cs.CL（2024-01-22）

📊 共 18 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) (15 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (3)

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

#题目一句话要点标签🔗⭐
1 The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models 评估多模态大语言模型在非语言抽象推理中的能力 large language model foundation model chain-of-thought ✅
2 CMMMU: A Chinese Massive Multi-discipline Multimodal Understanding Benchmark 提出CMMMU基准以评估中文多模态模型的推理能力 multimodal
3 Hallucination is Inevitable: An Innate Limitation of Large Language Models 提出形式化框架揭示大型语言模型幻觉不可避免性 large language model
4 Fine-tuning Large Language Models for Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection 提出多生成器、多领域和多语言文本检测方法以解决机器生成文本识别问题 large language model
5 Temporal Blind Spots in Large Language Models 探讨大型语言模型中的时间盲点以提升时序理解能力 large language model ✅
6 APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference 提出APT以提高大语言模型的训练与推理效率 large language model
7 Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text 提出Binoculars以实现零样本检测机器生成文本 large language model
8 A Framework to Implement 1+N Multi-task Fine-tuning Pattern in LLMs Using the CGC-LORA Algorithm 提出CGC-LoRA算法以实现LLMs的1+N多任务微调模式 large language model
9 Text Embedding Inversion Security for Multilingual Language Models 提出多语言嵌入反演安全机制以应对安全威胁 large language model
10 Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? 提出系统框架以解决LLMs生成与检索上下文合并问题 large language model
11 PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety 提出PsySafe框架以解决多智能体系统安全问题 large language model ✅
12 SMUTF: Schema Matching Using Generative Tags and Hybrid Features 提出SMUTF以解决大规模表格数据模式匹配问题 large language model ✅
13 Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data 提出廉价学习方法以提升社交数据科学中的语言模型性能 large language model
14 Revisiting Demonstration Selection Strategies in In-Context Learning 提出TopK + ConE以解决示例选择对ICL性能影响的问题 large language model
15 AI for social science and social science of AI: A Survey 提出AI与社会科学结合的系统框架以促进研究 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
16 GRATH: Gradual Self-Truthifying for Large Language Models 提出GRATH以解决大型语言模型的真实性问题 DPO direct preference optimization large language model
17 Distilling Mathematical Reasoning Capabilities into Small Language Models 提出方程思维蒸馏技术以提升小型语言模型的数学推理能力 distillation large language model chain-of-thought
18 West-of-N: Synthetic Preferences for Self-Improving Reward Models 提出合成偏好数据以提升奖励模型质量 reinforcement learning RLHF

⬅️ 返回 cs.CL 首页 · 🏠 返回主页