cs.CL（2025-06-10）

📊 共 17 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) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 Did I Faithfully Say What I Thought? Bridging the Gap Between Neural Activity and Self-Explanations in Large Language Models 提出NeuroFaith框架以评估和提升LLM自我解释的可信度 large language model
2 Scalable Medication Extraction and Discontinuation Identification from Electronic Health Records Using Large Language Models 利用大型语言模型提取电子健康记录中的药物信息与停药识别 large language model
3 Large Language Models and Emergence: A Complex Systems Perspective 探讨大型语言模型的涌现能力与智能特性 large language model
4 Dialect Normalization using Large Language Models and Morphological Rules 提出结合规则与大语言模型的方言标准化方法 large language model
5 PHRASED: Phrase Dictionary Biasing for Speech Translation 提出短语字典偏置方法以解决语音翻译中的短语翻译挑战 large language model multimodal
6 Atomic-to-Compositional Generalization for Mobile Agents with A New Benchmark and Scheduling System 提出UI-NEXUS基准与AGENT-NEXUS调度系统以解决移动代理的组合任务泛化问题 large language model multimodal
7 UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench 提出UTBoost以解决SWE-Bench中测试用例不足问题 large language model
8 LLM-as-a-qualitative-judge: automating error analysis in natural language generation 提出LLM作为定性评估工具以自动化自然语言生成错误分析 large language model ✅
9 Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions 研究大型语言模型在政治问题中的信息基础能力 large language model
10 FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation 提出FaithfulRAG以解决知识冲突问题 large language model ✅
11 PropMEND: Hypernetworks for Knowledge Propagation in LLMs 提出PropMEND以解决大语言模型知识传播问题 large language model
12 From Legal Texts to Defeasible Deontic Logic via LLMs: A Study in Automated Semantic Analysis 提出基于大语言模型的法律文本自动语义分析方法 large language model
13 The impact of fine tuning in LLaMA on hallucinations for named entity extraction in legal documentation 提出基于LLaMA微调的命名实体提取方法以减少法律文档中的幻觉现象 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🔗⭐
14 Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning 提出Router-R1以解决多轮路由与聚合问题 reinforcement learning large language model
15 Learning to Reason Across Parallel Samples for LLM Reasoning 提出样本集聚合器以提升大语言模型的推理能力 reinforcement learning large language model
16 Can A Gamer Train A Mathematical Reasoning Model? 利用游戏GPU训练数学推理模型以降低资源需求 reinforcement learning large language model ✅
17 Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model 提出Step-Audio-AQAA以解决音频交互中的自然语言生成问题 DPO direct preference optimization

⬅️ 返回 cs.CL 首页 · 🏠 返回主页