cs.CL（2024-07-12）

📊 共 26 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) (21 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers 提出SPIQA数据集以解决科学论文中的多模态问答问题 large language model multimodal chain-of-thought
2 Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors 提出基于LLM导师的逐步验证与纠正框架，提升学生推理错误识别与反馈质量 large language model
3 Towards Chapter-to-Chapter Context-Aware Literary Translation via Large Language Models 提出基于大型语言模型的章节级文学翻译方法，并构建新的中英文学翻译数据集。 large language model
4 Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models 提出Token监督价值模型，提升大语言模型数学问题求解能力 large language model
5 Robustness of Large Language Models to Perturbations in Text 研究表明大型语言模型对文本扰动具有较强的鲁棒性，并在语法纠错和词汇语义变化任务上取得新突破。 large language model
6 Empowering Few-Shot Relation Extraction with The Integration of Traditional RE Methods and Large Language Models 提出DSARE，融合传统关系抽取与大语言模型，提升少样本关系抽取性能 large language model
7 Large Language Models for Integrating Social Determinant of Health Data: A Case Study on Heart Failure 30-Day Readmission Prediction 利用大型语言模型整合社会决定因素数据，预测心力衰竭患者30天再入院率。 large language model
8 Mitigating Entity-Level Hallucination in Large Language Models 提出DRAD动态检索增强方法，缓解大语言模型中的实体级幻觉问题 large language model ✅
9 Scalability of Bayesian Network Structure Elicitation with Large Language Models: a Novel Methodology and Comparative Analysis 提出基于LLM多数投票的贝叶斯网络结构学习方法，并分析其可扩展性。 large language model
10 Pronunciation Assessment with Multi-modal Large Language Models 提出基于多模态大语言模型的发音评估系统，提升语音学习的智能化水平。 large language model
11 Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation 提出基于LLM的生物医学假设生成框架，并进行全面评估与分析。 large language model
12 Optimized Multi-Token Joint Decoding with Auxiliary Model for LLM Inference 提出MTAD框架，加速LLM多token联合解码，提升推理速度和效果。 large language model
13 Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts 提出专家知识多样性剪枝方法，提升稀疏MoE模型的任务无关参数效率。 large language model
14 GRAD-SUM: Leveraging Gradient Summarization for Optimal Prompt Engineering GRAD-SUM：利用梯度总结实现大型语言模型的最优提示工程 large language model
15 Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training 提出解耦拒绝训练(DeRTa)以提升LLM在不安全内容生成时的拒绝能力 large language model
16 Self-Evolving GPT: A Lifelong Autonomous Experiential Learner 提出Self-Evolving GPT，实现大型语言模型的终身自主经验学习 large language model
17 What an Elegant Bridge: Multilingual LLMs are Biased Similarly in Different Languages 多语言LLM在不同语言中表现出相似的基于语法性别的偏见 large language model
18 Bridging Dictionary: AI-Generated Dictionary of Partisan Language Use 提出“桥梁词典”，利用AI生成党派语言使用差异词典，促进政治沟通。 large language model
19 Transformer Layers as Painters 探索Transformer层的功能：通过重组层结构优化预训练模型 large language model
20 The Sociolinguistic Foundations of Language Modeling 从社会语言学视角审视语言模型，提升其性能和社会价值 large language model
21 The Honorific Effect: Exploring the Impact of Japanese Linguistic Formalities on AI-Generated Physics Explanations 研究日语敬语对大语言模型物理学解释的影响，揭示文化因素对AI的影响。 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🔗⭐
22 A Survey on Symbolic Knowledge Distillation of Large Language Models 综述论文：探索大语言模型中符号知识蒸馏方法与应用 distillation large language model
23 3M-Health: Multimodal Multi-Teacher Knowledge Distillation for Mental Health Detection 提出3M-Health模型，利用多模态多教师知识蒸馏进行心理健康检测。 distillation multimodal
24 New Desiderata for Direct Preference Optimization 针对直接偏好优化（DPO）的不足，提出新的评估标准和改进损失函数。 reinforcement learning RLHF DPO
25 Is Contrasting All You Need? Contrastive Learning for the Detection and Attribution of AI-generated Text 提出WhosAI：基于对比学习的AI生成文本检测与溯源框架 contrastive learning large language model
26 One Stone, Four Birds: A Comprehensive Solution for QA System Using Supervised Contrastive Learning 提出基于监督对比学习的QA系统方案，提升鲁棒性和效率，实现多任务统一。 representation learning contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页