cs.CL（2025-04-18）

📊 共 16 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) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models 提出CoT-RAG以解决大语言模型推理可靠性不足问题 large language model chain-of-thought
2 LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Models LogicTree：用于大语言模型连贯严谨逻辑推理的结构化证明探索框架 large language model chain-of-thought
3 BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models 提出BadApex，一种基于自适应优化机制的黑盒大语言模型后门攻击方法。 large language model
4 Controlled Territory and Conflict Tracking (CONTACT): (Geo-)Mapping Occupied Territory from Open Source Intelligence 提出CONTACT框架，利用开源情报和LLM进行受控区域和冲突追踪的地理信息映射。 large language model ✅
5 MEQA: A Meta-Evaluation Framework for Question & Answer LLM Benchmarks MEQA：用于问答大语言模型基准测试的元评估框架 large language model
6 Generative AI Act II: Test Time Scaling Drives Cognition Engineering 探索认知工程：测试时扩展驱动通用人工智能从知识检索到思维构建的转变 large language model ✅
7 Divergent LLM Adoption and Heterogeneous Convergence Paths in Research Writing 研究揭示LLM在学术写作中的差异化应用与风格趋同现象 large language model
8 Continual Pre-Training is (not) What You Need in Domain Adaption 研究表明领域自适应持续预训练并非提升法律LLM推理能力的必要手段 large language model
9 DETAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification DETAM：通过定向注意力修改防御大型语言模型的越狱攻击 large language model
10 Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering 提出SecMulti-RAG，解决企业RAG系统检索范围和数据安全问题 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🔗⭐
11 Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models 针对大语言模型，提出特征对齐与表征迁移的知识蒸馏方法 distillation large language model
12 Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning 提出过程预判推理，提升大语言模型在测试时的复杂推理能力 reinforcement learning large language model ✅
13 From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs 提出三阶段端到端优化方法，实现高性价比超小型LLM部署 reinforcement learning distillation large language model
14 Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planning 提出UDP框架，通过构建用户世界模型实现用户定制的对话策略规划 world model
15 Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling 提出基于奖励的课程采样的GRPO方法，提升意图检测的泛化性能 reinforcement learning chain-of-thought

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models 提出Thought Manipulation方法，通过外部CoT引导，提升大模型推理效率并降低计算成本。 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页