cs.CL（2024-12-31）

📊 共 24 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) (20 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansion 提出LUSAR列表排序方法，提升多模态大语言模型在多模态实体集合扩展任务中的性能。 large language model multimodal
2 Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices 提出SELLM框架，利用大语言模型生成跨学科专家知识，解决电子设备开发难题 large language model
3 Efficient Standardization of Clinical Notes using Large Language Models 利用大型语言模型高效标准化临床笔记，提升数据质量与互操作性 large language model
4 LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models LLM-MedQA：利用LLM案例研究增强医疗问答系统性能 large language model
5 An Empirical Evaluation of Large Language Models on Consumer Health Questions 评估大型语言模型在消费者健康问题解答中的表现，揭示其潜力和局限性。 large language model
6 Setting Standards in Turkish NLP: TR-MMLU for Large Language Model Evaluation 提出TR-MMLU基准以解决土耳其NLP评估问题 large language model
7 A review of faithfulness metrics for hallucination assessment in Large Language Models 综述：评估大型语言模型幻觉现象的忠实度指标研究 large language model
8 RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions RAG-Instruct：通过多样化检索增强指令提升大型语言模型能力 large language model ✅
9 GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression GRASP：通过自适应奇异参数替换冗余层，实现高效LLM压缩 large language model
10 AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects AraSTEM：用于评估LLM在STEM学科知识的阿拉伯语多选题基准 large language model
11 Superposition in Transformers: A Novel Way of Building Mixture of Experts 提出Transformer叠加方法，缓解LLM微调中的灾难性遗忘问题 large language model
12 TinyHelen's First Curriculum: Training and Evaluating Tiny Language Models in a Simpler Language Environment TinyHelen：在简化语言环境中训练和评估小型语言模型，提升学习效率。 instruction following ✅
13 Chunk-Distilled Language Modeling 提出Chunk-Distilled LM，通过检索式生成多token文本块，提升LLM效率与可控性。 large language model
14 Exploring Variability in Fine-Tuned Models for Text Classification with DistilBERT 研究DistilBERT微调策略中超参数对文本分类模型性能的影响 large language model
15 Enhancing LLM Reasoning with Multi-Path Collaborative Reactive and Reflection agents 提出RR-MP框架，利用多路径协作反应与反思Agent增强LLM的推理能力 large language model
16 MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation 提出MAIN-RAG，利用多Agent协同过滤提升检索增强生成质量，无需训练。 large language model
17 LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts LLM-Rubric：一种多维度、校准的方法，用于自然语言文本的自动评估。 large language model
18 Echoes in AI: Quantifying lack of plot diversity in LLM outputs 提出Sui Generis指标，量化评估大语言模型生成故事中情节元素的多样性不足问题。 large language model
19 Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking 系统性评估结构化知识提示的泛化性，并提出SUBARU基准 large language model
20 Zero-Shot Strategies for Length-Controllable Summarization 提出零样本长度可控摘要策略，提升LLaMA 3在无微调下的长度控制精度 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
21 An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems 利用大型语言模型生成开放性问题解决方案的综述与讨论 reinforcement learning large language model
22 Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective 揭示LLM价值观的潜在因果结构，并提出轻量级价值观引导方法 reinforcement learning RLHF large language model
23 Loss-Aware Curriculum Learning for Chinese Grammatical Error Correction 提出一种损失感知的课程学习框架，用于提升中文语法纠错性能。 curriculum learning

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
24 MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models 提出MapEval基准，评估大模型在地理空间推理中的能力。 spatial relationship foundation model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页