cs.CL（2025-04-23）

📊 共 32 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (9 🔗3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 Can Large Language Models Help Multimodal Language Analysis? MMLA: A Comprehensive Benchmark 提出MMLA基准，评估多模态大语言模型在多模态语言理解中的认知语义能力。 large language model multimodal ✅
2 Design and Application of Multimodal Large Language Model Based System for End to End Automation of Accident Dataset Generation 提出基于多模态大语言模型的端到端系统，实现交通事故数据集的自动化生成。 large language model multimodal
3 GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning GreenMind：面向结构化和逻辑推理的下一代越南语大型语言模型 large language model chain-of-thought
4 Param$Δ$ for Direct Weight Mixing: Post-Train Large Language Model at Zero Cost 提出ParamΔ，实现零成本迁移后训练知识到新版大语言模型 large language model instruction following
5 Tracing Thought: Using Chain-of-Thought Reasoning to Identify the LLM Behind AI-Generated Text 提出COT Fine-tuned框架，用于检测AI生成文本并识别生成模型的LLM chain-of-thought
6 Do Large Language Models know who did what to whom? 研究表明大型语言模型虽能提取语义角色，但其表征受句法影响大于语义。 large language model
7 How Effective are Generative Large Language Models in Performing Requirements Classification? 评估生成式大语言模型在需求分类任务中的有效性 large language model
8 UrbanPlanBench: A Comprehensive Urban Planning Benchmark for Evaluating Large Language Models UrbanPlanBench：一个用于评估大型语言模型在城市规划领域能力的综合基准 large language model ✅
9 Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries: A Pilot Study 对比大型语言模型与传统机器翻译工具在医疗咨询摘要翻译中的性能 large language model
10 EMRModel: A Large Language Model for Extracting Medical Consultation Dialogues into Structured Medical Records EMRModel：一种用于将医疗咨询对话抽取为结构化病历的大语言模型 large language model
11 Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Case Study 提出化学领域多跳推理基准，评估大型语言模型的复杂推理能力 large language model
12 Durghotona GPT: A Web Scraping and Large Language Model Based Framework to Generate Road Accident Dataset Automatically in Bangladesh Durghotona GPT：基于网络爬取和LLM的孟加拉国道路交通事故数据集自动生成框架 large language model
13 Out-of-the-Box Conditional Text Embeddings from Large Language Models 提出PonTE：一种利用大语言模型生成无监督条件文本嵌入的方法 large language model
14 A Post-trainer's Guide to Multilingual Training Data: Uncovering Cross-lingual Transfer Dynamics 揭示多语言训练数据中的跨语言迁移动态，为后训练提供指导。 large language model instruction following
15 Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control 提出基于表征工程的LLM审查控制方法，揭示并操控模型“思想” large language model ✅
16 Testing Conviction: An Argumentative Framework for Measuring LLM Political Stability 提出论证框架Testing Conviction，评估LLM政治立场的稳定性，区分真实立场与表演性文本生成。 large language model
17 Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation 提出语义对齐词汇适配(SAVA)方法，优化LLM意大利语处理，提升效率并降低token冗余。 large language model
18 IberBench: LLM Evaluation on Iberian Languages IberBench：伊比利亚语言LLM综合评测基准，解决非英语语言评测数据匮乏问题。 large language model
19 MOOSComp: Improving Lightweight Long-Context Compressor via Mitigating Over-Smoothing and Incorporating Outlier Scores MOOSComp：通过缓解过平滑和引入异常值评分，改进轻量级长文本压缩 large language model
20 HEMA : A Hippocampus-Inspired Extended Memory Architecture for Long-Context AI Conversations HEMA：一种受海马体启发的扩展记忆架构，用于长程AI对话 large language model
21 Creating and Evaluating Code-Mixed Nepali-English and Telugu-English Datasets for Abusive Language Detection Using Traditional and Deep Learning Models 构建尼泊尔语-英语和泰卢固语-英语混合语数据集，用于检测辱骂性语言 large language model
22 QuaDMix: Quality-Diversity Balanced Data Selection for Efficient LLM Pretraining QuaDMix：面向高效LLM预训练的质量-多样性平衡数据选择框架 large language model
23 Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions 提出Text-to-TrajVis任务，实现自然语言到轨迹数据可视化的转换。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
24 Co-CoT: A Prompt-Based Framework for Collaborative Chain-of-Thought Reasoning 提出Co-CoT框架，通过可交互的思维链推理提升AI透明度和用户参与度 preference learning chain-of-thought
25 Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning 提出基于Text2SQL强化学习的表格推理方法，提升LLM在结构化数据上的推理能力。 reinforcement learning large language model chain-of-thought
26 Monte Carlo Planning with Large Language Model for Text-Based Game Agents 提出MC-DML算法，利用大语言模型进行文本游戏智能体蒙特卡洛规划 reinforcement learning large language model
27 WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model WebEvolver：通过共进化世界模型增强Web Agent的自我改进能力 world model distillation large language model ✅
28 Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification Emo Pillars：知识蒸馏支持细粒度上下文感知和无上下文情感分类 distillation large language model
29 SplitReason: Learning To Offload Reasoning SplitReason：通过学习卸载推理任务提升大语言模型效率与精度。 reinforcement learning large language model chain-of-thought
30 PIS: Linking Importance Sampling and Attention Mechanisms for Efficient Prompt Compression 提出PIS：结合重要性采样与注意力机制的高效Prompt压缩框架 reinforcement learning large language model
31 LLMSR@XLLM25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation 提出基于质量引导蒸馏的结构化多智能体推理方法，提升低资源场景性能 distillation ✅
32 AdaParse: An Adaptive Parallel PDF Parsing and Resource Scaling Engine AdaParse：自适应并行PDF解析与资源调度引擎，提升科学文档处理效率。 DPO direct preference optimization ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页