cs.CL（2024-01-18）

📊 共 16 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) (13 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 A Survey on Hardware Accelerators for Large Language Models 综述硬件加速器以提升大型语言模型的性能与能效 large language model
2 Large Language Models for Scientific Information Extraction: An Empirical Study for Virology 提出基于大语言模型的科学信息提取方法以解决病毒学领域信息获取问题 large language model
3 Gender Bias in Machine Translation and The Era of Large Language Models 探讨机器翻译中的性别偏见及其解决方案 large language model
4 Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access 提出草图引导约束解码以提升黑箱大语言模型的性能 large language model
5 Leveraging Biases in Large Language Models: "bias-kNN'' for Effective Few-Shot Learning 提出'bias-kNN'方法以利用大语言模型中的偏见提升少样本学习效果 large language model
6 Lateral Phishing With Large Language Models: A Large Organization Comparative Study 比较LLM生成与人工撰写的网络钓鱼邮件的有效性 large language model
7 R-Judge: Benchmarking Safety Risk Awareness for LLM Agents 提出R-Judge以评估LLM代理的安全风险意识 large language model ✅
8 All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks 提出简单黑箱方法以解决大型语言模型的越狱攻击问题 large language model
9 Inconsistent dialogue responses and how to recover from them 提出对话一致性检测与恢复方法以解决聊天系统问题 large language model
10 Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation 提出Quintd工具以解决开放大语言模型在数据到文本生成中的语义准确性问题 large language model
11 Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs 提出代码提示以提升文本+代码LLM的条件推理能力 chain-of-thought
12 A Comparative Study on Annotation Quality of Crowdsourcing and LLM via Label Aggregation 提出Crowd-LLM混合标签聚合方法以提升数据标注质量 large language model
13 Interplay of Semantic Communication and Knowledge Learning 提出知识图谱增强的语义通信系统以提升解码性能 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
14 Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals? 探讨大型语言模型在科学摘要生成中的适应性与控制性 classifier-free guidance large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
15 Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations 提出MultiBully-Ex以解决网络欺凌表情包的可解释性问题 HuMoR multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
16 Self-Rewarding Language Models 提出自奖励语言模型以提升训练反馈质量 DPO instruction following

⬅️ 返回 cs.CL 首页 · 🏠 返回主页