语言大模型 / LLM - arXivDaily 专题

2408.14134 2025-02-18 cs.LG cs.AI cs.CL cs.SI 90%

Exploring the Potential of Large Language Models for Heterophilic Graphs

Yuxia Wu, Shujie Li, Yuan Fang, Chuan Shi

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 by NAACL 2025

2309.02705 2025-02-06 cs.CL cs.AI cs.CR cs.LG 90%

Certifying LLM Safety against Adversarial Prompting

Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Aaron Jiaxun Li, Soheil Feizi, Himabindu Lakkaraju

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

Comments Accepted at COLM 2024: https://openreview.net/forum?id=9Ik05cycLq

2411.00154 2025-02-04 cs.CL cs.AI cs.LG 90%

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

Haritz Puerto, Martin Gubri, Sangdoo Yun, Seong Joon Oh

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 Findings of NAACL 2025. Our code is available at https://github.com/parameterlab/mia-scaling

2402.14875 2025-01-27 cs.CL cs.AI cs.CY cs.LG 90%

What's in a Name? Auditing Large Language Models for Race and Gender Bias

Alejandro Salinas, Amit Haim, Julian Nyarko

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 62 pages, 34 tables, 16 figures

2501.13831 2025-01-24 cs.CL cs.AI cs.LG 90%

Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing

Hao Zhang, Felix Stahlberg, Shankar Kumar

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 by ICASSP 2025

2501.02438 2025-01-07 cs.LG cs.AI cs.CL cs.DC 90%

Efficient Deployment of Large Language Models on Resource-constrained Devices

Zhiwei Yao, Yang Xu, Hongli Xu, Yunming Liao, Zuan Xie

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

2501.02342 2025-01-07 cs.LG cs.AI cs.CL cs.CV cs.HC 90%

Optimizing Small Language Models for In-Vehicle Function-Calling

Yahya Sowti Khiabani, Farris Atif, Chieh Hsu, Sven Stahlmann, Tobias Michels, Sebastian Kramer, Benedikt Heidrich, M. Saquib Sarfraz, Julian Merten, Faezeh Tafazzoli

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

2501.02018 2025-01-07 cs.CL cs.AI cs.CR cs.LG 90%

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs

Joao Fonseca, Andrew Bell, Julia Stoyanovich

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

2405.19026 2024-12-23 cs.LG cs.AI cs.CL cs.CR 90%

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

Andrew Zhao, Quentin Xu, Matthieu Lin, Shenzhi Wang, Yong-jin Liu, Zilong Zheng, Gao Huang

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 by the 39th Annual AAAI Conference on Artificial Intelligence (AAAI-25)

2412.15127 2024-12-20 cs.CL cs.AI cs.LG 90%

Adaptive Pruning for Large Language Models with Structural Importance Awareness

Haotian Zheng, Jinke Ren, Yushan Sun, Ruichen Zhang, Wenbo Zhang, Zhen Li, Dusit Niyato, Shuguang Cui, Yatong Han

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 12 pages, 6 figures, 12 tables

2404.08707 2024-12-17 cs.LG cs.AI cs.CL 90%

CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes

Haokun Zhao, Haixia Han, Jie Shi, Chengyu Du, Jiaqing Liang, Yanghua Xiao

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

2412.06849 2024-12-11 cs.LG cs.AI cs.CL 90%

GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model

Haotong Yang, Xiyuan Wang, Qian Tao, Shuxian Hu, Zhouchen Lin, Muhan 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 under review

2403.15112 2024-12-06 cs.CL cs.AI cs.LG 90%

Text Clustering with Large Language Model Embeddings

Alina Petukhova, João P. Matos-Carvalho, Nuno Fachada

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 The peer-reviewed version of this paper is published in the International Journal of Cognitive Computing in Engineering at https://doi.org/10.1016/j.ijcce.2024.11.004. This version is typeset by the authors and differs only in pagination and typographical detail

Journal ref International Journal of Cognitive Computing in Engineering, 6, pp. 100-108, 2025

2403.02253 2024-11-18 cs.CR cs.AI cs.CL cs.LG 90%

KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection

Yuexin Li, Chengyu Huang, Shumin Deng, Mei Lin Lock, Tri Cao, Nay Oo, Hoon Wei Lim, Bryan Hooi

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 by USENIX Security 2024

Journal ref 33rd USENIX Security Symposium (USENIX Security 2024), 793--810

2411.06084 2024-11-12 cs.LG cs.AI cs.CL 90%

Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques

Jahid Hasan

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

Comments 9 pages, 2 figures

2411.05046 2024-11-11 cs.CL cs.AI cs.LG 90%

PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training

Rongjie Yi, Xiang Li, Weikai Xie, Zhenyan Lu, Chenghua Wang, Ao Zhou, Shangguang Wang, Xiwen Zhang, Mengwei Xu

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

2406.07933 2024-11-01 cs.CL cs.AI cs.LG 90%

Large Language Model Unlearning via Embedding-Corrupted Prompts

Chris Yuhao Liu, Yaxuan Wang, Jeffrey Flanigan, Yang Liu

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 NeurIPS 2024 Poster

2404.11216 2024-10-23 cs.CL cs.AI cs.LG 90%

Position Engineering: Boosting Large Language Models through Positional Information Manipulation

Zhiyuan He, Huiqiang Jiang, Zilong Wang, Yuqing Yang, Luna Qiu, Lili Qiu

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

2410.14578 2024-10-21 cs.CL cs.AI cs.LG 90%

Large Language Models Are Overparameterized Text Encoders

Thennal D K, Tim Fischer, Chris Biemann

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 8 pages of content + 1 for limitations and ethical considerations, 14 pages in total including references and appendix, 5+1 figures

2406.16635 2024-10-18 cs.LG cs.AI cs.CL 90%

ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models

Yash Akhauri, Ahmed F AbouElhamayed, Jordan Dotzel, Zhiru Zhang, Alexander M Rush, Safeen Huda, Mohamed S Abdelfattah

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 EMNLP 2024 (Main, Long Paper)

2410.12013 2024-10-17 cs.CL cs.AI cs.LG 90%

MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

Yanyue Xie, Zhi Zhang, Ding Zhou, Cong Xie, Ziang Song, Xin Liu, Yanzhi Wang, Xue Lin, An Xu

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

2405.06001 2024-10-10 cs.LG cs.AI cs.CL 90%

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit

Ruihao Gong, Yang Yong, Shiqiao Gu, Yushi Huang, Chengtao Lv, Yunchen Zhang, Xianglong Liu, Dacheng Tao

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 by EMNLP 2024 Industry Track

2409.04464 2024-09-19 cs.CL cs.AI cs.LG math.OC 90%

Leveraging Large Language Models for Solving Rare MIP Challenges

Teng Wang, Wing-Yin Yu, Ruifeng She, Wenhan Yang, Taijie Chen, Jianping 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

2405.14366 2024-09-10 cs.CL cs.AI cs.LG 90%

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Akide Liu, Jing Liu, Zizheng Pan, Yefei He, Gholamreza Haffari, Bohan Zhuang

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 Project is available at https://minicache.vmv.re

2402.14846 2024-08-29 cs.CL cs.AI cs.LG 90%

Stick to your Role! Stability of Personal Values Expressed in Large Language Models

Grgur Kovač, Rémy Portelas, Masataka Sawayama, Peter Ford Dominey, Pierre-Yves Oudeyer

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 The project website and code are available at https://sites.google.com/view/llmvaluestability Published in PLOS ONE ( https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0309114 ), and a shorter version at CogSci 24 ( https://escholarship.org/uc/item/7w4823c6 )

Journal ref PLOS ONE, August 2024

2403.13000 2024-08-09 cs.LG cs.AI cs.CL cs.CR 90%

Duwak: Dual Watermarks in Large Language Models

Chaoyi Zhu, Jeroen Galjaard, Pin-Yu Chen, Lydia Y. Chen

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

2406.07368 2024-07-26 cs.CL cs.AI cs.LG 90%

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

Haoran You, Yichao Fu, Zheng Wang, Amir Yazdanbakhsh, Yingyan Celine Lin

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 by ICML 2024; 17 pages; 10 figures; 16 tables

2407.15351 2024-07-24 cs.LG cs.AI cs.CL 90%

LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation

Jiaxing Zhang, Jiayi Liu, Dongsheng Luo, Jennifer Neville, Hua Wei

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 Preprint Paper with 13 pages

2401.06692 2024-07-09 cs.CL cs.AI cs.LG 90%

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models

Gantavya Bhatt, Yifang Chen, Arnav M. Das, Jifan Zhang, Sang T. Truong, Stephen Mussmann, Yinglun Zhu, Jeffrey Bilmes, Simon S. Du, Kevin Jamieson, Jordan T. Ash, Robert D. Nowak

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

Comments Accepted to Findings of the Association for Computational Linguistics: ACL 2024

2407.03759 2024-07-08 cs.CL cs.AI cs.LG cs.NI 90%

Convolutional vs Large Language Models for Software Log Classification in Edge-Deployable Cellular Network Testing

Achintha Ihalage, Sayed M. Taheri, Faris Muhammad, Hamed Al-Raweshidy

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

1. 效率与部署 22188 篇

Exploring the Potential of Large Language Models for Heterophilic Graphs

Certifying LLM Safety against Adversarial Prompting

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

What's in a Name? Auditing Large Language Models for Race and Gender Bias

Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing

Efficient Deployment of Large Language Models on Resource-constrained Devices

Optimizing Small Language Models for In-Vehicle Function-Calling

Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs

DiveR-CT: Diversity-enhanced Red Teaming Large Language Model Assistants with Relaxing Constraints

Adaptive Pruning for Large Language Models with Structural Importance Awareness

CEM: A Data-Efficient Method for Large Language Models to Continue Evolving From Mistakes

GL-Fusion: Rethinking the Combination of Graph Neural Network and Large Language model

Text Clustering with Large Language Model Embeddings

KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection

Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques

PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training

Large Language Model Unlearning via Embedding-Corrupted Prompts

Position Engineering: Boosting Large Language Models through Positional Information Manipulation

Large Language Models Are Overparameterized Text Encoders

ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models

MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router

LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit

Leveraging Large Language Models for Solving Rare MIP Challenges

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Stick to your Role! Stability of Personal Values Expressed in Large Language Models

Duwak: Dual Watermarks in Large Language Models

When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models

LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models

Convolutional vs Large Language Models for Software Log Classification in Edge-Deployable Cellular Network Testing