cs.CL（2024-06-28）

📊 共 23 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) (20 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

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

#题目一句话要点标签🔗⭐
1 The SIFo Benchmark: Investigating the Sequential Instruction Following Ability of Large Language Models SIFo基准：评估大型语言模型在顺序指令遵循方面的能力 large language model instruction following
2 CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models CMMaTH：构建中文多模态数学能力评估基准，促进基础模型发展 large language model foundation model multimodal
3 Single Parent Family: A Spectrum of Family Members from a Single Pre-Trained Foundation Model 提出渐进式低秩分解(PLRD)方法，高效压缩并生成多种尺寸的大语言模型。 large language model foundation model
4 SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs 提出SK-VQA：大规模合成知识生成数据集，用于训练上下文增强的多模态LLM multimodal
5 ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models ToolBeHonest：一个用于工具增强大语言模型的多层次幻觉诊断基准 large language model
6 EHRmonize: A Framework for Medical Concept Abstraction from Electronic Health Records using Large Language Models EHRmonize：利用大语言模型从电子病历中提取医学概念，提升数据整合效率。 large language model
7 LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models 提出LEMoe以解决大型语言模型的终身编辑问题 large language model
8 Simulating Financial Market via Large Language Model based Agents 提出基于大语言模型Agent的金融市场模拟器ASFM，用于经济研究。 large language model
9 Belief Revision: The Adaptability of Large Language Models Reasoning 提出Belief-R数据集与Delta推理框架，评估大语言模型在信息演变下的信念修正能力 large language model
10 Can GPT-4 Help Detect Quit Vaping Intentions? An Exploration of Automatic Data Annotation Approach 利用GPT-4检测戒电子烟意图：一种自动数据标注方法探索 large language model chain-of-thought
11 From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models 提出GlobalRG基准，评估视觉-语言模型在多文化理解上的能力 visual grounding
12 SMLT-MUGC: Small, Medium, and Large Texts -- Machine versus User-Generated Content Detection and Comparison SMLT-MUGC：基于文本长度的机器与用户生成内容检测及对比研究 large language model
13 Scaling Synthetic Data Creation with 1,000,000,000 Personas 提出Persona Hub，利用十亿级Persona驱动LLM生成多样化合成数据 large language model
14 Evaluating Human Alignment and Model Faithfulness of LLM Rationale 评估LLM推理的对齐性和忠实性：提示 vs. 归因方法 large language model
15 AnomaLLMy -- Detecting anomalous tokens in black-box LLMs through low-confidence single-token predictions AnomaLLMy：通过低置信度单token预测检测黑盒LLM中的异常token large language model
16 ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation ITERTL：一种迭代框架，用于微调LLM以生成RTL代码 large language model
17 Calibrating LLMs with Preference Optimization on Thought Trees for Generating Rationale in Science Question Scoring 提出基于思维树偏好优化的LLM校准方法，提升科学问题评分中推理生成质量。 large language model ✅
18 NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations NLPerturbator：研究代码大语言模型对自然语言变体的鲁棒性 large language model
19 Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation 提出KELLER以解决法律案例检索中的知识缺失问题 large language model
20 Mixture of In-Context Experts Enhance LLMs' Long Context Awareness 提出MoICE，增强LLM在长文本中对不同位置信息的感知能力 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🔗⭐
21 Direct Preference Knowledge Distillation for Large Language Models 提出直接偏好知识蒸馏(DPKD)方法，提升大语言模型蒸馏效率与精度。 distillation large language model
22 YuLan: An Open-source Large Language Model 发布开源120亿参数大语言模型YuLan，提供完整训练细节助力研究。 curriculum learning large language model ✅

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

#题目一句话要点标签🔗⭐
23 Into the Unknown: Generating Geospatial Descriptions for New Environments 提出基于地理空间数据增强方法，提升未知环境下的地理空间描述生成性能。 spatial relationship VLN large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页