cs.CL（2024-04-03）

📊 共 34 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) (27 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱四：生成式动作 (Generative Motion) (1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models 提出Conifer以解决大型语言模型复杂指令遵循能力不足问题 large language model instruction following
2 BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memes 提出多模态方法以识别表情包中的劝说技巧 multimodal
3 Automatic Prompt Selection for Large Language Models 提出自动提示选择方法以优化大语言模型的输入处理 large language model
4 Measuring Social Norms of Large Language Models 提出新的数据集以评估大型语言模型的社会规范理解能力 large language model
5 PhonologyBench: Evaluating Phonological Skills of Large Language Models 提出PhonologyBench以评估大型语言模型的音韵能力 large language model
6 Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models 提出Min-K%++以解决大语言模型预训练数据检测问题 large language model
7 GreedLlama: Performance of Financial Value-Aligned Large Language Models in Moral Reasoning 提出GreedLlama以解决金融价值对道德推理的影响问题 large language model
8 Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT 评估大型语言模型在波斯语中的应用潜力 large language model
9 Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model 构建材料知识图谱以解决材料科学领域信息整合问题 large language model
10 An Incomplete Loop: Instruction Inference, Instruction Following, and In-context Learning in Language Models 探讨语言模型中的指令推理与学习机制 instruction following
11 Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models 提出CherryQ以解决大语言模型参数异质性与量化问题 large language model
12 Towards Large Language Model driven Reference-less Translation Evaluation for English and Indian Languages 提出基于大语言模型的无参考翻译评估方法以解决翻译质量评估问题 large language model
13 Revisiting subword tokenization: A case study on affixal negation in large language models 研究词缀否定对大型语言模型的影响及其分词方法 large language model
14 uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers? 通过提示工程提升LLM的侧向思维能力 chain-of-thought
15 Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data 提出低资源LLM分类的新策略以提升效率与准确性 large language model
16 KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking 提出KnowHalu以解决大型语言模型生成文本中的幻觉检测问题 large language model
17 MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise 提出MIMIR以解决个性化智能体调优问题 large language model
18 Similar Data Points Identification with LLM: A Human-in-the-loop Strategy Using Summarization and Hidden State Insights 提出一种基于LLM的相似数据点识别方法以解决数据分析问题 large language model
19 On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL 研究线性化方法以处理结构化数据在编码-解码语言模型中的应用 large language model
20 Auditing the Use of Language Models to Guide Hiring Decisions 提出对应实验方法以审计语言模型在招聘中的应用 large language model
21 MuLan: A Study of Fact Mutability in Language Models 提出MuLan基准以评估语言模型对事实可变性的理解能力 large language model
22 Towards a Fully Interpretable and More Scalable RSA Model for Metaphor Understanding 提出一种可解释且可扩展的RSA模型以解决隐喻理解问题 large language model
23 FPT: Feature Prompt Tuning for Few-shot Readability Assessment 提出特征提示调优方法解决少样本可读性评估问题 large language model
24 Scalable Model Editing via Customized Expert Networks 提出可扩展模型编辑方法以解决大语言模型知识更新问题 large language model ✅
25 Improving Topic Relevance Model by Mix-structured Summarization and LLM-based Data Augmentation 通过混合结构摘要和LLM数据增强提升主题相关性模型 large language model
26 Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Models 提出Think-and-Execute框架以提升语言模型的算法推理能力 large language model
27 CSEPrompts: A Benchmark of Introductory Computer Science Prompts 提出CSEPrompts以评估计算机科学教育中的LLM影响 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
28 Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models 提出自适应Kullback-Leibler散度以优化大语言模型蒸馏 distillation large language model ✅
29 ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline 提出自我批评管道以提升大语言模型的数学问题解决能力 direct preference optimization large language model ✅
30 Calibrating the Confidence of Large Language Models by Eliciting Fidelity 提出一种方法以校准大型语言模型的置信度 RLHF large language model
31 Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages 提出利用大语言模型扩展口语理解系统至新语言的方案 contrastive learning large language model
32 Cross-Architecture Transfer Learning for Linear-Cost Inference Transformers 提出跨架构迁移学习以降低Transformer推理成本 SSM linear attention

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
33 Personality-affected Emotion Generation in Dialog Systems 提出个性化情感生成方法以解决对话系统情感一致性问题 motion generation

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
34 Language, Environment, and Robotic Navigation 提出语言与环境结合的机器人导航框架以提升导航能力 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页