cs.CL（2023-10-23）

📊 共 48 篇论文 | 🔗 10 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (42 🔗9) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (42 篇)

#题目一句话要点标签🔗⭐
1 CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks 提出CoF-CoT以提升大语言模型在多领域NLU任务中的表现 large language model chain-of-thought
2 Unleashing the potential of prompt engineering for large language models 探讨提示工程在大语言模型中的应用潜力 large language model multimodal chain-of-thought
3 AlpaCare:Instruction-tuned Large Language Models for Medical Application 提出AlpaCare以解决医疗领域LLM指令跟随能力不足问题 large language model instruction following ✅
4 Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic 分析大型语言模型在阿拉伯语多轮指令跟随中的能力 large language model instruction following
5 The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models 提出BLA基准以评估多模态模型的基本语言能力 multimodal
6 Health Disparities through Generative AI Models: A Comparison Study Using A Domain Specific large language model 比较领域特定大语言模型以解决健康差异问题 large language model
7 Function Vectors in Large Language Models 提出函数向量机制以增强大语言模型的任务执行能力 large language model
8 Branch-Solve-Merge Improves Large Language Model Evaluation and Generation 提出Branch-Solve-Merge以提升大型语言模型的评估与生成能力 large language model
9 Did the Neurons Read your Book? Document-level Membership Inference for Large Language Models 提出文档级成员推断方法以提高LLM透明度 large language model
10 Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications 探讨大型语言模型在表格分类中的公平性问题 large language model
11 Contextual Refinement of Translations: Large Language Models for Sentence and Document-Level Post-Editing 提出基于大语言模型的自动后编辑方法以提升翻译质量 large language model ✅
12 Cross-lingual Prompting: Improving Zero-shot Chain-of-Thought Reasoning across Languages 提出跨语言提示方法以提升零-shot推理能力 chain-of-thought
13 Generating Prototypes for Contradiction Detection Using Large Language Models and Linguistic Rules 提出一种新方法以生成矛盾检测原型数据 large language model
14 Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses 利用大型语言模型生成编程课程代码追踪问题 large language model
15 S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models 提出S3Eval以解决大语言模型评估的挑战 large language model
16 Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model 对ChatGPT的形态学能力进行多语言分析以揭示其局限性 large language model
17 LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis 提出LLM-in-the-loop框架以优化主题分析过程 large language model
18 Unveiling A Core Linguistic Region in Large Language Models 揭示大型语言模型中的核心语言区域以理解智能机制 large language model
19 ALCUNA: Large Language Models Meet New Knowledge 提出KnowGen和ALCUNA以评估LLMs处理新知识的能力 large language model
20 DISC-FinLLM: A Chinese Financial Large Language Model based on Multiple Experts Fine-tuning 提出DISC-FinLLM以解决金融领域多任务处理问题 large language model ✅
21 Establishing Vocabulary Tests as a Benchmark for Evaluating Large Language Models 提出词汇测试作为评估大型语言模型的新基准 large language model
22 Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models 提出树状澄清框架以解决模糊问题 large language model ✅
23 Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue 提出CRS与LLM结合的方法以优化电商预售对话推荐 large language model
24 Evaluating Large Language Models on Controlled Generation Tasks 评估大型语言模型在可控生成任务中的表现 large language model
25 DetectGPT-SC: Improving Detection of Text Generated by Large Language Models through Self-Consistency with Masked Predictions 提出DetectGPT-SC以解决AI文本检测问题 large language model
26 LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers 提出LINC以解决逻辑推理中的语言模型局限性问题 large language model chain-of-thought ✅
27 Towards LLM-driven Dialogue State Tracking 提出LDST框架以提升对话状态跟踪的性能 large language model foundation model
28 Assessing Step-by-Step Reasoning against Lexical Negation: A Case Study on Syllogism 评估大语言模型在词汇否定下的逐步推理能力 large language model chain-of-thought
29 Plan, Verify and Switch: Integrated Reasoning with Diverse X-of-Thoughts 提出XoT框架以解决数学推理任务中的多样性问题 large language model chain-of-thought ✅
30 Exploring the Boundaries of GPT-4 in Radiology 评估GPT-4在放射学报告中的应用性能 large language model foundation model
31 Meaning Representations from Trajectories in Autoregressive Models 提出基于轨迹的语义表示方法以提升语言模型性能 multimodal ✅
32 Geographical Erasure in Language Generation 提出地理消除方法以解决语言生成中的偏见问题 large language model
33 Why LLMs Hallucinate, and How to Get (Evidential) Closure: Perceptual, Intensional, and Extensional Learning for Faithful Natural Language Generation 提出证据闭合机制以解决大型语言模型幻觉问题 multimodal
34 TaskDiff: A Similarity Metric for Task-Oriented Conversations 提出TaskDiff以解决任务导向对话相似性评估问题 large language model
35 DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM 提出DeTiME以解决现有主题建模与文本生成的不足问题 large language model
36 Reasoning about Ambiguous Definite Descriptions 提出模糊确定性描述以解决语言模型的歧义问题 large language model ✅
37 InstructExcel: A Benchmark for Natural Language Instruction in Excel 提出InstructExcel基准以解决自然语言指令在Excel中的应用问题 large language model
38 GPT-4 as an Effective Zero-Shot Evaluator for Scientific Figure Captions 利用GPT-4作为有效的零-shot评估器评估科学图形标题 large language model
39 Specialist or Generalist? Instruction Tuning for Specific NLP Tasks 提出通用指令调优以提升特定NLP任务模型性能 large language model ✅
40 Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer? 构建法律场景语料库以评估ChatGPT的IRAC推理能力 large language model
41 Language Models Hallucinate, but May Excel at Fact Verification 提出语言模型作为有效事实验证工具以解决虚假信息问题 large language model
42 NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation 提出NormDial数据集以研究社会规范遵循与违反 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🔗⭐
43 MCC-KD: Multi-CoT Consistent Knowledge Distillation 提出MCC-KD以解决知识蒸馏中的一致性与多样性问题 distillation large language model chain-of-thought
44 M2DF: Multi-grained Multi-curriculum Denoising Framework for Multimodal Aspect-based Sentiment Analysis 提出M2DF框架以解决多模态情感分析中的噪声图像问题 curriculum learning multimodal
45 PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter 提出PRCA以解决黑箱大语言模型在检索问答中的适应性问题 reinforcement learning large language model
46 GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs 提出GRENADE以解决文本属性图的自监督表示学习问题 representation learning contrastive learning ✅
47 Irreducible Curriculum for Language Model Pretraining 提出不可约课程以优化语言模型预训练 curriculum learning large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
48 Evaluating Spatial Understanding of Large Language Models 评估大型语言模型的空间理解能力 spatial relationship large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页