cs.CL（2024-09-06）

📊 共 15 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Self-Harmonized Chain of Thought 提出ECHO，通过自洽化思维链解决大语言模型推理不一致问题 large language model chain-of-thought
2 Can OpenSource beat ChatGPT? -- A Comparative Study of Large Language Models for Text-to-Code Generation 对比研究：ChatGPT等大型语言模型在文本生成代码任务中的性能评估 large language model
3 Learning vs Retrieval: The Role of In-Context Examples in Regression with Large Language Models 提出评估框架，探究大语言模型在回归任务中上下文学习的知识检索与学习机制。 large language model
4 GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding GALLa：图对齐大语言模型，提升源代码理解能力 large language model
5 Multi-Programming Language Ensemble for Code Generation in Large Language Model 提出多编程语言集成方法MPLE，提升大语言模型代码生成精度。 large language model ✅
6 Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning 利用参数高效微调定制大语言模型的生成风格 large language model
7 UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity UI-JEPA：通过屏幕用户活动实现用户意图的主动感知 large language model multimodal
8 How Does Code Pretraining Affect Language Model Task Performance? 研究代码预训练对语言模型任务性能的影响，揭示代码比例与任务表现的关联。 large language model
9 You can remove GPT2's LayerNorm by fine-tuning 通过微调去除GPT2的LayerNorm层，简化模型并保持性能 large language model ✅
10 Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers 通过大规模人工评估，验证LLM在生成新颖研究想法方面超越NLP专家的潜力 large language model
11 Column Vocabulary Association (CVA): semantic interpretation of dataless tables 提出列词汇关联(CVA)方法，用于仅基于元数据的无数据表格语义解释。 large language model
12 AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model AnyMatch：利用小型语言模型实现高效的零样本实体匹配 large language model
13 Sparse Rewards Can Self-Train Dialogue Agents 提出JOSH：利用稀疏奖励自训练对话Agent，提升工具调用能力 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🔗⭐
14 RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs 提出RLPF，利用预测反馈强化学习微调LLM，提升用户摘要在下游任务中的性能。 reinforcement learning large language model
15 Prompt-based Personality Profiling: Reinforcement Learning for Relevance Filtering 提出基于强化学习的提示方法，用于作者画像中相关内容过滤，提升预测准确性。 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页