语言大模型 / LLM - arXivDaily 专题

2403.12900 2024-03-20 cs.DC cs.AI cs.CL cs.LG 90%

Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference

Baolin Li, Yankai Jiang, Vijay Gadepally, Devesh Tiwari

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

2403.09743 2024-03-18 cs.CL cs.AI cs.LG 90%

The Human Factor in Detecting Errors of Large Language Models: A Systematic Literature Review and Future Research Directions

Christian A. Schiller

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 21 papers analysed and synthesized in detail from a total search result size of 594 (raw results) / 61 (scanned) / 28 (selected)

2301.11916 2024-02-14 cs.CL cs.AI cs.LG 90%

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

Xinyi Wang, Wanrong Zhu, Michael Saxon, Mark Steyvers, William Yang Wang

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；pretraining(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments code at: https://github.com/WANGXinyiLinda/concept-based-demonstration-selection Accepted to NeurIPS 2023

2402.00518 2024-02-02 cs.LG cs.AI cs.CL 90%

EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models

Xuchen Pan, Yanxi Chen, Yaliang Li, Bolin Ding, Jingren Zhou

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

2401.10446 2024-01-22 cs.CL cs.AI cs.LG cs.SD eess.AS 90%

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition

Yuchen Hu, Chen Chen, Chao-Han Huck Yang, Ruizhe Li, Chao Zhang, Pin-Yu Chen, EnSiong Chng

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ICLR 2024, Spotlight top 5%, 24 pages. This work will be open sourced at: https://github.com/YUCHEN005/RobustGER under MIT license

2309.14393 2024-01-22 cs.CL cs.AI cs.CY cs.LG 90%

LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models

Ahmad Faiz, Sotaro Kaneda, Ruhan Wang, Rita Osi, Prateek Sharma, Fan Chen, Lei Jiang

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 15 pages, 8 figures

Journal ref published in ICLR2024

2310.18331 2023-11-01 cs.CL cs.AI cs.LG 90%

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

Jiarun Liu, Wentao Hu, Chunhong Zhang

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Include wrong information in comment. Should be 7 pages and not published yet

2305.18395 2023-10-31 cs.CL cs.AI cs.LG 90%

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Minki Kang, Seanie Lee, Jinheon Baek, Kenji Kawaguchi, Sung Ju Hwang

专题命中效率与部署：language model(title,abstract)；small language model(title,abstract)；large language model(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments NeurIPS 2023

2310.13227 2023-10-23 cs.CL cs.AI cs.LG 90%

ToolChain: Efficient Action Space Navigation in Large Language Models with A Search

Yuchen Zhuang, Xiang Chen, Tong Yu, Saayan Mitra, Victor Bursztyn, Ryan A. Rossi, Somdeb Sarkhel, Chao Zhang

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

2303.05382 2023-09-07 cs.CL cs.AI cs.LG 90%

ChatGPT is on the Horizon: Could a Large Language Model be Suitable for Intelligent Traffic Safety Research and Applications?

Ou Zheng, Mohamed Abdel-Aty, Dongdong Wang, Zijin Wang, Shengxuan Ding

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Submitted to Nature - Machine Intelligence (Revised and Extended)

2305.05176 2023-05-10 cs.LG cs.AI cs.CL cs.SE 90%

FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Lingjiao Chen, Matei Zaharia, James Zou

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

2304.01083 2023-04-04 cs.CL cs.AI cs.CV cs.LG 90%

Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

Wen Shen, Lei Cheng, Yuxiao Yang, Mingjie Li, Quanshi Zhang

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

2608.20988 2026-08-24 cs.LG cs.AI 新提交 90%

Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models

面向大语言模型量化鲁棒性的雅可比引导噪声注入

Deepanshu Pandey, Arnav Chavan, Nahush Lele, Sankalp Dayal, Deepak Gupta

机构 * Amazon（亚马逊）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI、cs.LG

AI总结该研究针对大语言模型量化时自注意力机制对离散化误差敏感的问题，提出雅可比引导噪声注入训练策略，在低比特量化下显著提升了模型在图像分类与语言建模任务中的性能。

Comments Accepted at AdaptFM: Resource-Adaptive Foundation Model Inference, ICML 2026

2509.15174 2026-04-23 cs.CL cs.AI 90%

SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models

SMARTER: 一种数据高效框架，通过自增强大语言模型提升毒性检测与解释

Huy Nghiem, Advik Sachdeva, Hal Daumé

机构 * University of Maryland（马里兰大学）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.CL、cs.AI

AI总结 SMARTER通过两阶段框架利用大语言模型自身输出生成解释，提升内容审核的可解释性，实验表明在三个基准任务中实现13%的宏F1提升，且数据使用量仅为全训练数据的分数。

Comments ACL 2026. NLP, Hate speech detection, explanation, LLM. Version 3

2409.00084 2026-04-10 cs.CL cs.AI 90%

Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models

视觉-语言与大语言模型在胃肠病学中的表现：GPT、Claude、Llama、Phi、Mistral、Gemma及量化模型

Seyed Amir Ahmad Safavi-Naini, Shuhaib Ali, Omer Shahab, Zahra Shahhoseini, Thomas Savage, Sara Rafiee, Jamil S Samaan, Reem Al Shabeeb, Farah Ladak, Jamie O Yang, Juan Echavarria, Sumbal Babar, Aasma Shaukat, Samuel Margolis, Nicholas P Tatonetti, Girish Nadkarni, Bara El Kurdi, Ali Soroush

机构 * Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）； University of Texas Health（德克萨斯大学健康科学中心）； Virginia Hospital Center（弗吉尼亚医院中心）； Shahid Beheshti University of Medical Sciences（沙希德·贝赫什提医科大学）； Stanford University（斯坦福大学）； Cedars-Sinai Medical Center（西达赛奈医疗中心）； Inova Fairfax Medical Campus（伊诺瓦费尔法克斯医疗中心）； University of California–Los Angeles（加州大学洛杉矶分校）； NYU Grossman School of Medicine（纽约大学格罗斯曼医学院）； Columbia University（哥伦比亚大学）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)；分类 cs.CL、cs.AI

AI总结本研究评估了大语言模型和视觉-语言模型在胃肠病学中的医学推理性能，比较了不同模型配置、参数及提示工程策略对性能的影响，发现专有模型在准确性上优于开源模型，且图像描述对视觉-语言模型性能有显著影响。

Comments Manuscript Pages: 34, Figures: 7, Tables: 2, Supplementary File Pages: 35, Data Transparency Statement: Code is available at: https://github.com/Sdamirsa/LLM-VLM-in-Gastroenterology . Study data from American College of Gastroenterology (ACG) are restricted and available upon request with ACG permission. Correction: updated abstract considering Llama3.1 results

Journal ref npj Digital Medicine 8, 797 (2025)

2507.14017 2025-10-01 cs.CL cs.LG 90%

Efficient Temporal Tokenization for Mobility Prediction with Large Language Models

Haoyu He, Haozheng Luo, Yan Chen, Qi R. Wang

机构 * Northeastern University, Boston, MA（东北大学）； Northwestern University, Evanston, IL（西北大学）

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.LG

Journal ref Proceedings of the 3rd Workshop on Efficient Systems for Foundation Models (ES-FoMo III) at ICML 2025

2503.18002 2025-03-26 cs.NE cs.AI cs.AR cs.LG 90%

Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2

Steven Abreu, Sumit Bam Shrestha, Rui-Jie Zhu, Jason Eshraghian

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.AI、cs.LG

Comments Accepted to International Conference on Learning Representations (ICLR) Workshop on Scalable Optimization for Efficient and Adaptive Foundation Models (SCOPE)

2502.03034 2025-02-06 cs.CL cs.LG 90%

Knowledge Distillation from Large Language Models for Household Energy Modeling

Mohannad Takrouri, Nicolás M. Cuadrado, Martin Takáč

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)；分类 cs.CL、cs.LG

Comments Source code is available at https://github.com/Singularity-AI-Lab/LLM-Energy-Knowledge-Distillation

2311.14677 2023-11-28 cs.CY cs.CL cs.LG 90%

Filter bubbles and affective polarization in user-personalized large language model outputs

Tomo Lazovich

专题命中效率与部署：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Comments Accepted to NeurIPS 2023 Workshop "I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models"

2608.23353 2026-08-25 cs.CL cs.NE 新提交 90%

FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations

FormuEvo：大语言模型引导的进化算法用于发现求解器高效的混合整数规划模型

Haofeng Yuan, Jianing Peng, Jieyi Bi, Ni Zhang, Shiji Song, Zhiguang Cao

机构 * College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）； School of Computing and Information Systems, Singapore Management University（新加坡管理大学计算与信息系统学院）； Tsinghua University（清华大学）

专题命中效率与部署：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.CL

AI总结 FormuEvo是LLM引导的进化框架，将MIP模型设计转化为符号空间的进化优化，结合求解器感知诊断与结构化内存，发现的MIP模型性能远超专家设计及现有LLM方法，求解加速最高达5.5倍且知识可跨场景迁移。

Comments 27 pages, 6 figures, and 9 tables. To appear in the Proceedings of EMNLP 2026

2608.20280 2026-08-25 cs.DB cs.LG 版本更新 90%

Which Eviction Policy Should an LLM Cache Use? A Systematic Study Across Workloads, Capacities, and Encoders

大语言模型（LLM）缓存应采用哪种驱逐策略？跨工作负载、容量和编码器的系统研究

Yash Kulkarni, Shubham Harkare, Arvind Yogesh Suresh Babu

专题命中效率与部署：LLM(title,title_cn)；分类 cs.LG

AI总结本研究使用CLEVER工具在多场景下对比多种LLM缓存驱逐策略，发现LFU性能最优，且当前操作点的答案可替换性低、阈值难跨模型迁移，建议部署时先验证答案有效性再测试次级策略差异。

Comments 11 pages, 9 figures

2608.18503 2026-08-20 cs.LG 新提交 90%

LLM-Powered Predictive Decision-Making for Sustainable Data Center Operations

基于大语言模型的可持续数据中心运行预测决策

Hanzhao Wang, Jingxuan Wu, Yumeng Li, Yu Pan, Guanting Chen

机构 * The University of Sydney Business School, The University of Sydney（悉尼大学商学院，悉尼大学）； University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）； Purdue University（普渡大学）

专题命中效率与部署：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.LG

AI总结本研究针对数据中心高能耗问题，提出基于LLM的预测调度系统，经合作验证可降低32%能耗、30%等待时间，为数据中心可持续运行提供实用方案。

2608.15127 2026-08-18 cs.OS cs.AI cs.DC cs.MA 新提交 90%

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

从大语言模型（LLM）推理到智能体工作负载：特征分析与服务系统启示

Chaokun Chang, Yukun Zhou, Kaihua Fu, Dakai An, Tianyu Feng, Hanfeng Lu, Sheng Yao, Pu Guo, Yinghao Yu, Yizhou Shan, Bo Li, Binhang Yuan, Wei Wang

专题命中效率与部署：LLM(title,title_cn)；分类 cs.AI

AI总结本文提出AgentSysBench基准套件，分析智能体工作负载与传统LLM服务的6项差异，据此开展的4项设计探索可实现延迟降低、效率提升、内存减少及冗余调用节省等效果。

2608.14065 2026-08-18 cs.SE cs.AI 版本更新 90%

Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency

重新思考自动程序修复：缺陷复杂度、缺陷定位与大语言模型成本效率的影响

Junchi Liu, Ali Bigdeli, Roya Daneshi, Atu Ambala, Sudipto Ghosh, Fabio Santos

专题命中效率与部署：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结本研究通过实证分析，发现中等复杂度缺陷可超50%由低成本LLM修复，不精确缺陷定位会扩大APR技术差距，高成本LLM与强推理设置并非总能提升成本效率，DeepSeek-V3.2成本效率最优。

Comments 20 pages, 6 figures, 10 tables. Accepted at ESEM 2026

2608.12921 2026-08-17 cs.MA cs.AI 版本更新 90%

Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference

通过因果推理发现基于大语言模型的多智能体系统的高效且可解释的通信拓扑

Junzhi Li, Peng He, Qirui Ji, Wei Wang, Lixiang Liu, Chuxiong Sun

专题命中效率与部署：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结该研究针对基于LLM的多智能体系统通信拓扑可解释性不足的问题，提出模型无关框架E2-Explainer，通过因果推理识别关键通信子图，在保持任务性能的同时降低了通信成本。

2608.12915 2026-08-14 cs.DC cs.AI 新提交 90%

InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers

InFactPlanner：可持续地理分布式大语言模型（LLM）数据中心规划

Nicoletta Tsiopani, Moysis Symeonides, George Pallis, Marios D. Dikaiakos

专题命中效率与部署：LLM(title,title_cn)；分类 cs.AI

AI总结 InFactPlanner是用于LLM推理的可持续地理分布式数据中心部署假设分析的决策支持框架，可通过多维度建模分析得出可持续性与延迟最优选择存在差异等结论。

Comments Author copy of paper published at 34th International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication System (MASCOTS2026)

2601.03645 2026-08-12 cs.CL cs.CY 90%

LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight

LLM-MC-Affect: 基于大语言模型的蒙特卡洛建模：情感轨迹与潜在模糊性的人际动态洞察

Yu-Zheng Lin, Bono Po-Jen Shih, John Paul Martin Encinas, Elizabeth Victoria Abraham Achom, Karan Himanshu Patel, Jesus Horacio Pacheco, Sicong Shao, Jyotikrishna Dass, Soheil Salehi, Pratik Satam

机构 * University of Arizona（亚利桑那大学）； Pennsylvania State University（宾夕法尼亚州立大学）； Universidad de Sonora（索尔纳大学）； University of North Dakota（北达科他大学）

专题命中效率与部署：LLM(title,title_cn)；分类 cs.CL

AI总结本文提出LLM-MC-Affect框架，通过概率建模方法，将情感视为连续的潜在概率分布，从而捕捉人际互动中的情感轨迹和潜在模糊性，为动态分析提供新的视角和方法。

Comments Accepted to the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)

2508.03611 2026-08-12 cs.DC cs.AI 版本更新 90%

Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling

Astrolabe：基于随机预测引导调度的大语言模型服务负载均衡

Wei Da, Evangelia Kalyvianaki

机构 * University of Cambridge（剑桥大学）

专题命中效率与部署：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结本文提出Astrolabe，一种用于LLM服务的随机预测引导调度器，结合响应长度估计等策略实现负载均衡，在多组基准测试中提升SLO容量、降低延迟并减少资源开销。

Comments 16 pages. Accepted at SYSTOR 2026. Camera-ready version with expanded evaluation and revisions. Previously circulated as "Block"; renamed "Astrolabe" to match the SYSTOR publication title

2608.07583 2026-08-11 stat.ML cs.LG 新提交 90%

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough

RouteGuard：当互补性不足时，对LLM多智能体系统中的路由增益进行认证

Anchen Sun, Kaiqi Yang

专题命中效率与部署：LLM(title,title_cn)；分类 cs.LG

AI总结针对LLM多智能体路由的部署问题，提出RouteGuard框架，通过分解增益、结合Le Cam下界等实现认证，在两个基准中验证了其有效性。

2608.09577 2026-08-11 cs.AI 新提交 90%

ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization

ElasticBack：通过耦合触发-规则优化实现LLM智能体技能中的隐蔽条件后门

Hao Sui, Simeng Qin, Jie Liao, Xiaojun Jia, Bing Chen, Yang Liu

专题命中效率与部署：LLM(title,title_cn)；分类 cs.AI

AI总结本研究提出ElasticBack，通过耦合触发-规则优化在LLM智能体技能中植入条件性单技能后门，实验显示其攻击性能优异且隐蔽性强，可推动技能供应链的防御研究。

1. 效率与部署 22368 篇

Toward Sustainable GenAI using Generation Directives for Carbon-Friendly Large Language Model Inference

The Human Factor in Detecting Errors of Large Language Models: A Systematic Literature Review and Future Research Directions

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition

LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models

AllTogether: Investigating the Efficacy of Spliced Prompt for Web Navigation using Large Language Models

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search

ChatGPT is on the Horizon: Could a Large Language Model be Suitable for Intelligent Traffic Safety Research and Applications?

FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

Jacobian-guided Noise Injection for Quantization Robustness in Large Language Models

SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models

Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized Models

Efficient Temporal Tokenization for Mobility Prediction with Large Language Models

Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2

Knowledge Distillation from Large Language Models for Household Energy Modeling

Filter bubbles and affective polarization in user-personalized large language model outputs

FormuEvo: LLM-Guided Evolution for Discovering Solver-Efficient Mixed-Integer Programming Formulations

Which Eviction Policy Should an LLM Cache Use? A Systematic Study Across Workloads, Capacities, and Encoders

LLM-Powered Predictive Decision-Making for Sustainable Data Center Operations

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency

Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference

InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers

LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight

Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling

RouteGuard: Certifying Routing Gain in LLM Multi-Agent Systems When Complementarity Is Not Enough

ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization

ToolChain: Efficient Action Space Navigation in Large Language Models with A Search