cs.CL（2023-10-25）

📊 共 30 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) (23 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 R$^3$ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context 提出R$^3$提示方法以解决嘈杂环境下的推理问题 large language model chain-of-thought
2 Apollo: Zero-shot MultiModal Reasoning with Multiple Experts 提出Apollo框架以实现零-shot多模态推理 foundation model multimodal
3 Detecting Pretraining Data from Large Language Models 提出Min-K% Prob以解决大语言模型预训练数据检测问题 large language model
4 Prompt Me Up: Unleashing the Power of Alignments for Multimodal Entity and Relation Extraction 提出多模态对齐方法以提升实体与关系抽取能力 multimodal
5 HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models 提出HI-TOM基准以评估大型语言模型的高阶心智理论推理能力 large language model
6 Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting 提出集体批评与自我投票以提升大语言模型的多样性表现 large language model
7 OccuQuest: Mitigating Occupational Bias for Inclusive Large Language Models 提出OccuQuest以解决职业偏见问题，促进语言模型的包容性 large language model
8 CLEX: Continuous Length Extrapolation for Large Language Models 提出CLEX以解决长语言模型上下文窗口限制问题 large language model ✅
9 Decoding Stumpers: Large Language Models vs. Human Problem-Solvers 研究大型语言模型在解决直觉问题中的表现 large language model
10 Evaluating, Understanding, and Improving Constrained Text Generation for Large Language Models 提出约束文本生成方法以解决大语言模型的生成挑战 large language model
11 RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models 提出RCAgent以解决云根因分析中的自动化与隐私问题 large language model
12 PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization 提出PromptAgent以解决专家级提示优化问题 large language model chain-of-thought
13 LLM-FP4: 4-Bit Floating-Point Quantized Transformers 提出LLM-FP4以解决大语言模型的4位浮点量化问题 large language model ✅
14 BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generation 提出BOOST框架以提升语言模型的常识生成能力 large language model
15 Attention Lens: A Tool for Mechanistically Interpreting the Attention Head Information Retrieval Mechanism 提出Attention Lens以解析注意力头的信息检索机制 large language model
16 SkyMath: Technical Report 提出SkyMath以提升数学推理能力 large language model
17 Using GPT-4 to Augment Unbalanced Data for Automatic Scoring 提出基于GPT-4的数据增强框架以解决自动评分中的数据不平衡问题 large language model
18 Multilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper 提出多语言粗略政治立场分类方法以评估AI新闻的偏见 instruction following
19 Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study 通过跨语言迁移提升低资源编程语言的LLM性能 large language model
20 HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis 提出HANSEN基准以解决人类与AI口语文本作者分析问题 large language model ✅
21 Disentangling Extraction and Reasoning in Multi-hop Spatial Reasoning 提出信息提取与推理解耦以提升空间推理能力 large language model
22 ChatGPT is a Potential Zero-Shot Dependency Parser 探索ChatGPT在零样本依存句法分析中的潜力 large language model
23 Unraveling Feature Extraction Mechanisms in Neural Networks 基于神经切线核的特征提取机制研究 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
24 CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment 提出CycleAlign以解决大语言模型与人类价值对齐问题 reinforcement learning PPO RLHF
25 SuperHF: Supervised Iterative Learning from Human Feedback 提出SuperHF以解决语言模型对人类反馈的对齐问题 reinforcement learning PPO RLHF
26 SSLCL: An Efficient Model-Agnostic Supervised Contrastive Learning Framework for Emotion Recognition in Conversations 提出SSLCL框架以解决情感识别中的大批量限制问题 contrastive learning multimodal ✅
27 IntenDD: A Unified Contrastive Learning Approach for Intent Detection and Discovery 提出IntenDD以统一解决意图检测与发现问题 representation learning contrastive learning
28 BabyStories: Can Reinforcement Learning Teach Baby Language Models to Write Better Stories? 通过强化学习优化语言模型在故事创作中的表现 reinforcement learning RLHF ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
29 UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation 提出UPLex以解决大语言模型个性控制问题 manipulation large language model
30 Is ChatGPT a Good Multi-Party Conversation Solver? 评估ChatGPT在多方对话中的表现及其改进方案 MPC large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页