cs.CL（2024-11-15）

📊 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) (16 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization 提出混合偏好优化(MPO)方法，提升多模态大语言模型(MLLM)的推理能力 large language model multimodal chain-of-thought
2 MLAN: Language-Based Instruction Tuning Preserves and Transfers Knowledge in Multimodal Language Models MLAN：基于语言指令微调，在多模态语言模型中保持并迁移知识 large language model multimodal instruction following
3 Measuring Non-Adversarial Reproduction of Training Data in Large Language Models 量化大型语言模型在非对抗场景下对训练数据的复现程度 large language model
4 An Effective Framework to Help Large Language Models Handle Numeric-involved Long-context Tasks 提出一种高效框架，提升大语言模型在数值型长文本任务中的表现 large language model
5 Legal Evalutions and Challenges of Large Language Models 评估大语言模型在法律领域的应用，揭示其优势与挑战 large language model
6 Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation 利用提示工程与微调大语言模型，实现自动化代码评审意见生成 large language model
7 Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models? 评估LLM在临床文本信息抽取中的应用：性能、资源与实用性分析 large language model
8 Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits Orca：融合人格特质，提升大型语言模型角色扮演能力 large language model ✅
9 Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems 利用大型语言模型作为用户代理评估面向任务的对话系统 large language model
10 Does Prompt Formatting Have Any Impact on LLM Performance? 研究表明Prompt格式显著影响LLM性能，尤其在代码翻译任务中 large language model chain-of-thought
11 An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2 研究量化与剪枝对StarCoder2能耗与推理时间的影响 large language model
12 A dataset of questions on decision-theoretic reasoning in Newcomb-like problems 构建Newcomb类问题决策理论推理数据集，评估LLM的合作能力。 foundation model
13 A Survey of Event Causality Identification: Taxonomy, Challenges, Assessment, and Prospects 事件因果关系识别综述：系统分类、挑战、评估与展望 large language model
14 Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions 提出Compound-QA基准，用于评估LLM在复合问题上的理解、推理和知识能力。 large language model
15 Xmodel-1.5: An 1B-scale Multilingual LLM Xmodel-1.5：一个10亿参数规模的多语言大语言模型，性能均衡且可扩展。 large language model ✅
16 HistoLens: An LLM-Powered Framework for Multi-Layered Analysis of Historical Texts -- A Case Application of Yantie Lun HistoLens：基于LLM的历史文本多层分析框架，以《盐铁论》为例 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
17 Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization 提出HDPO方法，针对性缓解多模态大语言模型中的幻觉问题 DPO direct preference optimization large language model
18 Leveraging large language models for efficient representation learning for entity resolution 提出TriBERTa，利用大语言模型高效学习实体解析的表征 representation learning contrastive learning large language model
19 CMATH: Cross-Modality Augmented Transformer with Hierarchical Variational Distillation for Multimodal Emotion Recognition in Conversation 提出CMATH模型，通过跨模态增强Transformer和分层变分蒸馏提升对话情感识别精度。 distillation multimodal
20 Layer Importance and Hallucination Analysis in Large Language Models via Enhanced Activation Variance-Sparsity 提出基于激活方差-稀疏性的层重要性评估方法，并用于大语言模型幻觉抑制。 contrastive learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页