cs.CL（2024-04-09）

📊 共 21 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) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2) 支柱一：机器人控制 (Robot Control) (1 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Characterizing Multimodal Long-form Summarization: A Case Study on Financial Reports 提出多模态长文本摘要框架以解决金融报告摘要问题 large language model multimodal ✅
2 VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding? 提出VisualWebBench以评估多模态大语言模型在网页理解中的能力 large language model multimodal
3 FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models 提出FreeEval框架以解决大语言模型评估的可靠性与效率问题 large language model
4 Exploring the Necessity of Visual Modality in Multimodal Machine Translation using Authentic Datasets 探讨视觉模态在多模态机器翻译中的必要性 multimodal
5 Visually Descriptive Language Model for Vector Graphics Reasoning 提出视觉描述语言模型以解决矢量图形推理问题 foundation model multimodal ✅
6 Less is More for Improving Automatic Evaluation of Factual Consistency 提出LIM-RA以提升自动评估事实一致性问题 large language model
7 Rethinking How to Evaluate Language Model Jailbreak 提出三种新指标以评估语言模型越狱问题 large language model
8 Model Generation with LLMs: From Requirements to UML Sequence Diagrams 利用LLMs自动生成UML时序图以提升需求建模效率 large language model
9 Khayyam Challenge (PersianMMLU): Is Your LLM Truly Wise to The Persian Language? 提出Khayyam Challenge以评估波斯语大型语言模型的能力 large language model
10 Pitfalls of Conversational LLMs on News Debiasing 评估对话式大语言模型在新闻去偏见中的有效性 large language model
11 Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles 提出Clue-Instruct以解决教育类填字游戏线索生成问题 large language model
12 [Call for Papers] The 2nd BabyLM Challenge: Sample-efficient pretraining on a developmentally plausible corpus 第二届BabyLM挑战赛提出样本高效预训练方法 multimodal
13 Privacy Preserving Prompt Engineering: A Survey 系统综述隐私保护提示工程以应对隐私风险 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🔗⭐
14 Latent Distance Guided Alignment Training for Large Language Models 提出潜在距离引导对齐训练以解决大语言模型对齐问题 RLHF DPO large language model
15 Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation 提出检索增强方法以个性化大型语言模型 reinforcement learning distillation large language model
16 LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders 提出LLM2Vec以提升解码器模型的文本编码能力 contrastive learning large language model
17 Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages 提出Cendol以解决印尼低资源语言的生成模型问题 RLHF large language model
18 MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies 提出MiniCPM以探索小型语言模型的可扩展训练策略 DPO large language model ✅
19 VI-OOD: A Unified Representation Learning Framework for Textual Out-of-distribution Detection 提出VI-OOD框架以解决文本领域的OOD检测问题 representation learning ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
20 Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks 提出Ada-LEval以解决长文本评估的不足问题 manipulation large language model ✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
21 Generalizable Sarcasm Detection Is Just Around The Corner, Of Course! 提出新数据集以提升讽刺检测模型的泛化能力 HuMoR

⬅️ 返回 cs.CL 首页 · 🏠 返回主页