cs.CL（2024-05-27）

📊 共 24 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) (17 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 Cost-efficient Knowledge-based Question Answering with Large Language Models 提出Coke策略，在知识库问答中利用LLM和小型模型实现精度和成本的优化。 large language model
2 TEII: Think, Explain, Interact and Iterate with Large Language Models to Solve Cross-lingual Emotion Detection 提出TEII框架，利用大语言模型解决跨语言情感检测问题 large language model
3 Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization 构建对抗性数据集ADT，揭示并利用分词缺陷降低大语言模型性能 large language model
4 Entity Alignment with Noisy Annotations from Large Language Models 提出LLM4EA框架，利用大语言模型解决实体对齐中的噪声标注问题。 large language model ✅
5 XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser XFormParser：一种简单高效的多模态多语言半结构化表单解析器 multimodal ✅
6 How Ready Are Generative Pre-trained Large Language Models for Explaining Bengali Grammatical Errors? 提出多领域数据集以提升孟加拉语语法错误解释工具的有效性 large language model
7 SelfCP: Compressing Over-Limit Prompt via the Frozen Large Language Model Itself SelfCP：利用冻结的大语言模型自身压缩超长Prompt，提升推理效率。 large language model
8 Empowering Large Language Models to Set up a Knowledge Retrieval Indexer via Self-Learning 提出PG-RAG，利用LLM自学习构建知识检索索引，提升RAG性能 large language model ✅
9 Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words? 评估大语言模型在知识密集型问答中自然语言表达内在不确定性的能力 large language model
10 Match, Compare, or Select? An Investigation of Large Language Models for Entity Matching 提出ComEM框架，结合多种策略和LLM，提升实体匹配效果和效率。 large language model
11 MindMerger: Efficient Boosting LLM Reasoning in non-English Languages MindMerger：高效提升LLM在非英语语言中的推理能力 large language model
12 Assessing LLMs Suitability for Knowledge Graph Completion 评估大型语言模型在知识图谱补全任务中的适用性 large language model
13 Generative Query Reformulation Using Ensemble Prompting, Document Fusion, and Relevance Feedback 提出基于集成提示的查询重构方法以提升检索效果 large language model
14 On the Noise Robustness of In-Context Learning for Text Generation 提出局部困惑度排序(LPR)方法，提升文本生成任务中上下文学习对噪声数据的鲁棒性。 large language model ✅
15 UniICL: An Efficient Unified Framework Unifying Compression, Selection, and Generation UniICL：一种高效的统一框架，用于压缩、选择和生成上下文学习示例 large language model
16 Perturbation-Restrained Sequential Model Editing 提出PRUNE框架，通过约束扰动上限提升LLM序贯编辑中的通用能力 large language model ✅
17 AutoPSV: Automated Process-Supervised Verifier 提出AutoPSV，通过自动标注推理步骤提升大语言模型的推理能力。 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
18 EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation EMERGE：利用检索增强生成提升多模态电子病历预测建模 predictive model large language model multimodal ✅
19 The Expressive Capacity of State Space Models: A Formal Language Perspective 形式语言视角下状态空间模型表达能力研究，揭示其与Transformer的优劣势 Mamba SSM state space model
20 BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation 提出BWArea模型，通过模拟人脑机制实现可控语言生成 world model large language model
21 Cross-Modal Safety Alignment: Is textual unlearning all you need? 跨模态安全对齐：文本领域知识遗忘足以应对多模态攻击吗？ reinforcement learning RLHF large language model
22 Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering ALMupQA：通过多视角用户偏好排序反馈对LLM进行对齐，用于编程问答 reinforcement learning RLHF large language model
23 Exploring the LLM Journey from Cognition to Expression with Linear Representations 通过线性表示探索LLM从认知到表达的演进，聚焦Baichuan系列模型 reinforcement learning RLHF large language model
24 Unlocking the Secrets of Linear Complexity Sequence Model from A Unified Perspective 提出线性复杂度序列模型(LCSM)，统一线性注意力、状态空间模型等多种序列建模技术。 state space model linear attention

⬅️ 返回 cs.CL 首页 · 🏠 返回主页