cs.CL（2023-10-24）

📊 共 36 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (26 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning 提出MuSR以评估语言模型在多步软推理中的能力 large language model chain-of-thought
2 Multimodal Representations for Teacher-Guided Compositional Visual Reasoning 提出基于教师引导的多模态表示以提升视觉推理能力 multimodal
3 SoK: Memorization in General-Purpose Large Language Models 提出记忆分类法以解决大规模语言模型中的信息记忆问题 large language model
4 LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery 提出LoRAShear以解决大语言模型的高计算成本问题 large language model ✅
5 Knowledge Editing for Large Language Models: A Survey 提出知识编辑方法以高效更新大型语言模型 large language model
6 MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications 提出MindLLM以解决轻量化大语言模型训练与应用问题 large language model
7 A Communication Theory Perspective on Prompting Engineering Methods for Large Language Models 提出基于通信理论的提示工程方法以优化大型语言模型 large language model
8 GenKIE: Robust Generative Multimodal Document Key Information Extraction 提出GenKIE以解决文档关键信息提取中的OCR错误问题 multimodal
9 This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models 提出大型否定基准以挑战大语言模型的否定理解能力 large language model
10 BLESS: Benchmarking Large Language Models on Sentence Simplification 提出BLESS基准以评估大语言模型在句子简化任务中的表现 large language model
11 Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation 提出Tuning-free Rule Accumulation框架以提升大语言模型性能 large language model
12 Prevalence and prevention of large language model use in crowd work 研究LLM在众包工作中的使用及其预防策略 large language model
13 CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation 提出CoAnnotating以解决人类与大语言模型协同标注问题 large language model ✅
14 TCRA-LLM: Token Compression Retrieval Augmented Large Language Model for Inference Cost Reduction 提出TCRA-LLM以解决检索增强大语言模型推理成本问题 large language model
15 CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model 提出CRaSh以提升大语言模型的微调效果 large language model ✅
16 Leveraging Large Language Models for Enhanced Product Descriptions in eCommerce 利用LLAMA 2.0模型自动生成电商产品描述以提升用户参与度 large language model
17 Instruct and Extract: Instruction Tuning for On-Demand Information Extraction 提出按需信息提取方法以解决长尾用户需求问题 large language model instruction following ✅
18 FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactions 提出FANToM基准以测试机器的心智理论能力 large language model chain-of-thought
19 Locally Differentially Private Document Generation Using Zero Shot Prompting 提出DP-Prompt机制以解决大语言模型隐私保护问题 large language model
20 A Survey on Detection of LLMs-Generated Content 综述LLMs生成内容检测方法以应对合成内容挑战 large language model ✅
21 In-Context Learning Creates Task Vectors 提出任务向量以增强上下文学习的理解 large language model
22 Self-Guard: Empower the LLM to Safeguard Itself 提出Self-Guard以增强大型语言模型的自我保护能力 large language model
23 Generative Language Models Exhibit Social Identity Biases 研究揭示大型语言模型的社会身份偏见问题 large language model
24 POE: Process of Elimination for Multiple Choice Reasoning 提出POE方法以提升多选推理任务的准确性 large language model
25 Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation 提出F3策略以应对大语言模型生成的虚假信息问题 large language model ✅
26 Interpreting Answers to Yes-No Questions in User-Generated Content 提出新语料库以解决社交媒体中是非问题的理解难题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
27 A Contextualized Real-Time Multimodal Emotion Recognition for Conversational Agents using Graph Convolutional Networks in Reinforcement Learning 提出基于图卷积网络的实时多模态情感识别方法以提升对话代理的情感理解能力 reinforcement learning large language model multimodal
28 WebWISE: Web Interface Control and Sequential Exploration with Large Language Models 提出WebWISE以解决Web软件任务自动化问题 reinforcement learning imitation learning large language model
29 Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression 提出基于检索的知识转移以解决极端大语言模型压缩问题 reinforcement learning PPO large language model
30 What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations 提出可驳斥道德推理以解决道德判断的模糊性问题 imitation learning distillation
31 Career Path Prediction using Resume Representation Learning and Skill-based Matching 提出CareerBERT以解决职业路径预测问题 representation learning
32 SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation 提出SteloCoder以解决多语言代码翻译问题 curriculum learning large language model ✅
33 Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words 提出对比学习的句子编码器以加权信息词汇 contrastive learning
34 Re-Temp: Relation-Aware Temporal Representation Learning for Temporal Knowledge Graph Completion 提出Re-Temp以解决时序知识图谱补全中的信息忽略问题 representation learning
35 Length is a Curse and a Blessing for Document-level Semantics 提出LA(SER)³框架以解决文档长度引发的语义偏移问题 representation learning contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
36 Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers 提出自动操控机器阅读理解快捷触发器的方法以提升LLM可靠性 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页