cs.CL（2024-09-04）

📊 共 22 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark MMMU-Pro：更鲁棒的多学科多模态理解评测基准 multimodal chain-of-thought
2 CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models 发布中文多模态数学数据集CMM-Math，用于评估和提升大模型数学推理能力。 large language model multimodal
3 PUB: Plot Understanding Benchmark and Dataset for Evaluating Large Language Models on Synthetic Visual Data Interpretation 提出PUB：用于评估大语言模型在合成视觉数据理解能力上的基准数据集 large language model multimodal
4 CLUE: Concept-Level Uncertainty Estimation for Large Language Models 提出概念级不确定性估计CLUE，提升LLM生成结果的可解释性与可靠性 large language model
5 Exploring Sentiment Dynamics and Predictive Behaviors in Cryptocurrency Discussions by Few-Shot Learning with Large Language Models 利用GPT-4o进行加密货币讨论的情感动态与预测行为分析 large language model
6 More is More: Addition Bias in Large Language Models 揭示大语言模型中的加法偏见：倾向于添加而非删除修改 large language model
7 Do Large Language Models Possess Sensitive to Sentiment? 评估大型语言模型的情感感知能力，揭示其在情感理解上的局限性 large language model
8 Detecting Calls to Action in Multimodal Content: Analysis of the 2021 German Federal Election Campaign on Instagram 利用BERT和GPT-4自动检测社交媒体行动呼吁，分析德国联邦选举Instagram活动 multimodal
9 A Comparative Study on Large Language Models for Log Parsing 对比研究大型语言模型在日志解析任务中的性能，发现开源模型可与商业模型媲美。 large language model
10 How Privacy-Savvy Are Large Language Models? A Case Study on Compliance and Privacy Technical Review 评估大语言模型在隐私合规性方面的能力，并提出隐私技术审查框架。 large language model
11 Prompt Baking Prompt Baking：将Prompt信息烘焙到LLM权重中，提升零样本性能并更新模型知识。 instruction following chain-of-thought
12 Language is Scary when Over-Analyzed: Unpacking Implied Misogynistic Reasoning with Argumentation Theory-Driven Prompts 利用论证理论驱动的提示，揭示大型语言模型在分析中隐含的厌女推理 large language model chain-of-thought
13 Deconfounded Causality-aware Parameter-Efficient Fine-Tuning for Problem-Solving Improvement of LLMs 提出解混因果自适应（DCA）方法，提升LLM在问题解决中的推理能力 large language model
14 ISO: Overlap of Computation and Communication within Seqenence For LLM Inference 提出序列级计算通信重叠方法ISO，提升LLM推理效率 large language model
15 Well, that escalated quickly: The Single-Turn Crescendo Attack (STCA) 提出单轮渐强攻击(STCA)，通过单次交互绕过LLM内容审查，引发有害响应。 large language model
16 Historical German Text Normalization Using Type- and Token-Based Language Modeling 提出一种结合类型和Token的Transformer语言模型，用于历史德语文本规范化。 large language model
17 Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models? 针对LLM嵌入模型，研究Pooling和Attention的有效设计方案，并提出多层可训练Pooling方法。 large language model
18 DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels 提出DetectiveQA数据集，用于评估LLM在侦探小说长文本推理中的能力。 large language model
19 STAB: Speech Tokenizer Assessment Benchmark 提出STAB：语音Tokenizer评估基准，用于全面评估和理解语音Tokenizer的特性。 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🔗⭐
20 Towards a Unified View of Preference Learning for Large Language Models: A Survey 对大型语言模型偏好学习的统一视角综述：解构对齐策略并建立联系 preference learning large language model
21 "Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation 提出LoRD：通过局部性强化蒸馏引导语言模型抽取，提升攻击性能。 distillation large language model ✅
22 LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architecture LongLLaVA：通过混合架构高效扩展多模态LLM至处理千张图像 Mamba large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页