cs.CL（2025-05-09）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Is your multimodal large language model a good science tutor? 提出基于教育评估指标和模拟学生的MLLM科学辅导能力评估与优化框架 large language model multimodal
2 Efficient Fairness Testing in Large Language Models: Prioritizing Metamorphic Relations for Bias Detection 提出基于变形关系的LLM公平性高效测试方法，提升偏差检测效率。 large language model
3 TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries 提出TopicVD数据集，用于纪录片视频引导的多模态机器翻译研究。 multimodal ✅
4 Estimating Quality in Therapeutic Conversations: A Multi-Dimensional Natural Language Processing Framework 提出一种多维度NLP框架，用于评估心理治疗对话质量，提升治疗效果。 multimodal
5 A Scaling Law for Token Efficiency in LLM Fine-Tuning Under Fixed Compute Budgets 提出一种考虑数据构成的LLM微调缩放律，提升固定计算资源下的token效率。 large language model
6 LLMs Get Lost In Multi-Turn Conversation 揭示LLM在多轮对话中性能显著下降的问题，并分析其原因。 large language model
7 Summarisation of German Judgments in conjunction with a Class-based Evaluation 提出一种结合法律实体信息的微调语言模型，用于生成德国判决书摘要。 large language model
8 Full-Parameter Continual Pretraining of Gemma2: Insights into Fluency and Domain Knowledge 通过全参数持续预训练Gemma2提升立陶宛语能力并保持领域知识 large language model ✅
9 Tell Me Who Your Students Are: GPT Can Generate Valid Multiple-Choice Questions When Students' (Mis)Understanding Is Hinted AnaQuest：利用学生理解偏差提示GPT生成高质量多选题 large language model
10 Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM 提出STARC，一种基于聚类的稀疏注意力重映射方法，用于PIM上高效LLM解码。 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🔗⭐
11 Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications MINT：通过偏好优化实现多模态知识迁移到大语言模型，应用于生物医学领域 DPO large language model foundation model
12 Multimodal Sentiment Analysis on CMU-MOSEI Dataset using Transformer-based Models 提出基于Transformer的早期融合模型，用于CMU-MOSEI数据集上的多模态情感分析。 MAE multimodal
13 Assessing Robustness to Spurious Correlations in Post-Training Language Models 评估后训练语言模型对虚假相关性的鲁棒性 DPO direct preference optimization large language model
14 Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillation Unilogit：一种基于均匀目标自蒸馏的LLM稳健机器遗忘方法 distillation large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 Insertion Language Models: Sequence Generation with Arbitrary-Position Insertions 提出插入语言模型（ILM），通过任意位置插入生成序列，提升规划任务性能。 MDM

⬅️ 返回 cs.CL 首页 · 🏠 返回主页