cs.CL（2023-10-16）

📊 共 34 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (27 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (27 篇)

#题目一句话要点标签🔗⭐
1 CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference 提出CoTFormer以解决计算资源受限环境下的推理效率问题 chain-of-thought
2 Semantic Parsing by Large Language Models for Intricate Updating Strategies of Zero-Shot Dialogue State Tracking 提出ParsingDST以解决零样本对话状态跟踪中的复杂更新策略问题 large language model
3 Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis 通过错误分析提出新方法以提升大型语言模型的安全性 large language model
4 Text Summarization Using Large Language Models: A Comparative Study of MPT-7b-instruct, Falcon-7b-instruct, and OpenAI Chat-GPT Models 比较不同大语言模型在文本摘要中的应用效果 large language model
5 Prediction of Arabic Legal Rulings using Large Language Models 利用大型语言模型预测阿拉伯法律裁决 large language model
6 Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT 评估ChatGPT在开放世界意图发现与识别中的应用 large language model
7 Battle of the Large Language Models: Dolly vs LLaMA vs Vicuna vs Guanaco vs Bard vs ChatGPT -- A Text-to-SQL Parsing Comparison 比较多种大型语言模型在Text-to-SQL解析中的表现 large language model
8 IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models 提出影响驱动的选择性标注方法以降低大语言模型的标注成本 large language model ✅
9 Towards reducing hallucination in extracting information from financial reports using Large Language Models 提出利用大语言模型减少财报信息提取中的幻觉问题 large language model
10 Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning Environment 提出基于大语言模型的开放信息提取新方法 large language model
11 On Context Utilization in Summarization with Large Language Models 提出中间摘要方法以解决长文本摘要中的位置偏差问题 large language model ✅
12 MechGPT, a language-based strategy for mechanics and materials modeling that connects knowledge across scales, disciplines and modalities 提出MechGPT以连接多尺度材料失效领域的知识 large language model foundation model multimodal
13 Privacy in Large Language Models: Attacks, Defenses and Future Directions 分析大型语言模型隐私攻击与防御策略 large language model
14 JMedLoRA:Medical Domain Adaptation on Japanese Large Language Models using Instruction-tuning 提出JMedLoRA以解决日本医疗领域大语言模型适应问题 large language model
15 Improving Large Language Model Fine-tuning for Solving Math Problems 提出三种微调策略以提升大语言模型数学问题求解能力 large language model
16 In-context Pretraining: Language Modeling Beyond Document Boundaries 提出上下文预训练以解决文档边界推理问题 large language model
17 Bridging the Novice-Expert Gap via Models of Decision-Making: A Case Study on Remediating Math Mistakes 提出Bridge方法以解决新手与专家之间的知识差距 large language model ✅
18 OpenAgents: An Open Platform for Language Agents in the Wild 提出OpenAgents以解决语言代理在实际应用中的可用性问题 large language model
19 Llemma: An Open Language Model For Mathematics 提出Llemma以提升数学语言模型的性能 large language model
20 Demonstrations Are All You Need: Advancing Offensive Content Paraphrasing using In-Context Learning 提出基于上下文学习的攻击性内容改写方法以提升交流文明 large language model
21 Character-LLM: A Trainable Agent for Role-Playing 提出Character-LLM以模拟特定人物的角色扮演 large language model
22 "Mistakes Help Us Grow": Facilitating and Evaluating Growth Mindset Supportive Language in Classrooms 利用大型语言模型支持教师的成长型思维语言 large language model
23 Data Contamination Through the Lens of Time 通过时间视角分析大语言模型的数据污染问题 large language model
24 G-SPEED: General SParse Efficient Editing MoDel 提出G-SPEED以解决高效文本编辑需求 large language model ✅
25 Evaluating the Reversal Curse in Model Editing 提出双向语言模型编辑以解决反转诅咒问题 large language model
26 Generative Calibration for In-context Learning 提出生成校准方法以解决上下文学习中的标签偏移问题 large language model
27 Learning to Rank Context for Named Entity Recognition Using a Synthetic Dataset 提出合成数据集以优化长文档命名实体识别的上下文检索 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🔗⭐
28 Verbosity Bias in Preference Labeling by Large Language Models 提出评估大型语言模型的冗长偏见问题及其度量方法 reinforcement learning RLHF large language model
29 Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks 调查大型语言模型在对抗攻击下的脆弱性 reinforcement learning large language model
30 Theory of Mind for Multi-Agent Collaboration via Large Language Models 利用大语言模型提升多智能体协作中的心智理论能力 reinforcement learning large language model
31 Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning 提出离线强化学习框架以提升对话系统的人格一致性 reinforcement learning offline RL offline reinforcement learning
32 Let's reward step by step: Step-Level reward model as the Navigators for Reasoning 提出基于步骤奖励模型的推理导航方法以提升多步推理能力 PPO large language model chain-of-thought
33 SD-HuBERT: Sentence-Level Self-Distillation Induces Syllabic Organization in HuBERT 提出SD-HuBERT以实现无监督音节组织的句子级表示学习 distillation

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

#题目一句话要点标签🔗⭐
34 Bridging Code Semantic and LLMs: Semantic Chain-of-Thought Prompting for Code Generation 提出语义链式思维提示以提升代码生成的准确性 semantic mapping semantic map large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页