cs.CL（2023-12-07）

📊 共 15 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) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning 提出LaRS，通过无监督学习潜在推理技能提升CoT推理效果 large language model chain-of-thought
2 Large Language Models for Mathematicians 探讨大型语言模型在数学领域的应用潜力与最佳实践 large language model
3 Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use 提出Attention Buckets方法，增强LLM上下文感知能力，显著提升工具使用性能。 large language model
4 Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Models Simul-LLM：探索基于大型语言模型的高质量同声传译框架 large language model
5 Comparing Large Language Model AI and Human-Generated Coaching Messages for Behavioral Weight Loss 利用大型语言模型提升行为减重干预效果，媲美人力指导。 large language model
6 Multimodal Misinformation Detection in a South African Social Media Environment 提出一种南非社交媒体环境下的多模态错误信息检测模型，并构建了相应的南非数据集。 multimodal
7 Large Language Models for Intent-Driven Session Recommendations 提出基于大语言模型的意图驱动会话推荐方法，解决用户意图动态变化问题。 large language model
8 CLadder: Assessing Causal Reasoning in Language Models CLadder：构建因果推理数据集，评估大型语言模型的因果推理能力 large language model chain-of-thought ✅
9 Chain of Code: Reasoning with a Language Model-Augmented Code Emulator 提出Chain of Code，通过代码模拟增强语言模型推理能力，提升语义理解任务性能。 chain-of-thought
10 A Block Metropolis-Hastings Sampler for Controllable Energy-based Text Generation 提出基于Block Metropolis-Hastings采样的可控能量模型文本生成方法 large language model
11 A Study on the Calibration of In-context Learning 研究表明ICL示例数量影响模型校准，并提出scaling-binning校准器以提升可靠性。 chain-of-thought
12 OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarization OpenAsp：提出一个面向多文档开放式方面摘要的基准数据集，以应对真实场景下的信息需求。 large language model
13 Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers 通过多项选择任务探究LLaMA模型的规模与层次对理解能力的影响 large language model
14 Analyzing the Inherent Response Tendency of LLMs: Real-World Instructions-Driven Jailbreak 提出RADIAL方法，通过诱导LLM固有响应倾向实现指令驱动的越狱攻击 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
15 Is Feedback All You Need? Leveraging Natural Language Feedback in Goal-Conditioned Reinforcement Learning 提出基于自然语言反馈的Goal-Conditioned强化学习方法，提升泛化性能 reinforcement learning decision transformer

⬅️ 返回 cs.CL 首页 · 🏠 返回主页