions	MODOC：一个灵活的模块化界面，用于文本检索和文本生成功能的互联互通	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	🔗	⭐
20	Large Language Model for Patent Concept Generation	提出PatentGPT，通过知识精调提升大语言模型在专利概念生成中的创新能力。	reinforcement learning RLHF large language model
21	Contrastive Learning Subspace for Text Clustering	提出子空间对比学习(SCL)方法，用于解决文本聚类中上下文信息和实例间关系建模不足的问题。	contrastive learning
22	On-Device Language Models: A Comprehensive Review	综述：端侧语言模型部署与优化技术	distillation large language model	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
23	Probing Causality Manipulation of Large Language Models	提出一种分层探测方法，评估大型语言模型对因果关系的操作能力	manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页