语言大模型 / LLM

ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models

Shixuan Li, Wei Yang, Peiyu Zhang, Xiongye Xiao, Defu Cao, Yuehan Qin, Xiaole Zhang, Yue Zhao, Paul Bogdan

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；foundation model(abstract)；prompting(abstract)

OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

Xing Hu, Yuan Cheng, Dawei Yang, Zukang Xu, Zhihang Yuan, Jiangyong Yu, Chen Xu, Zhe Jiang, Sifan Zhou

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Comments 10 Pages

AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model

Lipeng Ma, Weidong Yang, Yixuan Li, Ben Fei, Mingjie Zhou, Shuhao Li, Sihang Jiang, Bo Xu, Yanghua Xiao

专题命中 效率与部署 ：language model(title,abstract)；small language model(title,abstract)；LLM(abstract)；SLM(abstract)

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

Shaolei Zhang, Kehao Zhang, Qingkai Fang, Shoutao Guo, Yan Zhou, Xiaodong Liu, Yang Feng

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；foundation model(abstract)；instruction tuning(abstract)

Comments BayLing 2's online demo: http://nlp.ict.ac.cn/bayling/demo. BayLing 2's code and models: https://github.com/ictnlp/BayLing

FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models

Tao Fan, Guoqiang Ma, Yan Kang, Hanlin Gu, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang

专题命中 效率与部署 ：language model(title,abstract)；small language model(title,abstract)；LLM(abstract)；large language model(abstract)

ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization

Weibo Zhao, Yubin Shi, Xinyu Lyu, Wanchen Sui, Shen Li, Yong Li

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Comments Accepted at AAAI 2025

Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration

Wenjie Fu, Huandong Wang, Chen Gao, Guanghua Liu, Yong Li, Tao Jiang

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

Comments Repo: NeurIPS2024_SPV-MIA" target="_blank" rel="noopener">https://github.com/tsinghua-fib-lab/NeurIPS2024_SPV-MIA

Journal ref The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Compressing Large Language Models using Low Rank and Low Precision Decomposition

Rajarshi Saha, Naomi Sagan, Varun Srivastava, Andrea J. Goldsmith, Mert Pilanci

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Comments Accepted to The 38th Conference on Neural Information Processing Systems (NeurIPS 2024). [31 pages, 10 figures, 9 tables]

AutoTimes: Autoregressive Time Series Forecasters via Large Language Models

Yong Liu, Guo Qin, Xiangdong Huang, Jianmin Wang, Mingsheng Long

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；foundation model(abstract)

Pre-training Distillation for Large Language Models: A Design Space Exploration

Hao Peng, Xin Lv, Yushi Bai, Zijun Yao, Jiajie Zhang, Lei Hou, Juanzi Li

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Efficient Prompting for LLM-based Generative Internet of Things

Bin Xiao, Burak Kantarci, Jiawen Kang, Dusit Niyato, Mohsen Guizani

专题命中 效率与部署 ：LLM(title,abstract)；prompting(title,abstract)；large language model(abstract)；language model(abstract)

Comments 14 pages, 11 figures. IEEE Internet of Things Journal, 2024

Foundations of Large Language Model Compression -- Part 1: Weight Quantization

Sean I. Young

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Comments Preprint. 17 pages, 4 figures, 5 appendices

A Survey of Resource-efficient LLM and Multimodal Foundation Models

Mengwei Xu, Wangsong Yin, Dongqi Cai, Rongjie Yi, Daliang Xu, Qipeng Wang, Bingyang Wu, Yihao Zhao, Chen Yang, Shihe Wang, Qiyang Zhang, Zhenyan Lu, Li Zhang, Shangguang Wang, Yuanchun Li, Yunxin Liu, Xin Jin, Xuanzhe Liu

专题命中 效率与部署 ：LLM(title,abstract)；foundation model(title,abstract)；large language model(abstract)；language model(abstract)

Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation

Jingjing Xie, Yuxin Zhang, Mingbao Lin, Liujuan Cao, Rongrong Ji

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；instruction tuning(abstract)

Comments Accepted by ACMMM2024

HARE: HumAn pRiors, a key to small language model Efficiency

Lingyun Zhang, Bin jin, Gaojian Ge, Lunhui Liu, Xuewen Shen, Mingyong Wu, Houqian Zhang, Yongneng Jiang, Shiqi Chen, Shi Pu

专题命中 效率与部署 ：language model(title,abstract)；small language model(title,abstract)；large language model(abstract)；SLM(abstract)

SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models

Xudong Lu, Aojun Zhou, Yuhui Xu, Renrui Zhang, Peng Gao, Hongsheng Li

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Large Language Models are Effective Priors for Causal Graph Discovery

Victor-Alexandru Darvariu, Stephen Hailes, Mirco Musolesi

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, Ping Luo

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Comments ICLR 2024 Camera Ready

JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models

Jillian Fisher, Ximing Lu, Jaehun Jung, Liwei Jiang, Zaid Harchaoui, Yejin Choi

专题命中 效率与部署 ：language model(title,abstract)；small language model(title,abstract)；LLM(abstract)；large language model(abstract)

Comments Code is available at https://github.com/jfisher52/JAMDecoding

Small Language Models Improve Giants by Rewriting Their Outputs

Giorgos Vernikos, Arthur Bražinskas, Jakub Adamek, Jonathan Mallinson, Aliaksei Severyn, Eric Malmi

专题命中 效率与部署 ：language model(title,abstract)；small language model(title)；LLM(abstract)；large language model(abstract)

Comments Accepted at EACL 2024

QuIP: 2-Bit Quantization of Large Language Models With Guarantees

Jerry Chee, Yaohui Cai, Volodymyr Kuleshov, Christopher De Sa

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；post-training(abstract)

Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models

Jiang Zhang, Qiong Wu, Yiming Xu, Cheng Cao, Zheng Du, Konstantinos Psounis

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, Lili Qiu

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；instruction tuning(abstract)；prompting(abstract)

Comments Accepted at EMNLP 2023

PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation

Gaurav Sahu, Olga Vechtomova, Dzmitry Bahdanau, Issam H. Laradji

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

Comments Accepted to EMNLP 2023 (Long paper)

Sources of Hallucination by Large Language Models on Inference Tasks

Nick McKenna, Tianyi Li, Liang Cheng, Mohammad Javad Hosseini, Mark Johnson, Mark Steedman

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；pretraining(abstract)

Comments Findings of EMNLP 2023

Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment

评估小型语言模型用于前端路由：一个统一的基准和合成流量实验

Warren Johnson, Charles Lee

机构 * Plexor Labs（Plexor实验室） ； Project Autobots 纠错

专题命中 效率与部署 ：language model(title,abstract)；small language model(title,abstract)；SLM(abstract,comments)；LLM(abstract)

AI总结 本文通过统一基准和合成流量实验，评估小型语言模型在前端路由中的性能，发现Qwen-2.5-3B在准确率、延迟和成本上表现优异，但整体仍存在准确率与延迟的平衡问题。

Comments 23 pages, 1 figure, 9 tables. Article 8 in the TAAC Research Series. Code and data: https://github.com/micoverde/plexor-slm-frontdoor-rct

Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models

Guangji Bai, Zheng Chai, Chen Ling, Shiyu Wang, Jiaying Lu, Nan Zhang, Tingwei Shi, Ziyang Yu, Mengdan Zhu, Yifei Zhang, Xinyuan Song, Carl Yang, Yue Cheng, Liang Zhao

专题命中 效率与部署 ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)；pretraining(abstract)

Comments GitHub repo: https://github.com/tiingweii-shii/Awesome-Resource-Efficient-LLM-Papers

Does My README File Need To Be Updated? Exploring LLM-Based README Maintenance

我的 README 文件需要更新吗？探索基于 LLM 的 README 维护

Haoyu Gao, Hong Yi Lin, Christoph Treude, Gregory Gay, Mansooreh Zahedi

专题命中 效率与部署 ：LLM(title,title_cn)；large language model(abstract)；language model(abstract)

AI总结 本文提出了一种基于 LLM 的轻量级方法，用于在人机协作流程中精准更新 README 文件，以解决文档过时问题，并通过实验验证其有效性。

Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems

组织控制层：LLM代理系统执行边界的治理基础设施

Tianyu Shi, Yang Mo, Yiou Liu, Zhuonan Hao, Yin Wang, Wenzhuo Hu, Nan Yu, Meng Zhou, Jiangbo Yu

专题命中 效率与部署 ：LLM(title,title_cn)；prompting(abstract)

AI总结 针对LLM代理在执行边界产生的动作治理问题，提出组织控制层（OCL），通过策略执行和升级机制拦截生成动作，在不修改底层LLM生成器的情况下将不安全执行从88%降至接近零，同时将有效成功率从12%提升至96%。

Comments 13 pages, 2 figures

HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails

HoloAegis：冻结表示、拓扑推理：用于零样本大语言模型（LLM）护栏的最小参数安全流形

Tak Ho Alex Li, Kaijie Liu, Lik-Hang Lee, Kin Chung Ho, Ping Shum, Michael K. Ng

机构 * Hong Kong Baptist University（香港浸会大学） ； Guangdong Polytechnic Normal University（广东技术师范大学） ； Guangdong Institute of Digital Industry（广东数字产业研究院） ； The Hong Kong Polytechnic University（香港理工大学） ； The Education University of Hong Kong（香港教育大学） ； Southern University of Science and Technology（南方科技大学） 纠错

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

AI总结 HoloAegis是一种最小参数拓扑推理框架，通过冻结语义表示的纯几何推理实现零样本LLM安全护栏，在8个基准测试中达到最先进准确率，兼具低延迟、零冷启动数据和跨语言迁移能力。

Comments Preprint, August 2026. 10 tables, 2 figures