cs.CL（2024-09-18）

📊 共 28 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) (22 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗⭐
1 To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning 研究表明思维链主要提升数学和符号推理能力，其他任务收益有限 large language model chain-of-thought
2 Human-like Affective Cognition in Foundation Models 提出情感认知评估框架，验证大型模型在理解人类情感方面的能力 foundation model chain-of-thought
3 The Factuality of Large Language Models in the Legal Domain 评估大语言模型在法律领域的知识库真实性，并提出改进方法。 large language model
4 Systematic Characterization of the Effectiveness of Alignment in Large Language Models for Categorical Decisions 提出对齐合规指数ACI，系统评估大语言模型在分类决策中的对齐效果 large language model
5 Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models 提出基于大语言模型生成心理测量的价值观评估方法GPV，用于衡量人类和AI的价值观。 large language model
6 Using Large Language Models to Generate Clinical Trial Tables and Figures 利用大型语言模型自动生成临床试验表格和图表，提升报告效率。 large language model
7 Development and bilingual evaluation of Japanese medical large language model within reasonably low computational resources 提出一种低资源日语医疗大语言模型，性能媲美十倍参数量级模型 large language model ✅
8 TART: An Open-Source Tool-Augmented Framework for Explainable Table-based Reasoning 提出TART：一个开源的、工具增强的、可解释的表格推理框架 large language model chain-of-thought ✅
9 MeTHanol: Modularized Thinking Language Models with Intermediate Layer Thinking, Decoding and Bootstrapping Reasoning MeTHanol：中间层思维、解码和引导推理的模块化思维语言模型 large language model ✅
10 Efficacy of Synthetic Data as a Benchmark 评估LLM生成合成数据作为NLP任务基准的有效性，揭示其在不同任务上的表现差异。 large language model
11 VERA: Validation and Enhancement for Retrieval Augmented systems VERA：面向检索增强系统的验证与增强框架，提升生成精度 large language model
12 Local Explanations and Self-Explanations for Assessing Faithfulness in black-box LLMs 提出基于局部扰动和自解释的LLM忠实性评估方法 large language model
13 MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts MEOW：通过反向事实和记忆监督的大语言模型卸载学习方法 large language model
14 Gender Representation and Bias in Indian Civil Service Mock Interviews 揭示印度公务员模拟面试中存在的性别偏见，并提出新的数据集。 large language model
15 MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning MAgICoRe：多智能体迭代由粗到精推理框架，提升LLM数学问题求解能力 large language model
16 Sampling Latent Material-Property Information From LLM-Derived Embedding Representations 利用大语言模型嵌入表征采样潜在材料属性信息 large language model
17 LLMs in Education: Novel Perspectives, Challenges, and Opportunities 探讨大型语言模型在教育领域的应用、挑战与机遇 large language model
18 LLMs + Persona-Plug = Personalized LLMs 提出个性化LLM模型以解决用户偏好多样性问题 large language model
19 Enabling Real-Time Conversations with Minimal Training Costs 提出一种低成本双工解码方法，提升LLM实时对话能力 large language model
20 Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing 提出RoleKE-Bench，揭示并缓解LLM角色扮演中角色知识错误检测的挑战 large language model
21 Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation 提出利用LLM进行API交互的框架，实现自然语言分类和合成数据生成。 large language model
22 "A Woman is More Culturally Knowledgeable than A Man?": The Effect of Personas on Cultural Norm Interpretation in LLMs 研究表明LLM对社会规范的理解受人物角色影响，不同角色导致文化规范解释差异 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🔗⭐
23 Making Large Language Models into World Models with Precondition and Effect Knowledge 利用先决条件和效果知识，将大型语言模型转化为世界模型 world model large language model
24 RUIE: Retrieval-based Unified Information Extraction using Large Language Model 提出RUIE：基于检索的统一信息抽取框架，利用大语言模型实现高效任务泛化。 contrastive learning distillation large language model
25 DocMamba: Efficient Document Pre-training with State Space Model DocMamba：基于状态空间模型的高效文档预训练框架 Mamba state space model
26 From Lists to Emojis: How Format Bias Affects Model Alignment 揭示并利用格式偏见提升模型对齐效果，强调解耦内容与格式的重要性 reinforcement learning preference learning RLHF
27 Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement Qwen2.5-Math：通过自提升策略构建数学专家模型 reinforcement learning large language model chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
28 BodyShapeGPT: SMPL Body Shape Manipulation with LLMs BodyShapeGPT：利用LLM实现SMPL人体模型形状操控 manipulation SMPL SMPL-X

⬅️ 返回 cs.CL 首页 · 🏠 返回主页