cs.CL（2024-10-12）

📊 共 23 篇论文 | 🔗 8 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (22 🔗7) 支柱二：RL算法与架构 (RL & Architecture) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Toward General Instruction-Following Alignment for Retrieval-Augmented Generation 提出VIF-RAG，用于提升检索增强生成系统中指令遵循对齐能力 large language model instruction following
2 The Future of Learning in the Age of Generative AI: Automated Question Generation and Assessment with Large Language Models 探索生成式AI在教育领域的应用：基于大语言模型的自动问题生成与评估 large language model chain-of-thought
3 FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models FedEx-LoRA：通过精确聚合实现联邦学习中高效的基础模型微调 foundation model ✅
4 Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models 提出Ski方法，通过合成知识注入提升大语言模型的知识掌握能力 large language model
5 LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning 提出LINKED方法，通过知识过滤与一致性推理提升大语言模型常识推理能力 large language model
6 Enhanced Electronic Health Records Text Summarization Using Large Language Models 利用大型语言模型Flan-T5，增强电子病历文本的聚焦式摘要生成，提升临床效率。 large language model
7 Beyond Exact Match: Semantically Reassessing Event Extraction by Large Language Models 提出RAEE框架，利用大语言模型进行事件抽取的语义级重评估，解决传统精确匹配评估的局限性。 large language model
8 LLM$\times$MapReduce: Simplified Long-Sequence Processing using Large Language Models 提出LLM×MapReduce框架，通过分治策略简化长文本处理，提升长文本理解能力。 large language model
9 Are You Human? An Adversarial Benchmark to Expose LLMs 提出对抗性基准测试，用于实时检测大型语言模型（LLM）是否伪装成人类。 large language model instruction following
10 FlatQuant: Flatness Matters for LLM Quantization FlatQuant：通过优化权重分布，显著提升LLM量化性能。 large language model ✅
11 CAMPHOR: Collaborative Agents for Multi-input Planning and High-Order Reasoning On Device CAMPHOR：用于多输入规划和高阶推理的设备端协作智能体框架 large language model
12 Transformer-based Language Models for Reasoning in the Description Logic ALCQ 提出基于Transformer的语言模型以提升描述逻辑ALCQ推理能力 large language model
13 Extended Japanese Commonsense Morality Dataset with Masked Token and Label Enhancement 提出MTLE方法扩展日文常识道德数据集，提升AI道德推理能力 large language model
14 MIRAGE: Evaluating and Explaining Inductive Reasoning Process in Language Models 提出MIRAGE数据集，用于评估和解释语言模型中的归纳推理过程。 large language model
15 FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs' Responsiveness to Human Feedback 提出FB-Bench，用于评估LLM在中文多轮对话中对人类反馈的响应能力 large language model ✅
16 Rethinking Data Selection at Scale: Random Selection is Almost All You Need 大规模SFT数据选择：随机选择性能接近最优，数据多样性至关重要 large language model
17 COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement 提出COrAL：一种高效的、与顺序无关的语言模型，用于迭代优化大型语言模型。 large language model ✅
18 CollabEdit: Towards Non-destructive Collaborative Knowledge Editing 提出COLLABEDIT框架，解决大型语言模型非破坏性协同知识编辑问题 large language model ✅
19 AERA Chat: An Interactive Platform for Automated Explainable Student Answer Assessment AERA Chat：用于自动可解释学生答案评估的交互式平台 large language model
20 Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning Tasks 提出基于参数高效微调的Q-Former视觉推理方法，显著降低训练成本。 large language model ✅
21 ELICIT: LLM Augmentation via External In-Context Capability ELICIT：通过外部上下文能力增强LLM，无需额外训练或token。 large language model ✅
22 Impeding LLM-assisted Cheating in Introductory Programming Assignments via Adversarial Perturbation 通过对抗扰动降低LLM在入门编程作业中的作弊行为 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
23 Keys to Robust Edits: from Theoretical Insights to Practical Advances 提出鲁棒编辑路径REP，提升大语言模型知识编辑的鲁棒性和准确性 contrastive learning large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页