cs.CL（2025-05-06）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (14) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models 提出LS-Mixture SFT，解决SFT微调中LLM的过度推理问题，提升推理效率。 large language model chain-of-thought
2 Advancing Conversational Diagnostic AI with Multimodal Reasoning AMIE：基于多模态推理提升对话式诊断AI的性能 large language model multimodal
3 SLOT: Structuring the Output of Large Language Models SLOT：通过后处理转换LLM输出为结构化格式，提升下游任务可靠性 large language model
4 Scientific Hypothesis Generation and Validation: Methods, Datasets, and Future Directions 综述：大型语言模型驱动的科学假设生成与验证方法 large language model multimodal symbolic grounding
5 MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks MedArabiQ：构建阿拉伯语医疗任务基准，评估并提升LLM在医疗领域的应用。 large language model
6 TeleEval-OS: Performance evaluations of large language models for operations scheduling TeleEval-OS：首个面向电信运营调度的LLM性能评估基准 large language model
7 Integration of Large Language Models and Traditional Deep Learning for Social Determinants of Health Prediction 结合大语言模型与传统深度学习，用于预测健康的社会决定因素 large language model
8 BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models 提出BadLingual，一种针对大型语言模型的任务无关的语言后门攻击。 large language model
9 Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis ConfiDx：面向可解释疾病诊断的、能感知不确定性的大语言模型 large language model
10 Lightweight Clinical Decision Support System using QLoRA-Fine-Tuned LLMs and Retrieval-Augmented Generation 提出基于QLoRA微调LLaMA 3.2-3B和RAG的轻量级临床决策支持系统 large language model foundation model
11 Faster MoE LLM Inference for Extremely Large Models 针对超大MoE LLM，提出更快速的推理方法，提升效率并优化性能。 large language model
12 A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient 提出相对危险系数RDC，用于比较评估不同LLM的伦理和安全差距 large language model
13 Say It Another Way: Auditing LLMs with a User-Grounded Automated Paraphrasing Framework AUGMENT：一种用户行为驱动的LLM自动复述框架，用于可靠的审计。 large language model
14 Ψ-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback 提出Ψ-Arena，通过三方反馈交互式评估和优化基于LLM的心理咨询师。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
15 Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation 提出基于思维链蒸馏的Recall with Reasoning方法，提升Mamba在长文本上的记忆和外推能力 Mamba distillation chain-of-thought
16 SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation SepALM：利用音频语言模型进行错误纠正，提升语音分离的鲁棒性 distillation large language model chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页