cs.CL（2024-07-10）

📊 共 24 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 Analyzing Large language models chatbots: An experimental approach using a probability test 通过概率测试分析大型语言模型聊天机器人的逻辑推理能力 large language model
2 A Proposed S.C.O.R.E. Evaluation Framework for Large Language Models : Safety, Consensus, Objectivity, Reproducibility and Explainability 提出S.C.O.R.E.框架，用于评估医疗领域大语言模型的安全性、可靠性和伦理 large language model
3 Arabic Automatic Story Generation with Large Language Models 利用大型语言模型进行阿拉伯语自动故事生成，并构建高质量训练数据集。 large language model
4 Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models 揭示大语言模型中的“知识遮蔽”现象，并提出缓解幻觉的方法 large language model
5 Attribute or Abstain: Large Language Models as Long Document Assistants 提出LAB基准，评估LLM在长文档问答中进行归因的能力，并探索不同归因方法的效果。 large language model
6 A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training 综述大规模Web挖掘语料库在大型语言模型预训练中的挑战 large language model
7 Beyond Benchmarking: A New Paradigm for Evaluation and Assessment of Large Language Models 提出LLM评估新范式：从基准测试转向问题归因与优化建议 large language model
8 Review-LLM: Harnessing Large Language Models for Personalized Review Generation 提出Review-LLM，利用大语言模型生成个性化商品评论，解决现有方法个性化不足问题。 large language model
9 Interpretable Differential Diagnosis with Dual-Inference Large Language Models 提出Dual-Inf框架，利用双向推理LLM实现可解释的鉴别诊断 large language model
10 ETM: Modern Insights into Perspective on Text-to-SQL Evaluation in the Age of Large Language Models 提出ETM指标，提升大语言模型Text-to-SQL任务的评测可靠性 large language model
11 Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey) 针对大语言模型的事实依据与评估：实际挑战与经验总结综述 large language model
12 RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization 提出RoLoRA以解决LoRA方法中的激活异常问题 large language model multimodal ✅
13 Training on the Test Task Confounds Evaluation and Emergence 揭示测试任务训练对大语言模型评估和涌现能力的影响，并提出校正方法 large language model
14 Rel-A.I.: An Interaction-Centered Approach To Measuring Human-LM Reliance Rel-A.I.：一种以交互为中心的框架，用于评估人类对语言模型输出的依赖程度 large language model
15 Virtual Agents for Alcohol Use Counseling: Exploring LLM-Powered Motivational Interviewing 提出基于LLM的虚拟咨询师，用于酒精使用问题的动机访谈。 large language model
16 FsPONER: Few-shot Prompt Optimization for Named Entity Recognition in Domain-specific Scenarios FsPONER：针对领域特定场景，优化小样本提示学习的命名实体识别方法 large language model
17 On Leakage of Code Generation Evaluation Datasets 揭示代码生成评估数据集泄露问题，并提出新的无污染基准测试集LBPP。 large language model ✅
18 Beyond Fixed Length: Bucket Pre-training is All You Need 提出多桶数据预训练方法，解决LLM定长预训练的数据质量和效率问题 large language model
19 Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture 提出多语言混合评估方法，揭示LLM安全对齐在多语言环境下的脆弱性 large language model
20 Probability of Differentiation Reveals Brittleness of Homogeneity Bias in GPT-4 利用区分概率揭示GPT-4中同质性偏差的脆弱性 large language model

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

#题目一句话要点标签🔗⭐
21 Psycho-linguistic Experiment on Universal Semantic Components of Verbal Humor: System Description and Annotation 提出一种基于自定步速阅读的幽默语义成分标注系统 HuMoR

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities 提出针对LLM多智能体系统中操纵知识传播的两阶段攻击方法 manipulation large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
23 WorldAPIs: The World Is Worth How Many APIs? A Thought Experiment WorldAPIs：通过 wikiHow 教程，探索具身智能体所需的 API 空间 affordance 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🔗⭐
24 LokiLM: Technical Report LokiLM：一种基于知识蒸馏的14亿参数语言模型，在自然语言推理任务上表现出色。 distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页