cs.CL（2024-07-25）

📊 共 21 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) (19 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2)

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

#题目一句话要点标签🔗⭐
1 Dallah: A Dialect-Aware Multimodal Large Language Model for Arabic Dallah：一种面向阿拉伯语方言的多模态大型语言模型 large language model multimodal
2 I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition 评估双塔多模态系统在乐器识别中的性能，揭示文本编码器的局限性。 multimodal
3 An Efficient Inference Framework for Early-exit Large Language Models 针对Early-exit LLM，提出高效推理框架，加速迭代级批处理与KV缓存管理。 large language model
4 Demystifying Verbatim Memorization in Large Language Models 通过可控实验揭示大语言模型逐字记忆的内在机制与挑战 large language model
5 Closing the gap between open-source and commercial large language models for medical evidence summarization 通过微调开源大语言模型，提升医疗证据总结性能至可与商业模型媲美 large language model
6 Examining the Influence of Political Bias on Large Language Model Performance in Stance Classification 研究表明大型语言模型在立场分类任务中受政治偏见影响，数据集层面差异显著。 large language model
7 Know Your Limits: A Survey of Abstention in Large Language Models 大型语言模型拒答（Abstention）综述：应对幻觉与提升安全性的新视角 large language model
8 Exploring Bengali Religious Dialect Biases in Large Language Models with Evaluation Perspectives 评估大型语言模型在孟加拉语宗教方言上的偏见 large language model
9 GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy GermanPartiesQA：评估商业大语言模型在政治立场和谄媚行为上的表现 large language model
10 Are Large Language Models Possible to Conduct Cognitive Behavioral Therapy? 评估大型语言模型在认知行为疗法中的应用潜力与局限性 large language model
11 PEFT-U: Parameter-Efficient Fine-Tuning for User Personalization 提出PEFT-U基准，用于高效微调LLM以实现用户个性化。 large language model foundation model
12 Multi-group Uncertainty Quantification for Long-form Text Generation 针对长文本生成，提出多组不确定性量化方法以提升子群体内的校准性和可靠性。 large language model
13 Robust Claim Verification Through Fact Detection 提出FactDetect，通过从证据中提取事实增强声明验证的鲁棒性和推理能力。 large language model
14 Difficulty Estimation and Simplification of French Text Using LLMs 利用大型语言模型进行法语文本难度评估与简化 large language model
15 Keep the Cost Down: A Review on Methods to Optimize LLM' s KV-Cache Consumption 综述LLM KV-Cache优化方法，降低长文本处理的GPU内存消耗 large language model ✅
16 What does Kiki look like? Cross-modal associations between speech sounds and visual shapes in vision-and-language models 探究视觉-语言模型中的跨模态联想：Bouba-Kiki效应的分析 multimodal
17 Vision-Language Models Align with Human Neural Representations in Concept Processing 研究表明视觉-语言模型在概念处理中与人类神经表征对齐 multimodal ✅
18 factgenie: A Framework for Span-based Evaluation of Generated Texts FactGenie：一个用于生成文本中基于Span评估的框架 large language model
19 S2-Attention: Hardware-Aware Context Sharding Among Attention Heads 提出S2-Attention，通过硬件感知的上下文分片优化稀疏注意力，提升LLM推理效率。 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🔗⭐
20 Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning 提出基于直接偏好优化的自训练方法，提升小规模语言模型的思维链推理能力 preference learning DPO direct preference optimization
21 Banyan: Improved Representation Learning with Explicit Structure Banyan：利用显式结构改进表征学习，适用于低资源场景 representation learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页