cs.CL（2024-11-04）

📊 共 27 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) (22 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 Context-Informed Machine Translation of Manga using Multimodal Large Language Models 提出基于多模态大语言模型的漫画机器翻译方法，提升翻译质量并构建新数据集。 large language model multimodal
2 MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs 提出MM-Embed，利用多模态LLM实现通用多模态检索，并在M-BEIR和MTEB上取得SOTA。 large language model multimodal
3 FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees FactTest：基于有限样本和无分布保证的大语言模型事实性测试框架 large language model
4 Improving Scientific Hypothesis Generation with Knowledge Grounded Large Language Models 提出KG-CoI框架，通过知识图谱增强大语言模型在科学假设生成中的准确性和可信度。 large language model
5 Evaluating Creative Short Story Generation in Humans and Large Language Models 系统分析人类与大型语言模型的短篇故事创作能力 large language model
6 Scalable Efficient Training of Large Language Models with Low-dimensional Projected Attention 提出低维投影注意力(LPA)以高效训练大规模语言模型，提升性能并加速训练。 large language model
7 Explainable cognitive decline detection in free dialogues with a Machine Learning approach based on pre-trained Large Language Models 提出一种基于预训练大语言模型的认知衰退检测方法，用于分析自由对话。 large language model
8 Zebra-Llama: A Context-Aware Large Language Model for Democratizing Rare Disease Knowledge Zebra-Llama：一种上下文感知的大语言模型，用于普及罕见病知识 large language model
9 AVSS: Layer Importance Evaluation in Large Language Models via Activation Variance-Sparsity Analysis 提出AVSS指标，通过激活方差-稀疏性分析评估大语言模型层重要性，实现模型压缩。 large language model
10 A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness 综述小语言模型（SLM）：技术、增强、应用、与LLM协作及可信赖性 large language model
11 Advancements and limitations of LLMs in replicating human color-word associations 评估LLM在复现人类颜色-词语联想方面的能力与局限性 large language model
12 Extracting Unlearned Information from LLMs with Activation Steering 提出匿名激活引导方法，从已进行知识遗忘的大语言模型中精确提取未学习信息。 large language model
13 TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network 提出TeleOracle以解决通信网络智能管理问题 large language model
14 A Comparative Analysis of Counterfactual Explanation Methods for Text Classifiers 对比分析文本分类器反事实解释方法，揭示LLM与梯度方法优劣 large language model
15 Positive Experience Reflection for Agents in Interactive Text Environments 提出Sweet&Sour方法，通过正向经验反思提升LLM Agent在交互式文本环境中的性能 large language model
16 Shortcut Learning in In-Context Learning: A Survey 综述ICL中的捷径学习：分析类型、原因、基准与缓解策略 large language model
17 Culinary Class Wars: Evaluating LLMs using ASH in Cuisine Transfer Task 提出ASH基准以评估LLMs在菜谱转移任务中的表现 large language model ✅
18 QCG-Rerank: Chunks Graph Rerank with Query Expansion in Retrieval-Augmented LLMs for Tourism Domain QCG-Rerank：面向旅游领域的检索增强LLM的块图重排序与查询扩展 large language model
19 MILU: A Multi-task Indic Language Understanding Benchmark 提出MILU：一个多任务印度语言理解基准，用于评估LLM在印度语言上的能力。 large language model
20 MdEval: Massively Multilingual Code Debugging 提出MdEval大规模多语言代码调试基准，促进代码LLM在多语言环境下的调试能力。 large language model
21 The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units 利用神经科学方法，识别LLM中与任务相关的因果语言单元 large language model
22 Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education 通过监督式微调提升LLM在计算教育中的教学效果 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
23 Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback Align-SLM：利用AI反馈强化学习提升无文本口语语言模型的语义一致性 reinforcement learning DPO direct preference optimization
24 WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning WebRL：通过自进化在线课程强化学习训练LLM Web代理 reinforcement learning large language model
25 Code-Switching Curriculum Learning for Multilingual Transfer in LLMs 提出代码切换课程学习(CSCL)方法，提升LLM多语言迁移能力。 curriculum learning large language model
26 Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control 提出稀疏激活控制方法，提升LLM在安全性、事实性和偏见等多维度的可信度。 reinforcement learning RLHF large language model
27 Grounding Emotional Descriptions to Electrovibration Haptic Signals 提出一种基于NLP的计算流程，用于将用户情感描述与电震动触觉信号关联。 predictive model PULSE

⬅️ 返回 cs.CL 首页 · 🏠 返回主页