cs.CL（2024-09-30）

📊 共 34 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (31 🔗6) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (31 篇)

#题目一句话要点标签🔗⭐
1 DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data DeSTA2：无需语音指令微调数据，开发指令跟随语音语言模型 large language model instruction following chain-of-thought
2 Scheherazade: Evaluating Chain-of-Thought Math Reasoning in LLMs with Chain-of-Problems Scheherazade：利用问题链自动生成数学推理基准，评估LLM的思维链能力。 large language model chain-of-thought ✅
3 Instance-adaptive Zero-shot Chain-of-Thought Prompting 提出实例自适应的零样本思维链提示方法，提升LLM推理能力 large language model chain-of-thought
4 Are Large Language Models In-Context Personalized Summarizers? Get an iCOPERNICUS Test Done! 提出iCOPERNICUS框架，用于评估大型语言模型在上下文个性化摘要中的能力 large language model
5 Zero-Shot Classification of Crisis Tweets Using Instruction-Finetuned Large Language Models 利用指令微调的大语言模型进行危机推文的零样本分类 large language model
6 Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models 提出动态对话基准测试系统，评估LLM在多任务交错场景下的长期记忆和信息整合能力。 large language model
7 1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models 提出1TT平台，用于大型语言模型中高效数据共享和公平收益分配。 large language model
8 Aggressive Post-Training Compression on Extremely Large Language Models 提出一种激进的后训练压缩方法，在保证精度下高效压缩超大语言模型。 large language model
9 Towards Robust Multimodal Sentiment Analysis with Incomplete Data 提出语言主导的抗噪学习网络LNLN，解决多模态情感分析中的数据缺失问题。 multimodal
10 Do Influence Functions Work on Large Language Models? 研究表明影响函数在大型语言模型上的表现不佳，并分析了其原因。 large language model
11 A Methodology for Explainable Large Language Models with Integrated Gradients and Linguistic Analysis in Text Classification 提出SLIME方法，结合IG和语言分析提升LLM在文本分类中的可解释性 large language model
12 Evaluating the performance of state-of-the-art esg domain-specific pre-trained large language models in text classification against existing models and traditional machine learning techniques 利用Qlora微调的领域特定LLM在ESG文本分类中超越传统方法和现有模型 large language model
13 Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender Discourse 大型语言模型在性别歧视内容上的道德立场分析及其社会影响 large language model
14 LexEval: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models 提出LexEval以评估大型语言模型在法律领域的应用 large language model ✅
15 Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models 提出Reference Trustable Decoding，无需微调增强大语言模型下游任务能力。 large language model ✅
16 Using Large Multimodal Models to Extract Knowledge Components for Knowledge Tracing from Multimedia Question Information 利用大型多模态模型从多媒体问题信息中提取知识成分，用于知识追踪 multimodal
17 LLMEmb: Large Language Model Can Be a Good Embedding Generator for Sequential Recommendation LLMEmb：利用大语言模型生成物品嵌入，提升序列推荐系统性能 large language model ✅
18 Neurosymbolic AI approach to Attribution in Large Language Models 提出神经符号AI方法，提升大语言模型归因的可靠性和可解释性 large language model
19 A Looming Replication Crisis in Evaluating Behavior in Language Models? Evidence and Solutions 揭示大语言模型行为评估中潜在的复现危机，并提出解决方案 large language model chain-of-thought
20 HELPD: Mitigating Hallucination of LVLMs by Hierarchical Feedback Learning with Vision-enhanced Penalty Decoding 提出HELPD框架，通过分层反馈学习和视觉增强惩罚解码缓解LVLM中的多模态幻觉问题 multimodal
21 JaPOC: Japanese Post-OCR Correction Benchmark using Vouchers JaPOC：构建日语凭证OCR后校正基准，提升识别准确率 TAMP
22 DoPAMine: Domain-specific Pre-training Adaptation from seed-guided data Mining 提出DoPAMine以解决低资源行业领域的预训练数据不足问题 large language model
23 Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution 提出高斯概念子空间（GCS）方法，提升LLM概念表示的鲁棒性和应用效果 large language model
24 FaithEval: Can Your Language Model Stay Faithful to Context, Even If "The Moon is Made of Marshmallows" FaithEval：评估语言模型在不一致上下文中的忠实度，揭示现有模型在此方面的不足 large language model ✅
25 Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback 提出基于模块化RAG的自动简答题评分与反馈系统，提升评分准确率并提供可解释反馈。 large language model
26 KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head KV-Compress：一种基于分页KV缓存和变压缩率的注意力头压缩方法 large language model
27 Text Clustering as Classification with LLMs 提出一种基于LLM上下文学习的文本聚类框架，无需微调和复杂算法，简化文本聚类流程。 large language model ✅
28 Analysing Zero-Shot Readability-Controlled Sentence Simplification 探索零样本可读性控制的句子简化方法，分析上下文信息的影响。 large language model
29 How Entangled is Factuality and Deception in German? 研究德语中事实性与欺骗性的纠缠关系，揭示现有欺骗检测模型的局限性。 large language model
30 Enhancing High-order Interaction Awareness in LLM-based Recommender Model ELMRec：增强LLM对高阶交互的感知，提升推荐性能 large language model
31 Deep Learning and Machine Learning, Advancing Big Data Analytics and Management: Object-Oriented Programming 探讨面向对象编程在机器学习、深度学习和大数据分析中的应用，提升代码模块化、可维护性和可扩展性。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
32 Unsupervised Human Preference Learning 提出一种无监督人类偏好学习方法，利用小型偏好代理模型指导大型语言模型实现个性化内容生成。 preference learning large language model foundation model
33 Mamba for Streaming ASR Combined with Unimodal Aggregation 提出结合单峰聚合的Mamba流式ASR模型，提升识别精度与效率。 Mamba state space model
34 Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation 提出知识蒸馏、多任务学习和数据增强方法，提升罗马尼亚语攻击性语言检测性能。 distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页