cs.CL（2024-06-11）

📊 共 17 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#	题目	一句话要点	标签	🔗	⭐
1	UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback	UICoder：通过自动反馈微调大型语言模型以生成用户界面代码	large language model
2	MultiPragEval: Multilingual Pragmatic Evaluation of Large Language Models	MultiPragEval：首个多语种LLM语用评估基准，考察模型深层语言理解能力	large language model
3	Using General Large Language Models to Classify Mathematical Documents	利用通用大语言模型进行数学文档分类，提升文献检索效率。	large language model
4	Test-Time Fairness and Robustness in Large Language Models	提出分层不变性与数据增强策略，提升大语言模型测试时公平性和鲁棒性	large language model
5	Beyond Words: On Large Language Models Actionability in Mission-Critical Risk Analysis	利用RAG和微调LLM进行任务关键型风险分析，提升效率并发现潜在风险	large language model
6	Advancing Annotation of Stance in Social Media Posts: A Comparative Analysis of Large Language Models and Crowd Sourcing	对比分析大型语言模型与众包在社交媒体立场标注中的表现，揭示LLM的局限性。	large language model
7	Multimodal Belief Prediction	提出多模态信念预测框架，融合文本与语音信息提升信念识别准确率	multimodal
8	Markov Constraint as Large Language Model Surrogate	提出NgramMarkov约束，利用大语言模型提升约束编程文本生成效率与质量。	large language model
9	Large Language Models are Limited in Out-of-Context Knowledge Reasoning	评估大语言模型在上下文无关知识推理中的局限性	large language model
10	REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy	提出REAL采样以解决开放式生成中的事实性与多样性问题	large language model
11	Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena	提出Open-LLM-Leaderboard，通过开放式问题评估LLM，解决选择偏差和随机猜测问题。	large language model	✅
12	On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations	提出实体变体鲁棒训练方法，提升文档级关系抽取模型泛化能力	large language model
13	VersiCode: Towards Version-controllable Code Generation	VersiCode：面向版本可控的代码生成任务、数据集与评估指标	large language model	✅
14	BertaQA: How Much Do Language Models Know About Local Culture?	BertaQA：评估语言模型对本地文化知识的掌握程度，揭示跨语言知识迁移现象。	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	🔗	⭐
15	When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models	提出线性注意力增强技术，结合推测解码，加速并优化自回归大语言模型。	linear attention large language model	✅
16	Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling	Samba：一种高效的无限上下文语言建模的简单混合状态空间模型	Mamba SSM state space model	✅

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

#	题目	一句话要点	标签	🔗	⭐
17	Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities	综述性研究：全面分析互联网有毒Meme的计算检测与解释方法	HuMoR large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页