cs.CL（2024-05-17）

📊 共 24 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 From Generalist to Specialist: Improving Large Language Models for Medical Physics Using ARCoT ARCoT框架提升大语言模型在医学物理领域的专业性能 large language model chain-of-thought
2 A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers 综述多语言大语言模型：最新进展与未来方向 large language model
3 COGNET-MD, an evaluation framework and dataset for Large Language Model benchmarks in the medical domain COGNET-MD：医学领域大语言模型评估框架与数据集 large language model
4 Assessing Political Bias in Large Language Models 评估大型语言模型中的政治偏见，揭示其对欧盟选举的影响 large language model
5 Realistic Evaluation of Toxicity in Large Language Models 提出TET数据集，用于更真实地评估大型语言模型中的毒性问题 large language model
6 Benchmarking Large Language Models on CFLUE -- A Chinese Financial Language Understanding Evaluation Dataset 提出CFLUE：一个中文金融语言理解评估基准，用于全面评估大型语言模型。 large language model ✅
7 ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios ActiveLLM：基于大语言模型的文本少样本主动学习方法 large language model
8 Layer-Condensed KV Cache for Efficient Inference of Large Language Models 提出层压缩KV缓存，显著提升大语言模型推理效率。 large language model ✅
9 Dynamic data sampler for cross-language transfer learning in large language models 提出ChatFlow，一种基于跨语言迁移学习的动态数据采样中文LLM训练方法 large language model
10 Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization 提出基于自适应特征的低秩压缩方法，用于高效压缩大型语言模型。 large language model
11 A Hard Nut to Crack: Idiom Detection with Conversational Large Language Models 提出IdioTS数据集，评估大型语言模型在成语检测任务中的能力 large language model
12 Adaptable and Reliable Text Classification using Large Language Models 提出一种基于大语言模型的可适应、高可靠文本分类范式，简化传统流程。 large language model ✅
13 CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawl 提出CC-GPX，从Common Crawl中提取高质量带标注的地理空间数据。 large language model multimodal ✅
14 Language Models can Evaluate Themselves via Probability Discrepancy 提出ProbDiff，利用LLM自身概率差异进行自评估，无需外部模型。 large language model
15 AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations 提出AudioSetMix，利用LLM增强音频-语言数据集，提升模型性能。 large language model
16 Prompt Exploration with Prompt Regression 提出PEPR框架，通过提示回归预测提示组合效果，提升大语言模型提示工程效率。 large language model
17 SBAAM! Eliminating Transcript Dependency in Automatic Subtitling SBAAM：提出一种无需中间转录的自动字幕生成模型，提升多语言字幕生成效果。 TAMP
18 Revolutionizing Process Mining: A Novel Architecture for ChatGPT Integration and Enhanced User Experience through Optimized Prompt Engineering 提出一种基于优化Prompt工程的ChatGPT集成架构，提升过程挖掘工具的用户体验。 large language model
19 SPOR: A Comprehensive and Practical Evaluation Method for Compositional Generalization in Data-to-Text Generation 提出SPOR，用于全面评估数据到文本生成中组合泛化能力，填补现有方法对LLM和多维度评估的不足。 large language model
20 Language Models can Exploit Cross-Task In-context Learning for Data-Scarce Novel Tasks 提出跨任务提示以解决数据稀缺的新任务问题 large language model
21 Rethinking ChatGPT's Success: Usability and Cognitive Behaviors Enabled by Auto-regressive LLMs' Prompting 分析自回归LLM提示的可用性与认知行为，揭示其成功关键 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🔗⭐
22 RDRec: Rationale Distillation for LLM-based Recommendation 提出RDRec：通过知识蒸馏提升LLM推荐模型的推理能力 distillation large language model ✅
23 INDUS: Effective and Efficient Language Models for Scientific Applications INDUS：针对科学应用的高效语言模型，优于通用和领域特定模型 contrastive learning 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🔗⭐
24 ECR-Chain: Advancing Generative Language Models to Better Emotion-Cause Reasoners through Reasoning Chains 提出ECR-Chain，通过推理链提升生成式语言模型的情感原因推理能力 motion generation ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页