cs.CL（2024-12-03）

📊 共 22 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) (1 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗⭐
1 Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey 针对多模态大语言模型的可解释性与可理解性，提出数据、模型、训练&推理三维框架的综合综述。 large language model multimodal
2 Single-Cell Omics Arena: A Benchmark Study for Large Language Models on Cell Type Annotation Using Single-Cell Data SOAR：单细胞组学领域大语言模型细胞类型注释的基准研究 large language model chain-of-thought
3 Enhancing Trust in Large Language Models with Uncertainty-Aware Fine-Tuning 提出不确定性感知微调方法，提升大型语言模型的可信度 large language model
4 RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models RARE：检索增强推理提升大语言模型常识与医学推理能力 large language model
5 CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels 提出CNNSum：一个基于中文小说的多尺度长文本摘要基准，用于评估和提升大型语言模型。 large language model ✅
6 An Evolutionary Large Language Model for Hallucination Mitigation 提出EvoLLMs，利用进化计算自动生成高质量QA数据集，缓解大语言模型幻觉问题 large language model
7 Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training 针对土耳其语，提出基于语料库选择和训练的新方法以优化大型语言模型 large language model
8 Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models 研究LLM自提升能力：揭示生成-验证差距与模型规模的关联 large language model
9 Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining 提出GraCeFul，无需重训练即可过滤生成式大语言模型中的后门样本。 large language model ✅
10 A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis 针对ABSA任务，论文全面评估了大语言模型在不同范式下的性能表现。 large language model
11 CPTQuant - A Novel Mixed Precision Post-Training Quantization Techniques for Large Language Models CPTQuant：一种用于大型语言模型的新型混合精度后训练量化技术 large language model
12 Leveraging Large Language Models for Comparative Literature Summarization with Reflective Incremental Mechanisms 提出ChatCite，利用大语言模型和反射增量机制进行比较文学的总结。 large language model
13 A Primer on Large Language Models and their Limitations 大型语言模型（LLM）原理、局限性及应用研究综述 large language model
14 Let's Think Var-by-Var: Large Language Models Enable Ad Hoc Probabilistic Reasoning 提出基于大语言模型的概率推理框架以解决不确定性问题 large language model
15 Removing Spurious Correlation from Neural Network Interpretations 提出因果中介方法，消除话题混淆对神经网络解释的影响 large language model
16 Minimization of Boolean Complexity in In-Context Concept Learning 研究表明LLM上下文学习能力与概念的布尔复杂度高度相关 large language model
17 Time-Reversal Provides Unsupervised Feedback to LLMs 提出时间反转语言模型以增强LLM的无监督反馈能力 large language model
18 Patent-CR: A Dataset for Patent Claim Revision 构建专利权利要求修改数据集Patent-CR，用于评估和提升LLM在专利领域的文本修订能力 large language model
19 Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity 提出PoD框架，通过层间注意力相似性压缩长文本LLM推理中的KV缓存。 large language model
20 Multi-Bin Batching for Increasing LLM Inference Throughput 提出多桶批处理方法，提升大语言模型推理吞吐量 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
21 T-REG: Preference Optimization with Token-Level Reward Regularization 提出T-REG，利用token级奖励正则化优化LLM偏好对齐，提升指令遵循能力。 reinforcement learning RLHF large language model ✅

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
22 MediaSpin: Exploring Media Bias Through Fine-Grained Analysis of News Headlines MediaSpin数据集：通过细粒度分析新闻标题探索媒体偏见。 affordance

⬅️ 返回 cs.CL 首页 · 🏠 返回主页