cs.CL（2024-09-05）

📊 共 22 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) (18 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 The representation landscape of few-shot learning and fine-tuning in large language models 通过分析表征概率图景，揭示大语言模型中ICL与SFT的差异化学习机制 large language model
2 Leveraging Large Language Models through Natural Language Processing to provide interpretable Machine Learning predictions of mental deterioration in real time 利用自然语言处理和大型语言模型，为精神衰退提供可解释的实时机器学习预测 large language model
3 How Much Data is Enough Data? Fine-Tuning Large Language Models for In-House Translation: Performance Evaluation Across Multiple Dataset Sizes 通过微调LLaMA 3 8B，利用不同规模的翻译记忆提升企业内部翻译质量 large language model
4 CogniDual Framework: Self-Training Large Language Models within a Dual-System Theoretical Framework for Improving Cognitive Tasks 提出CogniDual框架，通过自训练提升LLM在认知任务中的表现 large language model
5 Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models 提出Debate on Graph (DoG)框架，提升LLM在知识图谱问答中的推理可靠性与灵活性。 large language model ✅
6 Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoption 提出方法以解决大型语言模型中的外群体偏见问题 large language model
7 Attention Heads of Large Language Models: A Survey 综述大型语言模型注意力头的角色与机制，揭示LLM内部推理过程。 large language model
8 Entity Extraction from High-Level Corruption Schemes via Large Language Models 提出基于大语言模型的金融犯罪实体抽取方法与微基准数据集 large language model
9 GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding GraphInsight：提升大语言模型对图结构理解能力，解决图规模增大时的位置偏见问题 large language model
10 MaterialBENCH: Evaluating College-Level Materials Science Problem-Solving Abilities of Large Language Models MaterialBENCH：评估大语言模型在大学材料科学问题解决中的能力 large language model
11 Debiasing Text Safety Classifiers through a Fairness-Aware Ensemble 提出一种公平感知集成方法，用于消除文本安全分类器中的偏见。 large language model
12 LLM Detectors Still Fall Short of Real World: Case of LLM-Generated Short News-Like Posts 揭示LLM检测器在识别LLM生成的新闻短文方面存在不足，并提出动态可扩展的评测基准。 large language model ✅
13 xLAM: A Family of Large Action Models to Empower AI Agent Systems 发布xLAM系列大型动作模型，提升AI Agent系统性能并开源 large language model ✅
14 Sketch: A Toolkit for Streamlining LLM Operations Sketch工具包：简化LLM操作，实现各领域即插即用 large language model ✅
15 Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard 通过长期研究理解LLM发展：来自Open Ko-LLM排行榜的洞见 large language model
16 Sirius: Contextual Sparsity with Correction for Efficient LLMs Sirius：通过上下文稀疏和校正机制提升高效LLM的推理性能 large language model ✅
17 From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents 提出MAIC：利用LLM驱动的多智能体系统重塑在线教学，平衡规模化与自适应性 large language model
18 Shaping the Future of Endangered and Low-Resource Languages -- Our Role in the Age of LLMs: A Keynote at ECIR 2024 探讨LLM时代保护濒危语言的机遇与挑战，以奥克语为例 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🔗⭐
19 Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities 探索微调策略、模型合并与规模效应，提升LLM在材料科学领域的适应性 DPO direct preference optimization large language model
20 Experimentation in Content Moderation using RWKV 利用RWKV模型进行内容审核实验，并提出用于知识蒸馏的新型数据集。 distillation large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
21 Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding Con-ReCall：通过对比解码检测LLM中的预训练数据泄露 manipulation large language model
22 Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers 揭示LLM不同层注意力机制的重要性差异：先关注，后整合 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页