cs.CL（2024-04-29）

📊 共 29 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) (25 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (25 篇)

#题目一句话要点标签🔗⭐
1 Simplifying Multimodality: Unimodal Approach to Multimodal Challenges in Radiology with General-Domain Large Language Model 提出MID-M框架以解决医学多模态数据处理问题 large language model multimodal
2 Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning 提出SalesBot 2.0以解决销售对话自然性不足问题 large language model chain-of-thought
3 In-Context Symbolic Regression: Leveraging Large Language Models for Function Discovery 提出基于大语言模型的上下文符号回归方法以解决函数发现问题 large language model
4 Benchmarking Benchmark Leakage in Large Language Models 提出检测管道以解决大语言模型基准数据泄露问题 large language model
5 PoPE: Legendre Orthogonal Polynomials Based Position Encoding for Large Language Models 提出基于勒让德正交多项式的位置编码以解决现有方法的不足 large language model
6 A Framework for Real-time Safeguarding the Text Generation of Large Language Model 提出LLMSafeGuard以实时保障大型语言模型的文本生成安全性 large language model
7 Evaluating and Mitigating Linguistic Discrimination in Large Language Models 提出LDFighter以解决大型语言模型中的语言歧视问题 large language model
8 BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers 提出BMRetriever以提升生物医学文本检索能力 large language model ✅
9 FoundaBench: Evaluating Chinese Fundamental Knowledge Capabilities of Large Language Models 提出FoundaBench以评估中文大语言模型的基础知识能力 large language model
10 Plan of Thoughts: Heuristic-Guided Problem Solving with Large Language Models 提出基于POMDP的多步推理问题解决方案 large language model
11 Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting 提出混合指令方法以提升大语言模型的对齐效率 large language model
12 MileBench: Benchmarking MLLMs in Long Context 提出MileBench以解决多模态大语言模型在长文本中的评估问题 large language model multimodal
13 Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations? 探讨视觉与语言解码器在生成解释时的输入依赖性 multimodal
14 Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting 提出Kangaroo框架以实现无损自我推测解码 large language model ✅
15 Time Machine GPT 提出Time Machine GPT以解决语言模型的时间适应性问题 large language model
16 LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report 提出LoRA Land以实现高效的LLM微调与部署 large language model
17 Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models 提出多模型评估面板以解决LLM评估偏差问题 large language model
18 Ethical Reasoning and Moral Value Alignment of LLMs Depend on the Language we Prompt them in 探讨语言对大型语言模型伦理推理的影响 large language model
19 What Drives Performance in Multilingual Language Models? 研究多语言模型性能驱动因素以提升跨语言能力 large language model
20 Accelerating Production LLMs with Combined Token/Embedding Speculators 提出结合令牌/嵌入预测器以加速生产环境中的LLM推理 large language model
21 Markovian Transformers for Informative Language Modeling 提出马尔可夫变换器以解决链式推理不足问题 chain-of-thought
22 Truth-value judgment in language models: 'truth directions' are context sensitive 探讨上下文对语言模型真值判断的影响 large language model
23 The Spatial Semantics of Iconic Gesture 提出空间手势语义模型以解决手势与语言意义的结合问题 multimodal
24 101 Billion Arabic Words Dataset 提出1010亿阿拉伯词数据集以解决阿拉伯语言模型数据稀缺问题 large language model
25 Can GPT-4 do L2 analytic assessment? 利用GPT-4进行第二语言分析性评估以提升自动评分技术 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🔗⭐
26 HFT: Half Fine-Tuning for Large Language Models 提出半精调方法以解决大语言模型遗忘问题 direct preference optimization large language model
27 UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts 提出UMETTS框架以解决情感文本到语音合成问题 contrastive learning multimodal
28 More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness 探讨RLHF对大语言模型信任度的影响 reinforcement learning RLHF large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
29 Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions 通过前提移除干预探索细粒度LLM物理推理的极限 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页