cs.CL（2023-12-12）

📊 共 18 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales 提出基于提示生成推理的临床诊断框架，提升LLM在临床推理中的诊断能力 large language model chain-of-thought
2 Large language models in healthcare and medical domain: A review 综述医疗领域大语言模型：发展、应用、挑战与未来 large language model
3 LLM in a flash: Efficient Large Language Model Inference with Limited Memory LLM in a flash：利用闪存高效推理受限内存的大语言模型 large language model
4 Classifying complex documents: comparing bespoke solutions to large language models 对比定制模型与大语言模型在复杂法律文档分类中的性能 large language model
5 Multilingual large language models leak human stereotypes across language boundaries 揭示多语言大模型中跨语言边界的刻板印象泄露现象 large language model
6 Context Matters: Data-Efficient Augmentation of Large Language Models for Scientific Applications 针对科学应用，论文提出数据高效的LLM增强方法，提升模型可靠性。 large language model
7 SM70: A Large Language Model for Medical Devices SpassMed公司发布SM70：一款面向医疗设备的700亿参数大语言模型，提升医疗问答准确性和安全性。 large language model
8 Comparable Demonstrations are Important in In-Context Learning: A Novel Perspective on Demonstration Selection 提出可比示例(CDs)以缓解ICL中的示例偏差，提升模型泛化能力 large language model
9 SCCA: Shifted Cross Chunk Attention for long contextual semantic expansion 提出Shifted Cross Chunk Attention，扩展LLM长文本上下文能力 large language model
10 LLMs Perform Poorly at Concept Extraction in Cyber-security Research Literature LLM在网络安全文献概念抽取中表现不佳，提出统计增强的名词抽取器。 large language model
11 DiffuVST: Narrating Fictional Scenes with Global-History-Guided Denoising Models DiffuVST：利用全局历史引导的去噪模型生成虚构场景叙事 multimodal
12 Improving Factual Error Correction by Learning to Inject Factual Errors 提出LIFE框架，通过学习注入错误来提升事实错误纠正效果 large language model
13 Alignment for Honesty 提出一种对齐大型语言模型诚实性的框架，使其在知识不足时拒绝回答问题。 large language model ✅
14 ComplexityNet: Increasing LLM Inference Efficiency by Learning Task Complexity ComplexityNet：通过学习任务复杂度提升LLM推理效率 large language model
15 Rethinking the Instruction Quality: LIFT is What You Need 提出LIFT：通过指令融合迁移提升大语言模型指令数据质量 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
16 Dynamic Corrective Self-Distillation for Better Fine-Tuning of Pretrained Models 提出动态修正自蒸馏方法，提升预训练模型在有限数据下的微调性能 distillation
17 Toward a Reinforcement-Learning-Based System for Adjusting Medication to Minimize Speech Disfluency 提出基于强化学习的药物调整系统，以最小化精神健康相关的言语障碍。 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 Can LLM find the green circle? Investigation and Human-guided tool manipulation for compositional generalization 提出人机协作工具操控框架，提升LLM在组合泛化任务中的性能 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页