cs.CL（2024-02-18）

📊 共 50 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (41 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (41 篇)

#题目一句话要点标签🔗⭐
1 MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing 提出MIKE基准以解决细粒度多模态实体知识编辑问题 large language model multimodal
2 An Empirical Categorization of Prompting Techniques for Large Language Models: A Practitioner's Guide 提出七类提示技术以简化大语言模型的使用 large language model
3 InfuserKI: Enhancing Large Language Models with Knowledge Graphs via Infuser-Guided Knowledge Integration 提出InfuserKI框架以高效整合未知知识至大语言模型 large language model
4 LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language Models 提出LoRETTA以解决大语言模型微调参数过多问题 large language model
5 GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network 提出GNNavi以解决大语言模型信息流导航问题 large language model
6 A Multi-Aspect Framework for Counter Narrative Evaluation using Large Language Models 提出多维度框架以评估反叙事生成的有效性 large language model
7 Stealthy Attack on Large Language Model based Recommendation 揭示大语言模型推荐系统的隐秘攻击与安全漏洞 large language model
8 Large Language Models Can Better Understand Knowledge Graphs Than We Thought 提出有效提示策略以提升大型语言模型对知识图谱的理解能力 large language model
9 Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning 通过机器遗忘解析预训练数据对大语言模型的影响 large language model
10 Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources 提出FlexLoRA以解决联邦学习中的资源异构问题 large language model
11 Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents 通过整合负例提升大型语言模型的代理能力 large language model
12 Metacognitive Retrieval-Augmented Large Language Models 提出MetaRAG以解决多次检索导致的生成不准确问题 large language model
13 SpeCrawler: Generating OpenAPI Specifications from API Documentation Using Large Language Models 提出SpeCrawler以解决API文档结构差异问题 large language model
14 Decoding News Narratives: A Critical Analysis of Large Language Models in Framing Detection 提出系统评估方法以提升新闻框架检测的可靠性 large language model
15 Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once? 提出多任务推理方法以提升大语言模型的效率与性能 large language model ✅
16 BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models 提出可扩展嵌入方法以高效扩展长上下文语言模型的能力 large language model
17 Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models 提出链式指令调优以解决复杂任务处理问题 large language model
18 From Prejudice to Parity: A New Approach to Debiasing Large Language Model Word Embeddings 提出DeepSoftDebias以解决大语言模型嵌入偏见问题 large language model
19 Benchmarking Knowledge Boundary for Large Language Models: A Different Perspective on Model Evaluation 提出知识边界概念以提升大语言模型评估的可靠性 large language model
20 DictLLM: Harnessing Key-Value Data Structures with Large Language Models for Enhanced Medical Diagnostics 提出DictLLM以解决医疗诊断中键值数据结构建模问题 large language model
21 LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks 提出LoRA-Flow以解决生成任务中LoRA组合的动态权重问题 large language model
22 Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction 提出利用大型语言模型提升中文语法错误纠正性能 large language model
23 Fine-grained and Explainable Factuality Evaluation for Multimodal Summarization 提出FALLACIOUS框架以解决多模态摘要的事实性评估问题 multimodal
24 Can Deception Detection Go Deeper? Dataset, Evaluation, and Benchmark for Deception Reasoning 提出欺骗推理方法以解决欺骗检测的主观性问题 large language model multimodal
25 Autocorrect for Estonian texts: final report from project EKTB25 开发爱沙尼亚语拼写与语法自动纠正工具 large language model
26 PreAct: Prediction Enhances Agent's Planning Ability 提出PreAct框架以提升智能体的规划能力 large language model
27 SciAgent: Tool-augmented Language Models for Scientific Reasoning 提出工具增强的语言模型以解决科学推理问题 large language model
28 Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement 提出自偏见评估方法以改善LLM自我优化效果 large language model ✅
29 Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models 探讨不同支架水平对人机协作写作的影响 large language model
30 Modelling Political Coalition Negotiations Using LLM-based Agents 提出基于大语言模型的代理以模拟政治联盟谈判 large language model
31 One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation 提出SUMMEVAL-OP数据集与LLMs评估方法以解决意见摘要评估问题 large language model
32 Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals 提出机制竞争模型以解析语言模型的事实与反事实处理 large language model ✅
33 Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks 提出针对机器生成文本检测器的鲁棒性压力测试方法 large language model
34 Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs 提出SOLID和SOLID-RL以生成意图感知的信息检索对话 large language model
35 Extensible Embedding: A Flexible Multipler For LLM's Context Length 提出可扩展嵌入以解决大型语言模型上下文长度限制问题 large language model
36 Unveiling the Secrets of Engaging Conversations: Factors that Keep Users Hooked on Role-Playing Dialog Agents 揭示角色扮演对话代理的用户留存因素 large language model
37 What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models 提出SimPlan以解决语言模型规划能力不足的问题 large language model
38 When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation 提出增强LLMs知识边界感知以优化检索增强方法 large language model
39 MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization 提出MatPlotAgent以自动化科学数据可视化任务 large language model
40 Benchmark Self-Evolving: A Multi-Agent Framework for Dynamic LLM Evaluation 提出基于多智能体框架的动态评估方法以提升大语言模型的评估准确性 large language model ✅
41 Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs 提出逻辑支架框架以提升大型语言模型的推理能力 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
42 EventRL: Enhancing Event Extraction with Outcome Supervision for Large Language Models 提出EventRL以解决大语言模型事件提取中的挑战 reinforcement learning large language model instruction following
43 Why Lift so Heavy? Slimming Large Language Models by Cutting Off the Layers 通过减少层数优化大型语言模型以解决存储与性能问题 distillation large language model
44 Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solution 提出基于RLHF的翻译偏好建模以提升翻译质量 reinforcement learning preference learning RLHF
45 Opening the black box of language acquisition 提出一种透明的语言学习架构以解决深度学习模型的不足 reinforcement learning large language model
46 Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM 提出Knowledge-to-SQL框架以解决SQL生成中的知识不足问题 preference learning large language model
47 AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition 提出AutoPRM以解决多步骤推理中的程序监督问题 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
48 How Susceptible are Large Language Models to Ideological Manipulation? 揭示大型语言模型对意识形态操控的脆弱性 manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
49 Integrating Pre-Trained Language Model with Physical Layer Communications 提出集成预训练语言模型与物理层通信的框架以解决通信效率问题 VQ-VAE foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
50 ChatGPT in Linear Algebra: Strides Forward, Steps to Go 探讨ChatGPT在基础线性代数教育中的应用与局限性 affordance

⬅️ 返回 cs.CL 首页 · 🏠 返回主页