cs.CL（2024-08-29）

📊 共 22 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic 提出Critic-CoT，通过思维链批判提升大语言模型推理能力 large language model chain-of-thought
2 Logic Contrastive Reasoning with Lightweight Large Language Model for Math Word Problems 提出逻辑对比推理方法，提升轻量级大语言模型在数学应用题上的表现 large language model chain-of-thought
3 A longitudinal sentiment analysis of Sinophobia during COVID-19 using large language models 利用大型语言模型纵向分析COVID-19期间的仇华情绪 large language model
4 Assessing Large Language Models for Online Extremism Research: Identification, Explanation, and New Knowledge 评估大型语言模型在网络极端主义研究中的应用：识别、解释与新知识发现 large language model
5 A Survey for Large Language Models in Biomedicine 综述性分析生物医学领域大语言模型，聚焦实际应用、挑战与未来方向 large language model
6 Can Large Language Models Replace Human Subjects? A Large-Scale Replication of Scenario-Based Experiments in Psychology and Management 利用大语言模型复现心理学实验：优势、局限与伦理考量 large language model
7 How Well Do LLMs Handle Cantonese? Benchmarking Cantonese Capabilities of Large Language Models 构建粤语LLM基准测试，评估并提升大语言模型在粤语上的能力 large language model
8 Theoretical and Methodological Framework for Studying Texts Produced by Large Language Models 构建研究大型语言模型文本产出的理论和方法框架 large language model
9 Instruction-tuned Large Language Models for Machine Translation in the Medical Domain 指令调优大型语言模型提升医疗领域机器翻译性能 large language model
10 Enhancing AI-Driven Psychological Consultation: Layered Prompts with Large Language Models 提出分层提示方法，利用大语言模型增强AI心理咨询服务 large language model
11 LLaVA-Chef: A Multi-modal Generative Model for Food Recipes 提出LLaVA-Chef，一种用于生成食物菜谱的多模态生成模型 large language model
12 WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks 提出一种基于线性变换水印的EaaS水印方法，克服复述攻击的脆弱性。 large language model
13 HoneyComb: A Flexible LLM-Based Agent System for Materials Science HoneyComb：一种灵活的、基于LLM的材料科学智能体系统 large language model
14 Enhancing Dialogue Generation in Werewolf Game Through Situation Analysis and Persuasion Strategies 提出基于情境分析和说服策略的狼人杀对话生成增强方法 large language model
15 LoraMap: Harnessing the Power of LoRA Connections LoraMap：利用LoRA连接提升LLM在事实核查任务中的性能 large language model
16 Plausible-Parrots @ MSP2023: Enhancing Semantic Plausibility Modeling using Entity and Event Knowledge Plausible-Parrots通过注入实体和事件知识增强LLM的语义合理性建模能力 large language model
17 LLMs vs Established Text Augmentation Techniques for Classification: When do the Benefits Outweight the Costs? 对比LLM与传统文本增强技术：探究分类任务中LLM的性价比优势 large language model
18 Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning 提出基于上下文学习的自对齐方法，提升LLM对文化价值观的对齐能力 large language model
19 The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization 分析Nucleus Sampling对缓解LLM文本记忆化效果不佳的现象 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🔗⭐
20 Reinforcement Learning without Human Feedback for Last Mile Fine-Tuning of Large Language Models 提出无需人工反馈的强化学习方法，用于大语言模型在下游任务上的精调。 reinforcement learning imitation learning large language model
21 A Gradient Analysis Framework for Rewarding Good and Penalizing Bad Examples in Language Models 提出基于梯度分析的框架，用于优化语言模型中好坏样本的奖励与惩罚机制 RLHF DPO direct preference optimization

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Modeling offensive content detection for TikTok 针对TikTok平台的冒犯性内容检测，提出并建模了一系列机器学习和深度学习模型。 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页