cs.CL（2025-06-25）

📊 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) (17 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering 提出MultiFinRAG以解决金融问答中的多模态推理问题 large language model multimodal
2 COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees 提出COIN框架以解决基础模型的不确定性量化问题 foundation model multimodal
3 Multi-lingual Functional Evaluation for Large Language Models 提出多语言功能评估基准以提升大语言模型的评估准确性 large language model instruction following
4 Enhancing Large Language Models through Structured Reasoning 通过结构化推理增强大型语言模型的推理能力 large language model
5 How to Retrieve Examples in In-context Learning to Improve Conversational Emotion Recognition using Large Language Models? 提出基于示例检索的情感识别方法以提升对话情感识别性能 large language model
6 GPTailor: Large Language Model Pruning Through Layer Cutting and Stitching 提出GPTailor以解决大语言模型压缩问题 large language model ✅
7 ChatGPT is not A Man but Das Man: Representativeness and Structural Consistency of Silicon Samples Generated by Large Language Models 提出准确性优化假设以解决LLM在民意调查中的代表性问题 large language model
8 Narrative Shift Detection: A Hybrid Approach of Dynamic Topic Models and Large Language Models 提出动态主题模型与大语言模型结合以检测叙事转变 large language model
9 A Multi-Pass Large Language Model Framework for Precise and Efficient Radiology Report Error Detection 提出三次通道大型语言模型框架以提升放射学报告错误检测精度 large language model
10 Memento: Note-Taking for Your Future Self 提出Memento以解决多跳问答中的推理与检索问题 large language model chain-of-thought
11 The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas 揭示LLM生成研究创意与人类创意执行结果的差距 large language model
12 Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes 通过行为情景分析揭示大型语言模型中的隐藏暴力倾向 large language model
13 When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs 提出多语言LLM推理计算扩展策略以提升性能 large language model
14 The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers 提出高级证据检索方法以解决科学事实核查的复杂性问题 multimodal
15 Probing AI Safety with Source Code 提出Code of Thought评估LLM安全性问题 large language model
16 TAPS: Tool-Augmented Personalisation via Structured Tagging 提出TAPS以解决个性化工具使用不足问题 large language model
17 A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs 提出STReason框架以解决多任务推理与复杂长形式推理问题 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🔗⭐
18 AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control 提出AALC以解决大型推理模型效率低下问题 reinforcement learning large language model chain-of-thought
19 OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling 提出OctoThinker以提升强化学习模型的可扩展性 reinforcement learning foundation model chain-of-thought
20 ReCode: Updating Code API Knowledge with Reinforcement Learning 提出ReCode框架以解决LLMs在API更新中的适应性问题 reinforcement learning large language model ✅
21 SEED: A Structural Encoder for Embedding-Driven Decoding in Time Series Prediction with LLMs 提出SEED以解决多变量时间序列预测中的结构与语义建模问题 representation learning large language model
22 DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation 提出DiffuCoder以提升代码生成的去噪效率 reinforcement learning large language model ✅
23 Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder 提出语义表示学习以弥合组合与分布语义的差距 representation learning VQ-VAE

⬅️ 返回 cs.CL 首页 · 🏠 返回主页