cs.CL（2024-09-19）

📊 共 41 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (30 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (10) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (30 篇)

#题目一句话要点标签🔗⭐
1 Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning 提出迭代思维框架以提升大型语言模型的推理能力 large language model chain-of-thought
2 From Linguistic Giants to Sensory Maestros: A Survey on Cross-Modal Reasoning with Large Language Models 综述：利用大型语言模型进行跨模态推理的研究进展与挑战 large language model ✅
3 LLM Surgery: Efficient Knowledge Unlearning and Editing in Large Language Models LLM手术：提出一种高效的大语言模型知识遗忘与编辑方法 large language model
4 Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization 提出HyperCloning方法，通过小模型初始化加速大语言模型预训练。 large language model
5 Enhancing E-commerce Product Title Translation with Retrieval-Augmented Generation and Large Language Models 提出基于检索增强生成（RAG）的方法，提升电商产品标题的跨语言翻译质量。 large language model
6 Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data 利用图结构合成数据，提升大语言模型在复杂逻辑推理任务上的能力 large language model
7 Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels 提出零到强泛化框架，无需金标迭代提升大语言模型能力 large language model
8 Are Large Language Models Good Essay Graders? 评估大型语言模型在自动作文评分任务中的有效性与人类评分对齐程度 large language model
9 FoodPuzzle: Developing Large Language Model Agents as Flavor Scientists FoodPuzzle：构建基于大语言模型的风味科学家智能体，加速食品风味研发。 large language model
10 Edu-Values: Towards Evaluating the Chinese Education Values of Large Language Models Edu-Values：构建中文教育价值观评测基准，评估大语言模型教育领域能力。 large language model
11 Exploring Large Language Models for Product Attribute Value Identification 探索大型语言模型在产品属性值识别中的应用，提升零样本和小样本学习能力。 large language model
12 Efficient Performance Tracking: Leveraging Large Language Models for Automated Construction of Scientific Leaderboards 提出SciLead数据集，并利用LLM自动构建科学排行榜，解决信息不完整和错误问题。 large language model
13 RAD-Bench: Evaluating Large Language Models Capabilities in Retrieval Augmented Dialogues RAD-Bench：评估大型语言模型在检索增强对话中的能力 large language model ✅
14 Profiling Patient Transcript Using Large Language Model Reasoning Augmentation for Alzheimer's Disease Detection 利用大语言模型推理增强的患者转录本分析用于阿尔茨海默病检测 large language model
15 Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models 利用语言最小对探究大型语言模型的语言相似性 large language model ✅
16 Mutual Information-based Representations Disentanglement for Unaligned Multimodal Language Sequences 提出基于互信息解耦的MIRD方法，解决非对齐多模态语言序列的信息冗余问题 multimodal
17 CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks 提出Juhaina：一个文化对齐的阿拉伯语-英语双语大语言模型及CamelEval评测基准。 large language model instruction following ✅
18 Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning CodePlan：通过扩展代码形式的规划能力，解锁大型语言模型的推理潜力 large language model instruction following
19 Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation 提出AgentCOT框架，通过多轮LLM生成解决复杂任务中的幻觉、可解释性和可控性问题 large language model chain-of-thought
20 What Would You Ask When You First Saw $a^2+b^2=c^2$? Evaluating LLM on Curiosity-Driven Questioning 提出基于好奇心驱动提问的LLM评估框架，用于衡量模型知识获取潜力 large language model
21 MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions MURI：通过逆向指令为低资源语言生成高质量指令微调数据集 large language model ✅
22 Michelangelo: Long Context Evaluations Beyond Haystacks via Latent Structure Queries 提出Michelangelo，通过潜在结构查询评估长文本语言模型的推理能力 large language model
23 CritiPrefill: A Segment-wise Criticality-based Approach for Prefilling Acceleration in LLMs CritiPrefill：基于分段关键性的LLM预填充加速方法 large language model
24 Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation 提出FaviComp，一种兼顾模型熟悉度的检索增强生成证据压缩方法 large language model
25 Guided Profile Generation Improves Personalization with LLMs 提出引导式用户画像生成方法，提升LLM在个性化任务中的性能 large language model
26 Pay Attention to What Matters 提出GUIDE方法，通过增强指令token的注意力得分，提升LLM对用户指令的遵循能力 large language model
27 Connecting Ideas in 'Lower-Resource' Scenarios: NLP for National Varieties, Creoles and Other Low-resource Scenarios 针对低资源场景，连接NLP领域思想以解决方言、克里奥尔语等语言处理难题。 large language model
28 Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation 提出FRAMES以解决检索增强生成系统评估问题 large language model
29 LLM-Measure: Generating Valid, Consistent, and Reproducible Text-Based Measures for Social Science Research LLM-Measure：利用大语言模型生成有效、一致且可复现的社会科学文本测量方法 large language model
30 CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair CraftRTL：通过构造正确的非文本表示和有针对性的代码修复，为Verilog代码模型生成高质量合成数据 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
31 Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization 研究表明：直接偏好优化(DPO)微调提升医学领域大语言模型在复杂任务上的性能 DPO direct preference optimization large language model
32 LLMR: Knowledge Distillation with a Large Language Model-Induced Reward 提出LLMR：一种基于大语言模型奖励的知识蒸馏方法，提升小模型性能。 distillation large language model
33 Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment 提出基于排序损失的知识蒸馏方法，提升小模型学习大模型多模态分布的能力 distillation large language model
34 Enhancing TinyBERT for Financial Sentiment Analysis Using GPT-Augmented FinBERT Distillation 利用GPT增强的FinBERT蒸馏提升TinyBERT在金融情感分析中的性能 predictive model distillation large language model
35 TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning 提出TACO-RL，一种基于强化学习的任务感知Prompt压缩优化方法，提升LLM效率。 reinforcement learning large language model
36 Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning 提出基于知识驱动数据增强和高斯衰减对比学习的无监督句子嵌入方法 contrastive learning large language model
37 Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights 提出一种高效知识蒸馏方法，利用教师模型的洞察力提升小型语言模型性能 distillation large language model
38 Small Language Models are Equation Reasoners 提出方程推理格式，显著提升小型语言模型算术能力 distillation large language model chain-of-thought
39 Enhancing SLM via ChatGPT and Dataset Augmentation 利用ChatGPT和数据增强提升小型语言模型在自然语言推理任务上的性能 distillation large language model
40 Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models 提出在线知识蒸馏(OKD)方法，提升自回归语言模型蒸馏效率与性能。 distillation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
41 CLAIR-A: Leveraging Large Language Models to Judge Audio Captions CLAIR-A：利用大型语言模型评估音频描述质量 scene understanding large language model ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页