cs.CL（2024-05-01）

📊 共 20 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) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 NumLLM: Numeric-Sensitive Large Language Model for Chinese Finance 提出NumLLM，提升中文金融大模型对数值变量的理解能力 large language model foundation model
2 Math Multiple Choice Question Generation via Human-Large Language Model Collaboration 提出人机协作工具，利用大语言模型辅助生成高质量数学选择题 large language model
3 When Quantization Affects Confidence of Large Language Models? 研究量化对大语言模型置信度的影响，揭示低置信度样本更易受损 large language model
4 Investigating Automatic Scoring and Feedback using Large Language Models 利用PEFT微调量化LLaMA-2模型，实现低成本、低延迟的自动评分与反馈生成。 large language model
5 New Benchmark Dataset and Fine-Grained Cross-Modal Fusion Framework for Vietnamese Multimodal Aspect-Category Sentiment Analysis 提出ViMACSA数据集与FCMF框架，用于细粒度越南语多模态情感分析。 multimodal ✅
6 DAM: A Universal Dual Attention Mechanism for Multimodal Timeseries Cryptocurrency Trend Forecasting 提出一种用于多模态时间序列加密货币趋势预测的通用双重注意力机制（DAM）。 multimodal
7 Is Temperature the Creativity Parameter of Large Language Models? 研究表明温度参数与大语言模型创造力的相关性弱，并非直接的“创造力参数”。 large language model
8 BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine 提出BiomedRAG，通过检索增强LLM解决生物医学领域知识更新和幻觉问题。 large language model
9 CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models 提出CofiPara框架，利用大模型进行粗到细的多模态讽刺目标识别 multimodal
10 Extracting chemical food safety hazards from the scientific literature automatically using large language models 利用大型语言模型自动从科学文献中提取食品安全化学危害 large language model
11 AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts AdaMoLE：自适应混合低秩适配专家微调大型语言模型 large language model
12 A Careful Examination of Large Language Model Performance on Grade School Arithmetic GSM1k：小学算术LLM基准测试，揭示数据集污染与过拟合问题 large language model
13 WIBA: What Is Being Argued? A Comprehensive Approach to Argument Mining WIBA：提出一个综合框架，用于全面理解跨语境的论证挖掘 large language model
14 "Ask Me Anything": How Comcast Uses LLMs to Assist Agents in Real Time Comcast利用大型语言模型AMA实时辅助客服，提升效率并降低成本 large language model
15 Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3 研究表明：针对Llama-3的模型编辑中，增大编辑批量大小可能适得其反 large language model
16 Are Models Biased on Text without Gender-related Language? 提出UnStereoEval框架，揭示语言模型在非刻板文本中仍存在的性别偏见 large language model ✅
17 Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment 提出MoTE框架，结合推理链与专家混合模型，提升LLM的自对齐能力 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🔗⭐
18 Addressing Topic Granularity and Hallucination in Large Language Models for Topic Modelling 提出基于DPO微调的LLM主题建模方法，解决主题粒度和幻觉问题 DPO large language model
19 The Real, the Better: Aligning Large Language Models with Online Human Behaviors 提出RLHB框架，利用在线人类行为对大型语言模型进行对齐。 reinforcement learning large language model
20 Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models 提出自精炼指令调优方法，提升小模型推理能力并对齐大模型 direct preference optimization large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页