cs.CL（2024-08-18）

📊 共 19 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) (3) 支柱八：物理动画 (Physics-based Animation) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis	提出PanoSent基准数据集与情感链推理框架，用于多模态对话场景下的全景情感六元组抽取。	large language model multimodal
2	HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model	HiAgent：利用分层工作记忆管理解决LLM长时程Agent任务	large language model	✅
3	Crossing New Frontiers: Knowledge-Augmented Large Language Model Prompting for Zero-Shot Text-Based De Novo Molecule Design	提出知识增强的大语言模型提示方法，用于零样本文本驱动的分子设计。	large language model
4	Revisiting the Graph Reasoning Ability of Large Language Models: Case Studies in Translation, Connectivity and Shortest Path	重新审视大语言模型的图推理能力：翻译、连通性和最短路径案例研究	large language model
5	Improving and Assessing the Fidelity of Large Language Models Alignment to Online Communities	提出一种基于指令调优的大语言模型对齐框架，用于评估其在在线社区中的表现	large language model
6	Fostering Natural Conversation in Large Language Models with NICO: a Natural Interactive COnversation dataset	NICO：一个自然交互式中文对话数据集，旨在提升LLM的自然对话能力	large language model
7	Image-Based Geolocation Using Large Vision-Language Models	提出基于大型视觉语言模型的图像地理定位框架，显著提升定位精度。	chain-of-thought
8	Out-of-distribution generalization via composition: a lens through induction heads in Transformers	通过Transformer归纳头组合实现分布外泛化能力	large language model
9	Retrieval-Augmented Generation Meets Data-Driven Tabula Rasa Approach for Temporal Knowledge Graph Forecasting	提出sLA-tKGF框架，结合RAG与数据驱动的Tabula Rasa方法，提升时序知识图谱预测性能。	large language model
10	Grammatical Error Feedback: An Implicit Evaluation Approach	提出一种隐式评估方法，无需人工标注即可评估语法错误反馈质量。	large language model
11	Using ChatGPT to Score Essays and Short-Form Constructed Responses	评估ChatGPT在作文和简答题评分中的表现，探索其作为辅助评分工具的潜力	large language model
12	HySem: A context length optimized LLM pipeline for unstructured tabular extraction	HySem：针对非结构化表格抽取，优化上下文长度的LLM流程	large language model
13	FASST: Fast LLM-based Simultaneous Speech Translation	FASST：一种基于快速LLM的同步语音翻译方法，提升质量-延迟权衡。	large language model
14	No Such Thing as a General Learner: Language models and their dual optimization	探讨LLM双重优化特性，反思其在人类认知和语言习得研究中的作用	large language model
15	Identifying Speakers and Addressees of Quotations in Novels with Prompt Learning	提出基于Prompt Learning的小说引语说话人和听者识别方法	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	🔗	⭐
16	Reward Difference Optimization For Sample Reweighting In Offline RLHF	提出奖励差异优化RDO，提升离线RLHF中LLM对人类偏好的对齐效果	reinforcement learning offline RL RLHF
17	REFINE-LM: Mitigating Language Model Stereotypes via Reinforcement Learning	提出REFINE-LM以解决语言模型中的偏见问题	reinforcement learning
18	WPN: An Unlearning Method Based on N-pair Contrastive Learning in Language Models	提出WPN：一种基于N-pair对比学习的语言模型不可学习方法，用于消除有害知识。	contrastive learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
19	Challenges and Responses in the Practice of Large Language Models	总结大语言模型实践中的挑战与应对，提供AI知识框架。	PULSE large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页