cs.CL（2024-08-28）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 Bias in LLMs as Annotators: The Effect of Party Cues on Labelling Decision by Large Language Models 研究表明：大型语言模型作为标注者会受到政治倾向信息的影响 large language model
2 Using Large Language Models to Create AI Personas for Replication, Generalization and Prediction of Media Effects: An Empirical Test of 133 Published Experimental Research Findings 利用大型语言模型创建AI角色，用于复制、推广和预测媒体影响 large language model
3 Structured Event Reasoning with Large Language Models 提出结合结构化事件表示与大语言模型的方法，提升复杂事件推理能力。 large language model
4 Scaling Up Summarization: Leveraging Large Language Models for Long Text Extractive Summarization EYEGLAXS框架：利用大语言模型进行长文本抽取式摘要，并在PubMed和ArXiv数据集上取得新性能。 large language model
5 SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models 提出SIaM，利用代码辅助的大语言模型实现数学推理能力的自我提升 large language model
6 Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression 提出指令感知上下文压缩方法，提升大语言模型效率与效果 large language model
7 Legilimens: Practical and Unified Content Moderation for Large Language Model Services Legilimens：为大型语言模型服务提供实用且统一的内容审核框架 large language model
8 Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Experts Nexus：通过自适应路由实现高效的混合专家模型训练 large language model
9 LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation LRP4RAG：利用逐层相关性传播检测RAG中的幻觉问题 large language model
10 BattleAgentBench: A Benchmark for Evaluating Cooperation and Competition Capabilities of Language Models in Multi-Agent Systems 提出BattleAgentBench，用于评估语言模型在多智能体系统中的合作与竞争能力 large language model
11 Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions 提出基于角色扮演LLM交互的心理咨询模拟框架，解决人工标注成本高昂问题。 large language model
12 WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback WildFeedback：利用用户交互反馈对齐大型语言模型 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 Boosting Lossless Speculative Decoding via Feature Sampling and Partial Alignment Distillation 提出FSPAD，通过特征采样与部分对齐蒸馏提升无损推测解码效率。 distillation large language model
14 StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements StyleRemix：通过风格元素蒸馏与扰动实现可解释的作者身份混淆 distillation large language model
15 ConCSE: Unified Contrastive Learning and Augmentation for Code-Switched Embeddings 提出ConCSE，统一对比学习与增强，提升英韩代码混合嵌入表示。 contrastive learning
16 ReMamba: Equip Mamba with Effective Long-Sequence Modeling ReMamba：通过选择性压缩和自适应增强Mamba长序列建模能力 Mamba

⬅️ 返回 cs.CL 首页 · 🏠 返回主页