cs.CL（2024-05-15）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15) 支柱二：RL算法与架构 (RL & Architecture) (1)

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

#题目一句话要点标签🔗⭐
1 A safety realignment framework via subspace-oriented model fusion for large language models 提出基于子空间模型融合的安全重对齐框架，提升大语言模型安全性。 large language model instruction following
2 A survey on fairness of large language models in e-commerce: progress, application, and challenge 综述：电商大语言模型公平性研究进展、应用与挑战 large language model
3 Spectral Editing of Activations for Large Language Model Alignment 提出激活谱编辑(SEA)方法，用于大语言模型的事实性和偏见对齐。 large language model
4 Tell Me Why: Explainable Public Health Fact-Checking with Large Language Models 利用大型语言模型进行可解释的公共卫生事实核查研究 large language model
5 PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models 提出PolygloToxicityPrompts，用于大规模多语言评估大型语言模型中的神经毒性退化问题。 large language model
6 Large Language Model Bias Mitigation from the Perspective of Knowledge Editing 提出Fairness Stamp (FAST)，通过知识编辑缓解大语言模型偏见问题 large language model
7 Comparing the Efficacy of GPT-4 and Chat-GPT in Mental Health Care: A Blind Assessment of Large Language Models for Psychological Support 对比GPT-4与ChatGPT在心理健康支持中的有效性：一项大型语言模型的盲评估研究 large language model
8 Sign of the Times: Evaluating the use of Large Language Models for Idiomaticity Detection 评估大型语言模型在成语检测任务中的性能表现，并与微调模型对比。 large language model
9 A Comprehensive Survey of Accelerated Generation Techniques in Large Language Models 综述加速大型语言模型生成技术，应对实时应用中的高延迟挑战。 large language model
10 Simulating Policy Impacts: Developing a Generative Scenario Writing Method to Evaluate the Perceived Effects of Regulation 提出基于LLM的生成式情景写作方法，评估政策对AI负面影响的感知效果。 large language model
11 Beyond Flesch-Kincaid: Prompt-based Metrics Improve Difficulty Classification of Educational Texts 提出基于Prompt的文本难度评估指标，提升教育文本难度分类效果 large language model
12 Facilitating Opinion Diversity through Hybrid NLP Approaches 提出一种混合NLP方法，旨在促进在线讨论中意见的多样性。 large language model
13 LLMs can learn self-restraint through iterative self-reflection 提出ReSearch算法，通过迭代自反思使LLM学习自我约束，减少幻觉。 large language model
14 Do language models capture implied discourse meanings? An investigation with exhaustivity implicatures of Korean morphology 评估大型语言模型对韩语形态句法蕴含的会话含义的捕捉能力 large language model
15 New Textual Corpora for Serbian Language Modeling 为塞尔维亚语建模提出新的文本语料库，促进大型语言模型训练 large language model

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

#题目一句话要点标签🔗⭐
16 Elements of World Knowledge (EWoK): A Cognition-Inspired Framework for Evaluating Basic World Knowledge in Language Models 提出EWoK框架，用于评估语言模型对基本世界知识的理解能力。 world model large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页