cs.CL（2024-02-01）

📊 共 26 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (18 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement 提出Logic-Explainer框架以提升LLMs的伦理推理解释能力 large language model chain-of-thought
2 IndiVec: An Exploration of Leveraging Large Language Models for Media Bias Detection with Fine-Grained Bias Indicators 提出IndiVec以解决媒体偏见检测问题 large language model instruction following
3 When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards 揭示大语言模型排行榜对基准敏感性的问题 large language model ✅
4 From PARIS to LE-PARIS: Toward Patent Response Automation with Recommender Systems and Collaborative Large Language Models 提出PARIS与LE-PARIS以自动化专利响应处理 large language model
5 Evaluation Methodology for Large Language Models for Multilingual Document Question and Answer 提出多语言文档问答的评估方法以提升LLM性能 large language model
6 Plan-Grounded Large Language Models for Dual Goal Conversational Settings 提出基于计划的语言模型以解决双重目标对话问题 large language model
7 Evaluating Large Language Models for Generalization and Robustness via Data Compression 提出无损数据压缩评估方法以解决大语言模型的泛化与鲁棒性问题 large language model
8 SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models 提出SA-MDKIF框架以解决医疗领域知识注入问题 large language model
9 Prompt-Time Symbolic Knowledge Capture with Large Language Models 提出基于提示的知识捕获方法以增强大型语言模型 large language model ✅
10 Can Large Language Models Understand Context? 提出上下文理解基准以评估大型语言模型的能力 large language model
11 Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization? 提出紧凑型大语言模型以解决会议摘要问题 large language model
12 A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains 提出REVEAL数据集以评估推理链的自动验证器 chain-of-thought
13 Hierarchical Multi-Label Classification of Online Vaccine Concerns 提出层次化多标签分类方法以识别在线疫苗关注问题 large language model
14 CroissantLLM: A Truly Bilingual French-English Language Model 提出CroissantLLM以解决双语模型性能不足问题 large language model
15 Executable Code Actions Elicit Better LLM Agents 提出可执行代码行动以解决LLM代理灵活性不足问题 large language model
16 Redefining "Hallucination" in LLMs: Towards a psychology-informed framework for mitigating misinformation 提出心理学框架以减轻大型语言模型中的虚假信息问题 large language model
17 Exploring Spatial Schema Intuitions in Large Language and Vision Models 探讨大语言模型中的空间模式直觉以理解人类语言 large language model ✅
18 Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration 提出多LLM协作方法以识别知识缺口并避免错误回答 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
19 Transforming and Combining Rewards for Aligning Large Language Models 提出LSC变换以优化语言模型的奖励对齐问题 RLHF large language model
20 Does DetectGPT Fully Utilize Perturbation? Bridging Selective Perturbation to Fine-tuned Contrastive Learning Detector would be Better 提出Pecola以解决DetectGPT在扰动利用上的不足 contrastive learning large language model
21 BlackMamba: Mixture of Experts for State-Space Models 提出BlackMamba以结合状态空间模型与专家混合模型的优势 Mamba SSM ✅
22 Investigating Bias Representations in Llama 2 Chat via Activation Steering 通过激活引导技术探讨Llama 2 Chat中的偏见表现 reinforcement learning RLHF large language model
23 Towards Efficient Exact Optimization of Language Model Alignment 提出EXO以高效优化语言模型与人类偏好的对齐问题 reinforcement learning DPO direct preference optimization ✅
24 Improving Dialog Safety using Socially Aware Contrastive Learning 提出社会意识对比学习以提升对话安全性 contrastive learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
25 What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection 提出基于大语言模型的社交媒体机器人检测方法 manipulation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
26 Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders 提出T5VQVAE以改善变分自编码器的语义控制问题 VQ-VAE

⬅️ 返回 cs.CL 首页 · 🏠 返回主页