cs.CL（2024-10-22）

📊 共 33 篇论文 | 🔗 7 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2)

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

#题目一句话要点标签🔗⭐
1 Captions Speak Louder than Images: Generalizing Foundation Models for E-commerce from High-quality Multimodal Instruction Data 提出MMECInstruct数据集和CASLIE框架，提升电商多模态基础模型泛化能力 foundation model multimodal ✅
2 IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing IPL：利用多模态大语言模型实现智能商品信息生成，提升C2C平台用户体验 large language model multimodal
3 In Context Learning and Reasoning for Symbolic Regression with Large Language Models 利用大型语言模型进行上下文学习和推理，解决符号回归问题 large language model chain-of-thought
4 Optimizing Chain-of-Thought Reasoning: Tackling Arranging Bottleneck via Plan Augmentation 提出基于计划增强的思维链优化方法，解决长距离推理中的编排瓶颈 large language model chain-of-thought
5 JMMMU: A Japanese Massive Multi-discipline Multimodal Understanding Benchmark for Culture-aware Evaluation JMMMU：面向文化感知的日语多模态理解大规模基准评测 multimodal ✅
6 Scalable Influence and Fact Tracing for Large Language Model Pretraining 提出可扩展的影响力与事实追溯方法，用于大规模语言模型预训练。 large language model
7 Automated Spinal MRI Labelling from Reports Using a Large Language Model 提出基于大型语言模型的脊柱MRI报告自动标注流程，用于辅助诊断。 large language model ✅
8 Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy 提出基于语义熵的大语言模型微调方法，提升模型拒绝回答不确定问题的能力 large language model
9 Exploring Possibilities of AI-Powered Legal Assistance in Bangladesh through Large Language Modeling 构建孟加拉国法律AI助手：基于大型语言模型的可能性探索 large language model
10 From Attention to Activation: Unravelling the Enigmas of Large Language Models 针对LLM中Attention集中和激活异常问题，提出Softmax-1和OrthoAdam优化器 large language model
11 Improving Pinterest Search Relevance Using Large Language Models 利用大型语言模型提升Pinterest搜索相关性 large language model
12 Can General-Purpose Large Language Models Generalize to English-Thai Machine Translation ? 研究表明通用大语言模型在低资源英泰翻译中泛化能力不足 large language model
13 Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models 提出自引导优化（SSO），实现大语言模型偏好对齐的自主优化。 large language model
14 Enhancing Answer Attribution for Faithful Text Generation with Large Language Models 提出改进的答案归因方法，提升大型语言模型生成文本的可信度 large language model
15 DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization 提出DIRI方法，利用LLM对抗性评估临床文本匿名化工具的安全性 large language model
16 Exploring Forgetting in Large Language Model Pre-Training 探索大型语言模型预训练阶段的遗忘现象及缓解方法 large language model
17 Analyzing Nobel Prize Literature with Large Language Models 利用大型语言模型分析诺贝尔文学奖作品，对比AI与人类的文学解读能力。 large language model
18 Learning Mathematical Rules with Large Language Models 研究大型语言模型学习和泛化数学规则的能力 large language model
19 ETHIC: Evaluating Large Language Models on Long-Context Tasks with High Information Coverage ETHIC：提出高信息覆盖率的长文本评估基准，揭示LLM在长上下文利用上的不足。 large language model ✅
20 SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine 提出SG-FSM，解决LLM在多跳问答中存在的幻觉和误差传播问题 large language model chain-of-thought
21 Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination 研究架构归纳偏置对LLM幻觉的影响：以蛇形机器人为例 large language model
22 AI-generated Essays: Characteristics and Implications on Automated Scoring and Academic Integrity 评估LLM生成文章的特性，揭示其对自动评分和学术诚信的影响 large language model
23 Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation 提出Meaning Typed Prompting，提升LLM结构化输出的效率和可靠性 large language model
24 AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration 提出AMUSD：一种用于LLM加速的异步多设备推测解码方法 large language model ✅
25 Context-aware Prompt Tuning: Advancing In-Context Learning with Adversarial Methods 提出上下文感知Prompt Tuning，结合ICL与对抗方法提升少样本学习性能 large language model
26 Human-LLM Hybrid Text Answer Aggregation for Crowd Annotations 提出Human-LLM混合文本答案聚合方法，提升众包标注质量 large language model
27 Arabic Dataset for LLM Safeguard Evaluation 构建阿拉伯语LLM安全评估数据集，揭示文化差异下的模型脆弱性 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🔗⭐
28 Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning 提出Trustworthy-Alignment算法，通过强化学习提升检索增强大语言模型的可靠性 reinforcement learning large language model
29 Large Language Models Empowered Personalized Web Agents 提出PUMA框架，赋能大语言模型实现个性化Web代理任务 direct preference optimization large language model
30 Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards 探索基于强化学习的LLM在形式语言任务中的训练与编程奖励 reinforcement learning PPO large language model
31 AdvAgent: Controllable Blackbox Red-teaming on Web Agents AdvAgent：针对Web Agent的可控黑盒对抗性测试框架 reinforcement learning foundation model ✅
32 MiniPLM: Knowledge Distillation for Pre-Training Language Models 提出MiniPLM，通过知识蒸馏提升预训练语言模型效率、灵活性和效果。 distillation ✅
33 Science Out of Its Ivory Tower: Improving Accessibility with Reinforcement Learning 提出基于强化学习的科学论文摘要改写框架，提升学术内容可访问性 reinforcement learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页