cs.CL（2024-04-15）

📊 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) (21 🔗1) 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 MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems 提出MMCode以评估多模态大语言模型在代码生成中的表现 large language model multimodal ✅
2 Personalized Collaborative Fine-Tuning for On-Device Large Language Models 提出个性化协作微调方法以解决设备端大语言模型训练问题 large language model
3 KG-CTG: Citation Generation through Knowledge Graph-guided Large Language Models 提出KG-CTG框架以提升引用文本生成的准确性 large language model
4 Are Large Language Models Reliable Argument Quality Annotators? 利用大型语言模型提升论证质量评估的可靠性 large language model
5 Towards Compositionally Generalizable Semantic Parsing in Large Language Models: A Survey 综述大型语言模型的组合泛化语义解析方法 large language model
6 Modelling Language using Large Language Models 提出大型语言模型作为公共语言的科学模型 large language model
7 Large language models and linguistic intentionality 探讨大型语言模型的语言意向性与语义理论 large language model
8 Modeling Emotions and Ethics with Large Language Models 提出情感与伦理整合的长语言模型以提升AI交互能力 large language model
9 INMS: Memory Sharing for Large Language Model based Agents 提出INMS框架以解决大语言模型代理的动态知识共享问题 large language model
10 Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection 提出GlitchHunter以解决大语言模型中的异常令牌问题 large language model
11 Resilience of Large Language Models for Noisy Instructions 研究大型语言模型在噪声指令下的鲁棒性 large language model
12 Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction 提出模型协作方法以提高关系三元组提取的召回率 large language model
13 A Large-Scale Evaluation of Speech Foundation Models 提出SUPERB基准以评估语音基础模型的有效性 foundation model
14 Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation 提出基于LLM的数据清洗方法以提升数据集质量 large language model chain-of-thought
15 Compression Represents Intelligence Linearly 提出压缩与智能线性关联的实证研究 large language model
16 LLM Evaluators Recognize and Favor Their Own Generations 探讨LLM自评偏见及其自我识别能力的影响 large language model
17 TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition 提出TabSQLify以解决大规模表格推理问题 large language model
18 Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems 研究对话上下文对众包评估标签质量的影响 large language model
19 ChatShop: Interactive Information Seeking with Language Agents 提出ChatShop以解决语言代理信息获取不足问题 large language model
20 Software Engineering Methods For AI-Driven Deductive Legal Reasoning 提出软件工程方法以提升AI驱动的法律推理能力 large language model
21 Benchmarking Llama2, Mistral, Gemma and GPT for Factuality, Toxicity, Bias and Propensity for Hallucinations 提出十四个新数据集以评估大语言模型的安全性 large language model

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

#题目一句话要点标签🔗⭐
22 Unveiling Imitation Learning: Exploring the Impact of Data Falsity to Large Language Model 提出FACO数据集以量化合成数据对语言模型的影响 imitation learning large language model
23 On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning 探讨语言模型微调对文本强化学习的影响 reinforcement learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页