cs.CL（2024-02-12）

📊 共 24 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗3)

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

#题目一句话要点标签🔗⭐
1 Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation 研究数据污染对大语言模型在文本到SQL翻译中的影响 large language model instruction following
2 The Sound of Healthcare: Improving Medical Transcription ASR Accuracy with Large Language Models 利用大型语言模型提升医疗转录ASR准确性 large language model chain-of-thought
3 Asking Multimodal Clarifying Questions in Mixed-Initiative Conversational Search 提出多模态澄清问题以改善混合主动对话搜索 multimodal
4 Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models 提出Diffusion-of-Thought以提升扩散语言模型的推理能力 chain-of-thought
5 Large Language Models "Ad Referendum": How Good Are They at Machine Translation in the Legal Domain? 评估大型语言模型在法律领域机器翻译的有效性 large language model
6 Anchor-based Large Language Models 提出基于锚点的大型语言模型以解决内存消耗问题 large language model
7 Do Membership Inference Attacks Work on Large Language Models? 评估大语言模型的成员推断攻击有效性 large language model
8 Had enough of experts? Quantitative knowledge retrieval from large language models 提出利用大型语言模型进行定量知识检索以改善数据分析 large language model
9 Detecting the Clinical Features of Difficult-to-Treat Depression using Synthetic Data from Large Language Models 基于合成数据的工具检测难治性抑郁症临床特征 large language model
10 Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples 提出Chain-of-Layer框架以解决有限示例下的分类法归纳问题 large language model
11 Show Me How It's Done: The Role of Explanations in Fine-Tuning Language Models 通过解释增强语言模型的微调性能 large language model
12 Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping 提出Step-On-Feet Tuning以提升大语言模型自对齐性能 large language model
13 Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets 通过整合任务特定与生成数据集提升阿姆哈拉语LLaMA模型 large language model
14 Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model 提出Aya模型以解决多语言处理中的资源不均问题 large language model
15 Pushing The Limit of LLM Capacity for Text Classification 提出RGPT框架以提升文本分类性能 large language model
16 Can LLMs Produce Faithful Explanations For Fact-checking? Towards Faithful Explainable Fact-Checking via Multi-Agent Debate 提出多智能体辩论框架以解决事实核查中的解释可信度问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
17 Mercury: A Code Efficiency Benchmark for Code Large Language Models 提出Mercury基准以评估代码大语言模型的代码效率 DPO direct preference optimization large language model ✅
18 Large Language Models as Agents in Two-Player Games 提出统一框架以优化大型语言模型在双人游戏中的学习过程 reinforcement learning large language model
19 Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs 提出精炼直接偏好优化方法以提升大型语言模型的行为一致性 DPO direct preference optimization large language model ✅
20 Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like 提出ELaTE以解决文本到语音系统中缺乏自然笑声的问题 flow matching HuMoR
21 Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts 提出相对偏好优化以解决大语言模型对用户偏好的对齐问题 DPO direct preference optimization large language model ✅
22 Injecting Wiktionary to improve token-level contextual representations using contrastive learning 通过注入维基词典提升对比学习的词级上下文表示 contrastive learning
23 Suppressing Pink Elephants with Direct Principle Feedback 提出直接原则反馈以解决语言模型控制问题 RLHF DPO
24 Topic Modeling as Multi-Objective Contrastive Optimization 提出多目标对比优化方法以提升主题建模效果 representation learning contrastive learning

⬅️ 返回 cs.CL 首页 · 🏠 返回主页