cs.CL（2025-03-26）

📊 共 28 篇论文 | 🔗 8 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) (5 🔗3) 支柱六：视频提取与匹配 (Video Extraction) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Qwen2.5-Omni Technical Report Qwen2.5-Omni：提出Thinker-Talker架构，实现端到端多模态流式生成文本与语音 large language model multimodal instruction following
2 Refining Time Series Anomaly Detectors using Large Language Models 利用多模态大语言模型优化时间序列异常检测，减少人工干预 large language model multimodal
3 ADS-Edit: A Multimodal Knowledge Editing Dataset for Autonomous Driving Systems 提出ADS-Edit：面向自动驾驶系统的多模态知识编辑数据集 multimodal ✅
4 Susceptibility of Large Language Models to User-Driven Factors in Medical Queries 研究表明大型语言模型在医疗问询中易受用户因素影响，尤其对误导信息敏感 large language model
5 Can Large Language Models Predict Associations Among Human Attitudes? GPT-4o能预测人类态度间的关联，揭示潜在信念结构 large language model
6 Iterative Prompting with Persuasion Skills in Jailbreaking Large Language Models 提出迭代提示攻击方法，利用说服技巧提升大语言模型越狱成功率 large language model
7 Evaluating Large Language Models for Automated Clinical Abstraction in Pulmonary Embolism Registries: Performance Across Model Sizes, Versions, and Parameters 利用大型语言模型自动化肺栓塞登记研究中的临床信息抽取，实现数据质量保障。 large language model
8 GatedxLSTM: A Multimodal Affective Computing Approach for Emotion Recognition in Conversations 提出GatedxLSTM模型，用于会话情感识别中的多模态情感计算，提升性能与可解释性。 multimodal
9 From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models 针对LLM在ABSA中隐式方面提取的评估，提出新指标并使用合成数据进行适配。 large language model
10 3MDBench: Medical Multimodal Multi-agent Dialogue Benchmark 提出3MDBench：用于评估医疗多模态多智能体对话的基准测试框架。 multimodal ✅
11 Enhancing Finite State Machine Design Automation with Large Language Models and Prompt Engineering Techniques 利用大型语言模型和提示工程提升有限状态机设计自动化 large language model
12 InfoBid: A Simulation Framework for Studying Information Disclosure in Auctions with Large Language Model-based Agents InfoBid：一个基于LLM智能体的拍卖信息披露策略仿真框架 large language model
13 StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs 提出MirrorAPI，模拟7000+真实API环境，提升工具学习基准测试的稳定性与真实性。 large language model chain-of-thought
14 ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction ScreenLLM：用于高效动作理解与预测的状态化屏幕模式 large language model multimodal
15 SARGes: Semantically Aligned Reliable Gesture Generation via Intent Chain 提出SARGes框架以解决语音同步手势生成问题 large language model
16 Patients Speak, AI Listens: LLM-based Analysis of Online Reviews Uncovers Key Drivers for Urgent Care Satisfaction 利用LLM分析在线评论，揭示影响急诊医疗满意度的关键因素 large language model
17 Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark 提出Mobile-MMLU，用于评估LLM在移动设备上的智能语言理解能力 large language model ✅
18 Collaborative Storytelling and LLM: A Linguistic Analysis of Automatically-Generated Role-Playing Game Sessions 通过语言学分析，揭示LLM在自动生成角色扮演游戏会话中的独特语言模式 large language model
19 sudo rm -rf agentic_security 提出SUDO框架，针对计算机代理的拒绝训练安全防护进行有效攻击 large language model
20 Advancements in Natural Language Processing: Exploring Transformer-Based Architectures for Text Understanding 探索Transformer架构在文本理解中的应用，提升NLP性能 multimodal
21 Leveraging Implicit Sentiments: Enhancing Reliability and Validity in Psychological Trait Evaluation of LLMs 提出CSI量表，用于更可靠、有效地评估大型语言模型的情感倾向。 large language model ✅
22 Hacia la interpretabilidad de la detección anticipada de riesgos de depresión utilizando grandes modelos de lenguaje 利用大语言模型与可解释推理，解决西班牙语抑郁风险早期检测问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
23 Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models 提出Re4优化的CBR系统，利用大语言模型生成功能测试脚本。 reinforcement learning large language model
24 Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach 提出多目标GRPO框架，优化语言模型安全性和对齐，降低计算成本。 reinforcement learning PPO RLHF ✅
25 ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models 提出ENCORE，通过熵引导的多头奖励组合提升LLM安全对齐效果 reinforcement learning RLHF large language model
26 GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization 提出GAPO，通过生成对抗策略优化学习偏好提示，提升LLM细粒度约束控制能力 PPO DPO large language model ✅
27 Unlocking Efficient Long-to-Short LLM Reasoning with Model Merging 提出基于模型融合的L2S推理方法，提升LLM推理效率并保持性能。 reinforcement learning 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🔗⭐
28 CFunModel: A "Funny" Language Model Capable of Chinese Humor Generation and Processing 提出CFunModel，首个面向中文幽默生成与处理的大语言模型 HuMoR large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页