cs.CL（2025-03-18）

📊 共 19 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (15 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#题目一句话要点标签🔗⭐
1 Do Multimodal Large Language Models Understand Welding? 评估多模态大语言模型在焊接质量评估中的能力，并提出WeldPrompt提示策略。 large language model multimodal chain-of-thought
2 Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks 通过思维链微调LLaMA和Gemma模型，提升乌克兰语考试任务性能 large language model chain-of-thought ✅
3 Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models 提出CROSS框架，利用LLM统一文本语义与图结构，提升时序文本属性图建模性能 large language model
4 Gender and content bias in Large Language Models: a case study on Google Gemini 2.0 Flash Experimental 评估Gemini 2.0 Flash在内容审核和性别偏见上的表现，并与ChatGPT-4o对比。 large language model
5 Word2Minecraft: Generating 3D Game Levels through Large Language Models Word2Minecraft：利用大型语言模型生成基于故事的Minecraft 3D游戏关卡 large language model ✅
6 Large Language Models for Virtual Human Gesture Selection 利用大型语言模型进行虚拟人手势选择，提升人机交互体验 large language model
7 From "Hallucination" to "Suture": Insights from Language Philosophy to Enhance Large Language Models 提出Anchor-RAG框架，利用语言哲学理论缓解大语言模型的幻觉问题 large language model
8 ConSCompF: Consistency-focused Similarity Comparison Framework for Generative Large Language Models 提出ConSCompF框架，用于在少量无标签数据上比较生成式大语言模型的相似性。 large language model
9 Enabling Inclusive Systematic Reviews: Incorporating Preprint Articles with Large Language Model-Driven Evaluations 提出AutoConfidence框架，利用LLM评估预印本质量，助力高效的系统性综述。 large language model
10 Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM Command R7B Arabic：面向企业，具备文化感知能力的小型多语种阿拉伯语LLM large language model instruction following
11 HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL HDLCoRe：一种免训练框架，通过提示工程和RAG缓解LLM生成HDL代码中的幻觉问题 large language model chain-of-thought
12 PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play PLAY2PROMPT：通过工具试错优化LLM Agent的零样本工具指令 large language model
13 Good/Evil Reputation Judgment of Celebrities by LLMs via Retrieval Augmented Generation 利用检索增强生成，LLM可判断名人善恶声誉 large language model
14 DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal DARS：动态动作重采样通过自适应树遍历提升代码生成Agent性能 large language model
15 LLM Generated Persona is a Promise with a Catch 揭示LLM生成Persona的偏差，强调严谨的生成方法以提升模拟真实度 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
16 Towards Harmless Multimodal Assistants with Blind Preference Optimization 提出盲偏好优化(BPO)方法，提升多模态大语言模型在多模态场景下的安全性。 DPO large language model multimodal ✅
17 Synthetic Data Generation Using Large Language Models: Advances in Text and Code 综述：利用大型语言模型生成合成数据，推动文本和代码领域发展。 reinforcement learning large language model
18 Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence 提出不确定性蒸馏方法，提升语言模型语义置信度表达的校准性。 distillation large language model
19 How much do LLMs learn from negative examples? 研究表明负样本训练能显著提升LLM在问答任务中的准确性和减少幻觉 RLHF DPO large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页