cs.CL（2025-08-05）

📊 共 38 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (33 🔗8) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (33 篇)

#题目一句话要点标签🔗⭐
1 RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior 提出RCP-Merging以解决长链推理模型与领域特定模型融合问题 large language model chain-of-thought
2 EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models 提出EmbedGrad以优化大语言模型的文本提示嵌入 large language model foundation model
3 Thinking with Nothinking Calibration: A New In-Context Learning Paradigm in Reasoning Large Language Models 提出Nothinking校准以提升大语言模型的推理能力 large language model chain-of-thought
4 Can Large Vision-Language Models Understand Multimodal Sarcasm? 提出无训练框架以解决多模态讽刺理解问题 multimodal ✅
5 Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models 提出强大的事实检查框架以解决LLM生成内容的虚假问题 large language model
6 Towards Trustworthy Multimodal Moderation via Policy-Aligned Reasoning and Hierarchical Labeling 提出Hi-Guard以解决多模态内容审核的透明性与准确性问题 multimodal ✅
7 Data and AI governance: Promoting equity, ethics, and fairness in large language models 提出数据与AI治理框架以解决大语言模型中的偏见与公平性问题 large language model
8 CardiffNLP at CLEARS-2025: Prompting Large Language Models for Plain Language and Easy-to-Read Text Rewriting 提出基于大语言模型的西班牙语文本改写方法 large language model
9 Automated scoring of the Ambiguous Intentions Hostility Questionnaire using fine-tuned large language models 利用微调的大型语言模型自动评分AIHQ问卷 large language model
10 CAP-LLM: Context-Augmented Personalized Large Language Models for News Headline Generation 提出CAP-LLM以解决个性化新闻标题生成中的事实一致性问题 large language model
11 Majority Bit-Aware Watermarking For Large Language Models 提出MajorMark以解决大语言模型水印质量与解码准确性问题 large language model
12 Probing Syntax in Large Language Models: Successes and Remaining Challenges 深入分析大型语言模型中的句法探测器以解决评估偏差问题 large language model
13 Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation 提出隐私感知解码以解决大语言模型隐私泄露问题 large language model ✅
14 CoCoTen: Detecting Adversarial Inputs to Large Language Models through Latent Space Features of Contextual Co-occurrence Tensors 提出CoCoTen以检测大型语言模型的对抗输入 large language model
15 Are We on the Right Way for Assessing Document Retrieval-Augmented Generation? 提出Double-Bench以解决文档检索增强生成评估不足问题 large language model multimodal
16 Pay What LLM Wants: Can LLM Simulate Economics Experiment with 522 Real-human Persona? 通过真实人类数据评估LLM在经济决策模拟中的能力 large language model multimodal
17 Multidimensional classification of posts for online course discussion forum curation 提出贝叶斯融合方法以优化在线课程讨论论坛的自动策展 large language model
18 Putnam-AXIOM: A Functional and Static Benchmark for Measuring Higher Level Mathematical Reasoning in LLMs 提出Putnam-AXIOM以解决LLMs数学推理基准的饱和问题 large language model ✅
19 More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generation 提出PartialOrderEval以解决LLM代码生成中的提示细节不足问题 large language model
20 Tackling Distribution Shift in LLM via KILO: Knowledge-Instructed Learning for Continual Adaptation 提出KILO框架以解决大语言模型的领域转移问题 large language model
21 From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation 提出EQGBench以解决教育问题生成的评估挑战 large language model
22 CTTS: Collective Test-Time Scaling 提出CTTS以解决单一测试时间缩放方法的局限性 large language model ✅
23 NLP Methods May Actually Be Better Than Professors at Estimating Question Difficulty 提出基于LLM的不确定性估计以改善考试题目难度评估 large language model
24 Long Story Generation via Knowledge Graph and Literary Theory 提出多代理故事生成器以解决长篇故事生成中的主题漂移问题 large language model
25 AttnTrace: Attention-based Context Traceback for Long-Context LLMs 提出AttnTrace以解决长上下文LLM的追溯效率问题 large language model ✅
26 FairLangProc: A Python package for fairness in NLP 提出FairLangProc以解决NLP中的公平性问题 large language model ✅
27 MultiRAG: A Knowledge-guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generation 提出MultiRAG以解决多源检索增强生成中的幻觉问题 large language model ✅
28 Do language models accommodate their users? A study of linguistic convergence 研究语言模型的语言适应性，揭示其与用户的语言趋同现象 large language model
29 LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning 提出LECTOR以解决语义干扰和个性化适应问题 large language model
30 Current State in Privacy-Preserving Text Preprocessing for Domain-Agnostic NLP 提出隐私保护文本预处理方法以解决NLP领域数据隐私问题 large language model
31 Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation 提出TPARAG以解决RAG系统的安全漏洞问题 large language model
32 Evaluation of GPT-based large language generative AI models as study aids for the national licensure examination for registered dietitians in Japan 评估基于GPT的大语言生成AI模型作为日本注册营养师考试的学习辅助工具 large language model
33 When Algorithms Meet Artists: Topic Modeling the AI-Art Debate, 2013-2025 提出基于BERTopic的方法以分析AI艺术辩论 multimodal

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

#题目一句话要点标签🔗⭐
34 Light-IF: Endowing LLMs with Generalizable Reasoning via Preview and Self-Checking for Complex Instruction Following 提出Light-IF框架以解决复杂指令遵循中的推理问题 reinforcement learning instruction following
35 Sotopia-RL: Reward Design for Social Intelligence 提出Sotopia-RL以解决社会智能任务中的奖励设计问题 reinforcement learning reward design large language model
36 CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward 提出CompassVerifier以解决LLMs评估与结果奖励问题 reinforcement learning large language model ✅
37 LLMs are Single-threaded Reasoners: Demystifying the Working Mechanism of Soft Thinking 提出随机软思维以解决LLMs单线程推理问题 reinforcement learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
38 CoAct-1: Computer-using Agents with Coding as Actions 提出CoAct-1以解决复杂任务中的计算机操作效率问题 manipulation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页