语言大模型 / LLM - arXivDaily 专题

2408.06621 2025-04-28 cs.LG cs.CL 82%

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

Sungmin Cha, Sungjun Cho, Dasol Hwang, Moontae Lee

机构 * New York University（纽约大学）； University of Wisconsin-Madison（威斯康星大学麦迪逊分校）； LG AI Research（LG人工智能研究）； University of Illinois Chicago（伊利诺伊大学芝加哥分校）

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

Comments ICLR 2025 camera-ready version

2504.07104 2025-04-11 cs.IR cs.CL cs.LG 82%

Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking

Will LeVine, Bijan Varjavand

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

2411.19346 2025-04-11 cs.CV cs.CL cs.LG 82%

CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections

Mohamed Fazli Imam, Rufael Fedaku Marew, Jameel Hassan, Mustansar Fiaz, Alham Fikri Aji, Hisham Cholakkal

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

2504.06225 2025-04-09 cs.CL cs.LG 82%

Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation

Biao Zhang, Fedor Moiseev, Joshua Ainslie, Paul Suganthan, Min Ma, Surya Bhupatiraju, Fede Lebron, Orhan Firat, Armand Joulin, Zhe Dong

专题命中效率与部署：large language model(abstract)；language model(abstract)；instruction tuning(abstract)；pretraining(abstract)

2310.15117 2025-04-09 cs.AI cs.CL 82%

Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference

Aniket Vashishtha, Abbavaram Gowtham Reddy, Abhinav Kumar, Saketh Bachu, Vineeth N Balasubramanian, Amit Sharma

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

2410.03461 2025-03-17 cs.CL cs.LG 82%

Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation

Tobias Leemann, Periklis Petridis, Giuseppe Vietri, Dionysis Manousakas, Aaron Roth, Sergul Aydore

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

2503.03594 2025-03-11 cs.CL cs.AI 82%

Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs

Haoran Fan, Bin Li, Yixuan Weng, Shoujun Zhou

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

Comments 20 pages, 10 figures

2410.01524 2025-02-25 cs.CL cs.LG 82%

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Seanie Lee, Haebin Seong, Dong Bok Lee, Minki Kang, Xiaoyin Chen, Dominik Wagner, Yoshua Bengio, Juho Lee, Sung Ju Hwang

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

Comments ICLR 2025

2502.11096 2025-02-21 cs.AI cs.CL 82%

Mixture of Tunable Experts -- Behavior Modification of DeepSeek-R1 at Inference Time

Robert Dahlke, Henrik Klagges, Dan Zecha, Benjamin Merkel, Sven Rohr, Fabian Klemm

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

2502.06918 2025-02-12 cs.LG cs.AI 82%

Leveraging GPT-4o Efficiency for Detecting Rework Anomaly in Business Processes

Mohammad Derakhshan, Paolo Ceravolo, Fatemeh Mohammadi

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

Comments 14 pages, 5 images, 4 tables

2501.16075 2025-01-28 cs.CL cs.AI cs.IR 82%

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation

Maxime Louis, Hervé Déjean, Stéphane Clinchant

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

2410.17799 2025-01-06 cs.CL cs.AI cs.SD eess.AS 82%

OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation

Qinglin Zhang, Luyao Cheng, Chong Deng, Qian Chen, Wen Wang, Siqi Zheng, Jiaqing Liu, Hai Yu, Chaohong Tan, Zhihao Du, Shiliang Zhang

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

Comments Work in progress

2412.12129 2024-12-18 cs.LG cs.AI cs.CV 82%

SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout

Chiyu Max Jiang, Yijing Bai, Andre Cornman, Christopher Davis, Xiukun Huang, Hong Jeon, Sakshum Kulshrestha, John Lambert, Shuangyu Li, Xuanyu Zhou, Carlos Fuertes, Chang Yuan, Mingxing Tan, Yin Zhou, Dragomir Anguelov

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

Comments Accepted to NeurIPS 2024

2411.02617 2024-11-06 cs.CL cs.LG cs.NI 82%

TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network

Nouf Alabbasi, Omar Erak, Omar Alhussein, Ismail Lotfi, Sami Muhaidat, Merouane Debbah

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

2408.13296 2024-10-31 cs.LG cs.CL 82%

The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities

Venkatesh Balavadhani Parthasarathy, Ahtsham Zafar, Aafaq Khan, Arsalan Shahid

专题命中效率与部署：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

2402.08644 2024-10-22 cs.AI cs.CL 82%

Tandem Transformers for Inference Efficient LLMs

Aishwarya P S, Pranav Ajit Nair, Yashas Samaga, Toby Boyd, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli

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

2410.02173 2024-10-04 cs.LG cs.AI 82%

Efficiently Deploying LLMs with Controlled Risk

Michael J. Zellinger, Matt Thomson

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

Comments 10 pages

2408.15301 2024-10-02 cs.LG cs.AI 82%

The Uniqueness of LLaMA3-70B Series with Per-Channel Quantization

Minghai Qin

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

Comments 27 pages, 41 figures

2311.02262 2024-10-02 cs.CL cs.LG 82%

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs

Qingru Zhang, Chandan Singh, Liyuan Liu, Xiaodong Liu, Bin Yu, Jianfeng Gao, Tuo Zhao

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

Comments The 12th International Conference on Learning Representations (ICLR 2024)

2406.12246 2024-09-26 cs.LG cs.CL cs.CV 82%

TroL: Traversal of Layers for Large Language and Vision Models

Byung-Kwan Lee, Sangyun Chung, Chae Won Kim, Beomchan Park, Yong Man Ro

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

Comments EMNLP 2024. Code is available in https://github.com/ByungKwanLee/TroL

2408.06567 2024-08-14 cs.CL cs.AI 82%

AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies

Bo-Wen Zhang, Liangdong Wang, Ye Yuan, Jijie Li, Shuhao Gu, Mengdi Zhao, Xinya Wu, Guang Liu, Chengwei Wu, Hanyu Zhao, Li Du, Yiming Ju, Quanyue Ma, Yulong Ao, Yingli Zhao, Songhe Zhu, Zhou Cao, Dong Liang, Yonghua Lin, Ming Zhang, Shunfei Wang, Yanxin Zhou, Min Ye, Xuekai Chen, Xinyang Yu, Xiangjun Huang, Jian Yang

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

2406.10251 2024-08-02 cs.CL cs.AI cs.IR 82%

The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs

Mert Yazan, Suzan Verberne, Frederik Situmeang

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

Comments Accepted to the IR-RAG Workshop at SIGIR 2024

2311.02248 2024-06-17 cs.CL cs.AI eess.AS 82%

COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning

Jing Pan, Jian Wu, Yashesh Gaur, Sunit Sivasankaran, Zhuo Chen, Shujie Liu, Jinyu Li

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

2406.04523 2024-06-10 cs.CL cs.LG 82%

Proofread: Fixes All Errors with One Tap

Renjie Liu, Yanxiang Zhang, Yun Zhu, Haicheng Sun, Yuanbo Zhang, Michael Xuelin Huang, Shanqing Cai, Lei Meng, Shumin Zhai

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

Comments 8 pages, 3 figures, 2 tables

2405.14428 2024-05-24 cs.CL cs.LG 82%

Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs

Jaewoo Yang, Hayun Kim, Younghoon Kim

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

2404.07413 2024-04-12 cs.CL cs.AI 82%

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

Yikang Shen, Zhen Guo, Tianle Cai, Zengyi Qin

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

2403.06914 2024-03-13 cs.CL cs.AI 82%

MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning

Yichuan Li, Xiyao Ma, Sixing Lu, Kyumin Lee, Xiaohu Liu, Chenlei Guo

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

Comments ICLR 2024

2403.05931 2024-03-12 cs.CL cs.LG 82%

Thread Detection and Response Generation using Transformers with Prompt Optimisation

Kevin Joshua T, Arnav Agarwal, Shriya Sanjay, Yash Sarda, John Sahaya Rani Alex, Saurav Gupta, Sushant Kumar, Vishwanath Kamath

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

Comments 6 pages, 4 figures, submitted to 2024 IEEE International Conference on Signal Processing and Communications (SPCOM)

2402.18113 2024-02-29 cs.CL cs.AI 82%

Small But Funny: A Feedback-Driven Approach to Humor Distillation

Sahithya Ravi, Patrick Huber, Akshat Shrivastava, Aditya Sagar, Ahmed Aly, Vered Shwartz, Arash Einolghozati

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

2311.04254 2024-02-26 cs.AI cs.LG 82%

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation

Ruomeng Ding, Chaoyun Zhang, Lu Wang, Yong Xu, Minghua Ma, Wei Zhang, Si Qin, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang

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

Comments 17 pages, 5 figures

1. 效率与部署 22497 篇

Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs

Relevance Isn't All You Need: Scaling RAG Systems With Inference-Time Compute Via Multi-Criteria Reranking

CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections

Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation

Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference

Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation

Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Mixture of Tunable Experts -- Behavior Modification of DeepSeek-R1 at Inference Time

Leveraging GPT-4o Efficiency for Detecting Rework Anomaly in Business Processes

PISCO: Pretty Simple Compression for Retrieval-Augmented Generation

OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation

SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout

TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network

The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities

Tandem Transformers for Inference Efficient LLMs

Efficiently Deploying LLMs with Controlled Risk

The Uniqueness of LLaMA3-70B Series with Per-Channel Quantization

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs

TroL: Traversal of Layers for Large Language and Vision Models

AquilaMoE: Efficient Training for MoE Models with Scale-Up and Scale-Out Strategies

The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs

COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning

Proofread: Fixes All Errors with One Tap

Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs

JetMoE: Reaching Llama2 Performance with 0.1M Dollars

MEND: Meta dEmonstratioN Distillation for Efficient and Effective In-Context Learning

Thread Detection and Response Generation using Transformers with Prompt Optimisation

Small But Funny: A Feedback-Driven Approach to Humor Distillation

Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation