cs.CL（2025-02-14）

📊 共 23 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 Are Large Language Models the future crowd workers of Linguistics? 利用大型语言模型替代语言学领域的人工众包工作，提升数据获取效率。 large language model chain-of-thought
2 Leveraging large language models for structured information extraction from pathology reports 利用大型语言模型从病理报告中提取结构化信息 large language model
3 Large Language Models and Synthetic Data for Monitoring Dataset Mentions in Research Papers 利用大语言模型和合成数据自动检测研究论文中的数据集引用 large language model
4 Evaluating the Meta- and Object-Level Reasoning of Large Language Models for Question Answering 评估大型语言模型在问答任务中元层次和对象层次的推理能力 large language model
5 VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models VisCon-100K：利用上下文网络数据微调视觉语言模型，提升多模态理解能力 large language model multimodal
6 Large Language Diffusion Models 提出LLaDA：一种基于扩散模型的大语言模型，挑战自回归模型主导地位。 large language model instruction following ✅
7 A Preliminary Exploration with GPT-4o Voice Mode GPT-4o语音模式初步探索：音频理解与推理能力评估 large language model multimodal
8 Enhancing Multilingual LLM Pretraining with Model-Based Data Selection 提出基于模型的跨语言LLM预训练数据选择方法，提升模型性能和效率。 large language model
9 KGGen: Extracting Knowledge Graphs from Plain Text with Language Models KGGen：利用语言模型从纯文本中抽取高质量知识图谱，解决知识图谱数据稀缺问题。 foundation model
10 Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias 评估大型语言模型中男性泛指偏见：揭示并量化LLM对性别刻板印象的强化 large language model
11 Hallucinations and Truth: A Comprehensive Accuracy Evaluation of RAG, LoRA and DoRA 提出DoRA，在RAG基础上优化LLM微调，提升生成式AI在特定领域的准确率和效率。 large language model
12 Prediction hubs are context-informed frequent tokens in LLMs 揭示LLM预测中枢为上下文相关的频繁token，避免不必要的hubness缓解 large language model
13 LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing LaRA：基准测试检索增强生成与长文本LLM，揭示长文本处理或RAG路由并非万能解 large language model ✅
14 Named entity recognition for Serbian legal documents: Design, methodology and dataset development 提出一种基于BERT的塞尔维亚语法律文档命名实体识别方法与数据集 large language model
15 Aspect-Oriented Summarization for Psychiatric Short-Term Readmission Prediction 提出面向方面的摘要方法，用于提升精神病短期再入院预测性能 large language model
16 Organize the Web: Constructing Domains Enhances Pre-Training Data Curation WebOrganizer：通过构建领域增强预训练数据筛选，提升下游任务性能。 large language model
17 Beyond English: Unveiling Multilingual Bias in LLM Copyright Compliance 揭示LLM版权合规中的多语言偏见，发现不同语言处理差异 large language model
18 Can Post-Training Quantization Benefit from an Additional QLoRA Integration? 提出PTQ-QLoRA集成方法，提升量化大语言模型在资源受限环境下的性能。 large language model
19 ORI: O Routing Intelligence 提出ORI：一种基于LLM路由的智能框架，提升多任务处理性能。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
20 Scaling Multimodal Search and Recommendation with Small Language Models via Upside-Down Reinforcement Learning 提出基于倒置强化学习的小语言模型多模态搜索与推荐框架 reinforcement learning distillation large language model
21 MM-RLHF: The Next Step Forward in Multimodal LLM Alignment MM-RLHF：通过人类偏好对齐，显著提升多模态大语言模型性能 RLHF large language model multimodal
22 Probabilistic Lexical Manifold Construction in Large Language Models via Hierarchical Vector Field Interpolation 提出基于分层向量场插值的概率词汇流形构建方法，提升大语言模型词嵌入的语义连贯性。 representation learning large language model
23 EmbBERT-Q: Breaking Memory Barriers in Embedded NLP EmbBERT-Q：突破嵌入式NLP的内存壁垒，专为资源受限设备设计。 Mamba large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页