cs.CL（2024-11-22）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains 提出乌克兰语多模态基准测试ZNO-Vision，评估模型在学术和文化领域的理解能力。 multimodal
2 De-biased Multimodal Electrocardiogram Analysis 提出一种去偏置的多模态心电图分析方法，提升模型在对抗测试和零样本学习中的性能。 large language model multimodal
3 PPLqa: An Unsupervised Information-Theoretic Quality Metric for Comparing Generative Large Language Models 提出PPLqa：一种无监督信息论指标，用于评估生成式大语言模型回复质量。 large language model
4 XGrammar: Flexible and Efficient Structured Generation Engine for Large Language Models XGrammar：为大语言模型提供灵活高效的结构化生成引擎 large language model
5 Sycophancy in Large Language Models: Causes and Mitigations 分析大型语言模型中的谄媚现象及其缓解策略 large language model
6 ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data ScribeAgent：利用生产级工作流数据微调LLM，提升Web Agent在专业领域的性能 large language model
7 IRLab@iKAT24: Learned Sparse Retrieval with Multi-aspect LLM Query Generation for Conversational Search 针对对话式搜索，提出基于多方面LLM查询生成和稀疏检索的学习方法 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🔗⭐
8 On the Impact of Fine-Tuning on Chain-of-Thought Reasoning 研究表明，微调会降低大型语言模型链式思考推理的可靠性。 reinforcement learning RLHF large language model
9 Information Extraction from Heterogeneous Documents without Ground Truth Labels using Synthetic Label Generation and Knowledge Distillation 提出TAIL方法，结合合成标签生成与知识蒸馏，解决异构文档信息抽取难题。 distillation multimodal
10 Tulu 3: Pushing Frontiers in Open Language Model Post-Training Tulu 3：开源语言模型后训练的突破，超越Llama 3.1 Instruct及部分闭源模型 reinforcement learning DPO direct preference optimization

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
11 Evaluating LLM Prompts for Data Augmentation in Multi-label Classification of Ecological Texts 利用LLM提示进行数据增强，提升生态文本多标签分类性能 manipulation large language model
12 Universal and Context-Independent Triggers for Precise Control of LLM Outputs 提出通用且上下文无关的触发器，实现对LLM输出的精确控制 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页