cs.CL（2025-08-12）

📊 共 32 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (26 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 A Survey on Training-free Alignment of Large Language Models 提出无训练对齐方法以解决大语言模型的对齐问题 large language model multimodal
2 P/D-Device: Disaggregated Large Language Model between Cloud and Devices 提出P/D-Device以解决云端与设备间资源瓶颈问题 large language model
3 Leveraging Large Language Models for Rare Disease Named Entity Recognition 利用大型语言模型解决稀有疾病命名实体识别问题 large language model
4 Entangled in Representations: Mechanistic Investigation of Cultural Biases in Large Language Models 提出Culturescope以解决大语言模型中的文化偏见问题 large language model
5 IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization 提出IROTE以解决大语言模型特征提取不稳定问题 large language model
6 Decoding Neural Emotion Patterns through Large Language Model Embeddings 提出一种新框架以无神经影像解码语言情感与大脑功能的关系 large language model
7 SinLlama -- A Large Language Model for Sinhala 提出SinLlama以提升僧伽罗语的语言模型支持 large language model
8 AutoCodeBench: Large Language Models are Automatic Code Benchmark Generators 提出AutoCodeBench以解决现有代码生成基准的局限性 large language model
9 Utilizing Multilingual Encoders to Improve Large Language Models for Low-Resource Languages 提出多层融合策略以提升低资源语言的LLM性能 large language model
10 Complex Logical Instruction Generation 提出LogicIFGen与LogicIFEval以解决复杂逻辑指令生成问题 large language model instruction following ✅
11 APIO: Automatic Prompt Induction and Optimization for Grammatical Error Correction and Text Simplification 提出APIO以解决语法错误纠正和文本简化问题 large language model chain-of-thought
12 TEN: Table Explicitization, Neurosymbolically 提出TEN方法以解决半结构化文本中的表格数据提取问题 large language model chain-of-thought
13 Quick on the Uptake: Eliciting Implicit Intents from Human Demonstrations for Personalized Mobile-Use Agents 提出IFRAgent框架以解决个性化移动代理的意图识别问题 large language model multimodal ✅
14 Retrospective Sparse Attention for Efficient Long-Context Generation 提出RetroAttention以解决长上下文生成中的KV缓存瓶颈问题 large language model
15 BiasGym: Fantastic LLM Biases and How to Find (and Remove) Them 提出BiasGym框架以识别和消除大型语言模型中的偏见 large language model
16 GreenTEA: Gradient Descent with Topic-modeling and Evolutionary Auto-prompting 提出GreenTEA以解决自动提示优化中的效率与效果问题 large language model
17 Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models 提出时间一致性方法以解决扩散语言模型的预测问题 large language model
18 ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs 提出自适应串行-并行解码以解决大语言模型推理延迟问题 large language model
19 Steering Towards Fairness: Mitigating Political Bias in LLMs 提出一种新方法以缓解大型语言模型中的政治偏见 large language model
20 DevNous: An LLM-Based Multi-Agent System for Grounding IT Project Management in Unstructured Conversation 提出DevNous以解决IT项目管理中的对话转化问题 large language model
21 A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models 系统性调查并分类并行文本生成技术以提升生成效率 large language model ✅
22 LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement 提出基于子任务引导与迭代优化的文本到表格生成方法 large language model
23 OdysseyBench: Evaluating LLM Agents on Long-Horizon Complex Office Application Workflows 提出OdysseyBench以解决长时间复杂办公应用工作流程评估问题 large language model
24 Jointly Generating and Attributing Answers using Logits of Document-Identifier Tokens 提出LoDIT以解决大型语言模型的答案生成与归因问题 large language model
25 TiMoE: Time-Aware Mixture of Language Experts 提出TiMoE以解决语言模型的时间知识过时问题 large language model ✅
26 Adaptive Personalized Conversational Information Retrieval 提出自适应个性化对话信息检索方法以解决查询个性化需求问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
27 KG-o1: Enhancing Multi-hop Question Answering in Large Language Models via Knowledge Graph Integration 提出KG-o1以提升大语言模型的多跳问答能力 DPO direct preference optimization large language model
28 Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments 提出自动化环境构建管道以提升大语言模型工具使用能力 reinforcement learning large language model
29 Train Long, Think Short: Curriculum Learning for Efficient Reasoning 提出课程学习策略以提高长语言模型的推理效率 curriculum learning large language model ✅
30 ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning 提出ParallelSearch以解决搜索查询的并行处理问题 reinforcement learning large language model
31 Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training 提出统一共训练框架以提升大型语言模型的内容安全性 reinforcement learning RLHF DPO
32 InternBootcamp Technical Report: Boosting LLM Reasoning with Verifiable Task Scaling 提出InternBootcamp以解决LLM推理能力不足的问题 reinforcement learning large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页