cs.CL（2024-03-06）

📊 共 24 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) (22 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Large Language Models to Support Real-World Fact-Checking 提出多模态大语言模型以支持现实世界的事实核查 large language model multimodal
2 Can Large Language Models do Analytical Reasoning? 提出分治法以提升大型语言模型的分析推理能力 large language model chain-of-thought
3 On the Origins of Linear Representations in Large Language Models 提出简单潜变量模型以揭示大语言模型线性表示的起源 large language model
4 Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ 提出MultiQ基准评估大型语言模型的多语言能力 large language model
5 Rapidly Developing High-quality Instruction Data and Evaluation Benchmark for Large Language Models with Minimal Human Effort: A Case Study on Japanese 提出高效自指令方法以快速生成日语指令数据和评估基准 large language model
6 Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language Models 提出Mixture-of-LoRAs以解决多任务学习中的干扰问题 large language model
7 Levels of AI Agents: from Rules to Large Language Models 提出AI代理的六个层级以提升智能决策能力 large language model
8 SaulLM-7B: A pioneering Large Language Model for Law 提出SaulLM-7B以解决法律文本理解与生成问题 large language model
9 ShortGPT: Layers in Large Language Models are More Redundant Than You Expect 提出ShortGPT以解决大语言模型冗余层问题 large language model
10 A Modular Approach for Multimodal Summarization of TV Shows 提出模块化方法以解决电视节目多模态摘要问题 multimodal
11 PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion 提出PPTC-R基准以评估大语言模型在PowerPoint任务完成中的鲁棒性 large language model ✅
12 CLongEval: A Chinese Benchmark for Evaluating Long-Context Large Language Models 提出CLongEval以解决长上下文大语言模型评估不足问题 large language model
13 Learning to Decode Collaboratively with Multiple Language Models 提出多语言模型协作解码方法以提升任务性能 large language model instruction following ✅
14 KIWI: A Dataset of Knowledge-Intensive Writing Instructions for Answering Research Questions 构建KIWI数据集以提升LLM在知识密集写作中的指令遵循能力 large language model instruction following
15 X-Shot: A Unified System to Handle Frequent, Few-shot and Zero-shot Learning Simultaneously in Classification 提出X-Shot以同时解决频繁、少样本和零样本学习问题 large language model instruction following
16 Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models 量化代码生成能力评估中的数据污染问题 large language model
17 WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off 提出WaterMax以解决大语言模型水印检测与质量的权衡问题 large language model ✅
18 FaaF: Facts as a Function for the evaluation of generated text 提出FaaF以解决生成文本的事实验证问题 large language model
19 Emojinize: Enriching Any Text with Emoji Translations 提出Emojinize以解决文本表情符号翻译问题 large language model
20 GPTopic: Dynamic and Interactive Topic Representations 提出GPTopic以解决传统主题建模的可访问性问题 large language model ✅
21 A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation 提出多源知识基准以解决对话生成中的知识检索问题 large language model
22 Japanese-English Sentence Translation Exercises Dataset for Automatic Grading 提出自动评估日英翻译练习的系统以提升语言学习效果 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
23 Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem 提出基于不可解数学问题的评估方法以解决LLM幻觉问题 reinforcement learning RLHF large language model ✅
24 Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization 提出D²O优化方法以解决LLM对人类负样本的对齐问题 DPO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页