cs.CL（2025-08-13）

📊 共 25 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 Speed Always Wins: A Survey on Efficient Architectures for Large Language Models 提出高效架构以解决大规模语言模型计算瓶颈问题 large language model foundation model multimodal
2 VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models 提出VisCodex以解决多模态代码生成问题 large language model multimodal
3 Columbo: Expanding Abbreviated Column Names for Tabular Data Using Large Language Models 提出Columbo以解决表格数据列名扩展问题 large language model chain-of-thought
4 Prompt-Response Semantic Divergence Metrics for Faithfulness Hallucination and Misalignment Detection in Large Language Models 提出语义偏差度量以检测大型语言模型的虚假生成问题 large language model
5 Benchmarking the Medical Understanding and Reasoning of Large Language Models in Arabic Healthcare Tasks 评估大型语言模型在阿拉伯医疗任务中的理解与推理能力 large language model
6 Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models 提出Memory Decoder以解决大语言模型领域适应问题 large language model
7 Evaluating the Role of Large Language Models in Legal Practice in India 评估大型语言模型在印度法律实践中的作用 large language model
8 Efficient Forward-Only Data Valuation for Pretrained LLMs and VLMs 提出For-Value框架以高效评估大模型数据影响力 large language model foundation model
9 Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs 提出多轮任务基准以评估大语言模型的推理与对话能力 large language model instruction following
10 Benchmarking the Legal Reasoning of LLMs in Arabic Islamic Inheritance Cases 利用LLMs提升阿拉伯伊斯兰继承案件的法律推理能力 large language model
11 Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data 提出格式偏见分析方法以解决LLMs在异构数据处理中的偏差问题 large language model
12 LaajMeter: A Framework for LaaJ Evaluation 提出LaaJMeter框架以解决LaaJ评估中的挑战 large language model
13 mSCoRe: a $M$ultilingual and Scalable Benchmark for $S$kill-based $Co$mmonsense $Re$asoning 提出mSCoRe以解决多语言常识推理的评估问题 large language model
14 Persuasiveness and Bias in LLM: Investigating the Impact of Persuasiveness and Reinforcement of Bias in Language Models 提出说服力与偏见强化框架以评估大型语言模型的影响 large language model
15 Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study 提出自动化框架以生成文本解释提升模型分类性能 large language model
16 Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages 提出LLM驱动的文化本地化框架以解决低资源语言数学问题 large language model
17 A Framework for Processing Textual Descriptions of Business Processes using a Constrained Language -- Technical Report 提出BeePath框架以简化业务流程文本描述建模 large language model
18 EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization 提出EffiEval以解决大语言模型评估中的计算挑战 large language model
19 AINL-Eval 2025 Shared Task: Detection of AI-Generated Scientific Abstracts in Russian 提出AINL-Eval 2025任务以检测俄语AI生成的科学摘要 large language model ✅
20 UWBa at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval 提出零-shot系统以解决多语言事实核查声明检索问题 large language model
21 User-centric Subjective Leaderboard by Customizable Reward Modeling 提出用户中心的主观排行榜以解决LLM选择难题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
22 Slow Tuning and Low-Entropy Masking for Safe Chain-of-Thought Distillation 提出SlowED以解决小型语言模型安全性问题 distillation large language model chain-of-thought
23 A Comprehensive Evaluation framework of Alignment Techniques for LLMs 提出多维评估框架以系统比较大语言模型的对齐技术 RLHF large language model
24 Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning 提出GFPO以解决长文本生成中的冗余问题 reinforcement learning large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
25 Using Large Language Models to Measure Symptom Severity in Patients At Risk for Schizophrenia 利用大型语言模型评估精神分裂症高风险患者的症状严重性 AMP large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页