cs.CL(2024-02-16)

📊 共 60 篇论文 | 🔗 11 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (48 🔗7) 支柱二:RL算法与架构 (RL & Architecture) (11 🔗3) 支柱六:视频提取与匹配 (Video Extraction) (1 🔗1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (48 篇)

#题目一句话要点标签🔗
1 Can Separators Improve Chain-of-Thought Prompting? 提出COT-SEP以改善链式思维提示的推理能力 large language model chain-of-thought
2 Chain of Logic: Rule-Based Reasoning with Large Language Models 提出Chain of Logic方法以解决复杂规则推理问题 large language model chain-of-thought
3 Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models 提出全面评估序列记忆编辑以解决大语言模型的知识更新问题 large language model
4 Large Language Models for Causal Discovery: Current Landscape and Future Directions 探讨大语言模型在因果发现中的应用与未来方向 large language model
5 Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement 提出Persona-DB以解决大语言模型个性化响应预测问题 large language model
6 Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives 提出Conan基准以解决侦探叙事中的复杂关系理解问题 large language model
7 Inference to the Best Explanation in Large Language Models 提出IBE-Eval框架以提升大语言模型解释的评估能力 large language model
8 ToolSword: Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages 提出ToolSword框架以揭示工具学习中LLMs的安全问题 large language model
9 GenRES: Rethinking Evaluation for Generative Relation Extraction in the Era of Large Language Models 提出GenRES以解决生成关系抽取评估不足问题 large language model
10 Large Language Models as Zero-shot Dialogue State Tracker through Function Calling 提出FnCTOD以解决任务导向对话状态跟踪问题 large language model
11 BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering 提出BlendFilter以解决知识检索噪声问题 large language model
12 EcoRank: Budget-Constrained Text Re-ranking Using Large Language Models 提出EcoRank以在预算约束下优化文本重排序 large language model
13 Towards Uncovering How Large Language Model Works: An Explainability Perspective 通过可解释性视角揭示大型语言模型的内部机制 large language model
14 German Text Simplification: Finetuning Large Language Models with Semi-Synthetic Data 利用半合成数据微调大型语言模型以解决德语文本简化问题 large language model
15 LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty 提出LinkNER框架以解决NER模型在新实体识别中的不足 large language model
16 Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models 提出对话式SimulMT框架以提高大语言模型的翻译效率 large language model
17 Assessing biomedical knowledge robustness in large language models by query-efficient sampling attacks 提出一种新方法评估大语言模型生物医学知识的鲁棒性 large language model
18 Steering Conversational Large Language Models for Long Emotional Support Conversations 提出策略相关注意力机制以增强对话模型的情感支持能力 large language model
19 I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Models 探讨大型语言模型中的文化偏见及其影响 large language model
20 Can We Verify Step by Step for Incorrect Answer Detection? 提出R2PE基准以解决LLM推理链准确性预测问题 large language model chain-of-thought
21 PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering 提出PAT-Questions基准以解决当前时间锚定的时间问答问题 large language model TAMP
22 Instruction Diversity Drives Generalization To Unseen Tasks 提出指令多样性以提升模型对未见任务的泛化能力 large language model
23 When is Tree Search Useful for LLM Planning? It Depends on the Discriminator 探讨判别器对大语言模型规划中树搜索的影响 large language model
24 Properties and Challenges of LLM-Generated Explanations 探讨大语言模型生成解释的特性与挑战 large language model
25 AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators 提出AFaCTA以解决事实声明检测中的标注成本和一致性问题 large language model
26 A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive 提出响应采样理论以优化大型语言模型决策过程 large language model
27 How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs? 提出自动评估方法以提升指令调优LLM的可靠性 large language model
28 An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference 提出跨语言词汇适应方法以提升语言模型推理效率 large language model
29 LongHeads: Multi-Head Attention is Secretly a Long Context Processor 提出LongHeads以解决长文本处理效率低的问题 large language model
30 When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers 提出ACE和LACE方法以解决LLM的安全漏洞问题 large language model
31 Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs 提出层次解析树与递归超图以识别机器生成文本 large language model
32 InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain? 提出$β$加权法律安全评分以解决印度法律领域的公平性与准确性问题 large language model
33 Where is the answer? Investigating Positional Bias in Language Model Knowledge Extraction 提出解决LLM知识提取中的位置偏差问题的方法 large language model
34 WilKE: Wise-Layer Knowledge Editor for Lifelong Knowledge Editing 提出Wise-Layer知识编辑器以解决长期知识编辑问题 large language model
35 Revisiting Word Embeddings in the LLM Era 系统比较LLM与传统词嵌入模型的性能差异 large language model
36 Dense Passage Retrieval: Is it Retrieving? 提出DPR机制分析以优化检索增强生成模型性能 large language model
37 Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities 探讨LLMs在时间序列预测中的应用与优化 large language model
38 Quantifying the Persona Effect in LLM Simulations 研究个性化变量对大型语言模型模拟效果的影响 large language model
39 Cultural Commonsense Knowledge for Intercultural Dialogues 提出MANGO方法以解决跨文化对话中的文化常识知识问题 large language model
40 Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm 提出工作流范式以解决LLM在文本到SQL中的注意力扩散问题 chain-of-thought
41 Humans or LLMs as the Judge? A Study on Judgement Biases 提出无需参考真实标注的框架以研究评判偏差 large language model
42 Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL 提出无人工干预融合方法以提升文本到SQL的演示多样性 large language model
43 Enhancing Numerical Reasoning with the Guidance of Reliable Reasoning Processes 提出Encore以解决不可靠推理过程的问题 large language model
44 AbsInstruct: Eliciting Abstraction Ability from LLMs through Explanation Tuning with Plausibility Estimation 提出AbsInstruct框架以提升LLMs的抽象能力 instruction following
45 Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement 提出MORTISE以解决角色扮演系统中的查询对齐问题 large language model
46 Rowen: Adaptive Retrieval-Augmented Generation for Hallucination Mitigation in LLMs 提出Rowen框架以缓解大语言模型中的幻觉问题 large language model
47 SPAR: Personalized Content-Based Recommendation via Long Engagement Attention 提出SPAR框架以解决个性化内容推荐中的长历史处理问题 large language model
48 DELL: Generating Reactions and Explanations for LLM-Based Misinformation Detection 提出DELL以解决大语言模型在虚假信息检测中的局限性 large language model

🔬 支柱二:RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗
49 DataDreamer: A Tool for Synthetic Data Generation and Reproducible LLM Workflows 提出DataDreamer以解决LLM工作流的可重复性问题 dreamer distillation large language model
50 FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models 提出FinTral以提升金融领域的多模态分析能力 DPO direct preference optimization large language model
51 OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models 提出OpenFMNav以解决开放集零-shot物体导航问题 reinforcement learning large language model foundation model
52 Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning 提出基于图表示学习的分类方法以优化LLM调查论文归类 representation learning large language model
53 Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models 提出多模态偏好对齐以解决视觉指令调优退化问题 RLHF DPO direct preference optimization
54 "Understanding AI": Semantic Grounding in Large Language Models 提出语义基础理论以评估大型语言模型的理解能力 world model world models large language model
55 Direct Preference Optimization with an Offset 提出带偏移的直接偏好优化方法以提升语言模型对人类偏好的对齐 reinforcement learning DPO direct preference optimization
56 A Condensed Transition Graph Framework for Zero-shot Link Prediction with Large Language Models 提出凝聚转移图框架以解决零样本链接预测问题 contrastive learning large language model
57 Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning 提出逐步学习方法以提升上下文学习能力 curriculum learning large language model
58 BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation 提出BitDistiller以提升超低精度LLM的性能 distillation large language model
59 Distillation Enhanced Generative Retrieval 提出DGR框架以增强生成检索性能 distillation

🔬 支柱六:视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗
60 When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models 提出FaLlacy理解基准以挑战大型语言模型的推理能力 HuMoR large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页