cs.CL（2024-08-07）

📊 共 23 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) (21 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks 提出基于问题复述的LLM不确定性量化方法，应用于分子化学任务 large language model
2 Improving Large Language Model (LLM) fidelity through context-aware grounding: A systematic approach to reliability and veracity 提出上下文感知 grounding 框架，提升大型语言模型可靠性与伦理对齐 large language model
3 Large Language Models for Biomedical Text Simplification: Promising But Not There Yet 利用大型语言模型进行生物医学文本简化研究：有前景但仍需努力 large language model
4 WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models WalledEval：为大型语言模型提供全面的安全评估工具包 large language model ✅
5 StructuredRAG: JSON Response Formatting with Large Language Models StructuredRAG：提出用于评估LLM生成JSON结构化输出能力的基准测试 large language model
6 Human Speech Perception in Noise: Can Large Language Models Paraphrase to Improve It? 提出Prompt-and-Select方法，利用大语言模型生成更易于噪声环境下理解的语音释义。 large language model
7 EgyBERT: A Large Language Model Pretrained on Egyptian Dialect Corpora 提出EgyBERT以解决埃及方言处理问题 large language model ✅
8 SLIM-RAFT: A Novel Fine-Tuning Approach to Improve Cross-Linguistic Performance for Mercosur Common Nomenclature 提出SLIM-RAFT，提升LLM在Mercosur通用命名规范跨语言任务中的性能 large language model chain-of-thought
9 EXAONE 3.0 7.8B Instruction Tuned Language Model LG AI Research发布EXAONE 3.0 7.8B指令调优语言模型 large language model instruction following ✅
10 Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation Optimus通过挖掘LLM训练中的GPU气泡，加速大规模多模态LLM训练。 large language model multimodal
11 Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond 提出 Speech-MASSIVE，一个用于多语言语音理解及其他任务的大规模语音数据集。 foundation model multimodal ✅
12 Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection 提出基于视觉提示注入的目标劫持攻击方法，揭示大型视觉语言模型的安全风险 instruction following
13 ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses ConfReady：一个基于RAG的助手和数据集，用于生成会议论文检查清单回复 large language model
14 Identifying and Mitigating Social Bias Knowledge in Language Models 提出 Fairness Stamp (FAST) 方法，用于识别和缓解语言模型中的社会偏见知识。 large language model
15 Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models 提出基于对抗提示和LLM评判的自动化方法，用于检测语言模型中的性别偏见。 large language model
16 Prompt and Prejudice 通过在伦理决策任务中添加姓名，揭示LLM/VLM中的人口偏见 large language model
17 NatLan: Native Language Prompting Facilitates Knowledge Elicitation Through Language Trigger Provision and Domain Trigger Retention 提出NatLan，通过母语提示增强多语言大模型在非优势语言上的知识获取能力。 large language model ✅
18 Forecasting Live Chat Intent from Browsing History 提出一种两阶段方法，通过浏览历史预测在线客服的用户意图。 large language model
19 NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time NACL：一种通用高效的LLM推理时KV缓存淘汰框架 large language model ✅
20 PAGED: A Benchmark for Procedural Graphs Extraction from Documents 提出PAGED基准，用于评估和提升文档中程序图的自动抽取能力 large language model
21 1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data 1.5-Pints：通过高质量数据，在数天内完成语言模型预训练，性能超越现有模型。 instruction following

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
22 A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use Case 针对旅游聊天机器人，对比LLM微调方法与评估指标，并提出RLHF优化方案 reinforcement learning RLHF large language model
23 A Logical Fallacy-Informed Framework for Argument Generation 提出FIPO框架，通过偏好优化和谬误分类损失提升LLM论证的逻辑合理性 DPO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页