语言大模型 / LLM - arXivDaily 专题

2410.03111 2024-10-07 cs.LG cs.AI cs.CL 80%

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy

Rongzhi Zhang, Kuang Wang, Liyuan Liu, Shuohang Wang, Hao Cheng, Chao Zhang, Yelong Shen

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

Comments 15 pages, 4 figures

2410.02725 2024-10-04 cs.CL cs.AI cs.LG 80%

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

Rohin Manvi, Anikait Singh, Stefano Ermon

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

2409.05152 2024-10-03 cs.CL cs.AI cs.DB cs.IR cs.LG 80%

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

Jintian Zhang, Cheng Peng, Mengshu Sun, Xiang Chen, Lei Liang, Zhiqiang Zhang, Jun Zhou, Huajun Chen, Ningyu Zhang

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

Comments EMNLP 2024 Findings; code is available at https://github.com/zjunlp/OneGen

2409.04081 2024-10-03 cs.CL cs.AI cs.HC cs.LG 80%

UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity

Yicheng Fu, Raviteja Anantha, Prabal Vashisht, Jianpeng Cheng, Etai Littwin

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

2409.11424 2024-09-19 cs.AR 80%

LlamaF: An Efficient Llama2 Architecture Accelerator on Embedded FPGAs

Han Xu, Yutong Li, Shihao Ji

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

2409.04831 2024-09-10 cs.SE cs.AI cs.CL cs.CR cs.LG 80%

MILE: A Mutation Testing Framework of In-Context Learning Systems

Zeming Wei, Yihao Zhang, Meng Sun

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

2408.13621 2024-08-28 cs.CV cs.AI cs.CL cs.LG 80%

Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models

Sakhinana Sagar Srinivas, Geethan Sannidhi, Sreeja Gangasani, Chidaksh Ravuru, Venkataramana Runkana

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

Comments Published at Deployable AI (DAI) Workshop at AAAI-2024

2408.11865 2024-08-23 cs.CL cs.AI cs.LG 80%

How Susceptible are LLMs to Influence in Prompts?

Sotiris Anagnostidis, Jannis Bulian

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

2402.07812 2024-08-09 cs.CL cs.AI cs.IR cs.LG 80%

Retrieval Augmented Thought Process for Private Data Handling in Healthcare

Thomas Pouplin, Hao Sun, Samuel Holt, Mihaela van der Schaar

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

Comments 17 pages, 18 figures

2309.01249 2024-08-06 cs.AI cs.CL cs.LG 80%

Large AI Model Empowered Multimodal Semantic Communications

Feibo Jiang, Li Dong, Yubo Peng, Kezhi Wang, Kun Yang, Cunhua Pan, Xiaohu You

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

Comments Accepted by IEEE CM

2408.01417 2024-08-05 cs.CL cs.AI cs.CV cs.LG 80%

Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs

Yilun Hua, Yoav Artzi

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

Comments Accepted to COLM 2024

2405.17430 2024-07-30 cs.CV cs.AI cs.CL cs.LG 80%

Matryoshka Multimodal Models

Mu Cai, Jianwei Yang, Jianfeng Gao, Yong Jae Lee

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

Comments Project Page: https://matryoshka-mm.github.io/

2407.14622 2024-07-23 cs.LG cs.AI cs.CL 80%

BOND: Aligning LLMs with Best-of-N Distillation

Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shariari, Sarah Perrin, Abe Friesen, Geoffrey Cideron, Sertan Girgin, Piotr Stanczyk, Andrea Michi, Danila Sinopalnikov, Sabela Ramos, Amélie Héliou, Aliaksei Severyn, Matt Hoffman, Nikola Momchev, Olivier Bachem

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

2407.12866 2024-07-19 cs.CL cs.AI cs.LG 80%

Beyond KV Caching: Shared Attention for Efficient LLMs

Bingli Liao, Danilo Vasconcellos Vargas

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

2407.11030 2024-07-17 cs.LG cs.AI cs.CL 80%

DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs

Zhen Tan, Daize Dong, Xinyu Zhao, Jie Peng, Yu Cheng, Tianlong Chen

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

2407.09527 2024-07-16 cs.CV cs.AI cs.CL cs.LG 80%

BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks

Jacob Nielsen, Peter Schneider-Kamp

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

Comments 17 pages, 4 Tables, 14 grafs. Accepted to DeLTA

2403.02181 2024-07-10 cs.CL cs.AI cs.LG 80%

Not All Layers of LLMs Are Necessary During Inference

Siqi Fan, Xin Jiang, Xiang Li, Xuying Meng, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang, Zhongyuan Wang

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

2406.10101 2024-06-18 cs.SE 80%

Requirements are All You Need: From Requirements to Code with LLMs

Bingyang Wei

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

2406.10290 2024-06-18 cs.CL cs.AI cs.LG 80%

MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases

Rithesh Murthy, Liangwei Yang, Juntao Tan, Tulika Manoj Awalgaonkar, Yilun Zhou, Shelby Heinecke, Sachin Desai, Jason Wu, Ran Xu, Sarah Tan, Jianguo Zhang, Zhiwei Liu, Shirley Kokane, Zuxin Liu, Ming Zhu, Huan Wang, Caiming Xiong, Silvio Savarese

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

2405.20835 2024-06-06 cs.LG cs.AI cs.CL 80%

Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs

Davide Paglieri, Saurabh Dash, Tim Rocktäschel, Jack Parker-Holder

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

2312.17025 2024-06-06 cs.CL cs.AI cs.LG cs.SE 80%

Experiential Co-Learning of Software-Developing Agents

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, Yifei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

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

Comments Accepted to ACL 2024, https://github.com/OpenBMB/ChatDev

2402.09723 2024-06-03 stat.ML cs.AI cs.CL cs.LG 80%

Efficient Prompt Optimization Through the Lens of Best Arm Identification

Chengshuai Shi, Kun Yang, Zihan Chen, Jundong Li, Jing Yang, Cong Shen

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

2402.16354 2024-05-28 cs.LG cs.AI cs.CL 80%

Language-guided Skill Learning with Temporal Variational Inference

Haotian Fu, Pratyusha Sharma, Elias Stengel-Eskin, George Konidaris, Nicolas Le Roux, Marc-Alexandre Côté, Xingdi Yuan

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

Comments ICML 2024

2311.06243 2024-04-30 cs.LG cs.AI cs.CL cs.CV 80%

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Weiyang Liu, Zeju Qiu, Yao Feng, Yuliang Xiu, Yuxuan Xue, Longhui Yu, Haiwen Feng, Zhen Liu, Juyeon Heo, Songyou Peng, Yandong Wen, Michael J. Black, Adrian Weller, Bernhard Schölkopf

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

Comments ICLR 2024 (v2: 34 pages, 19 figures)

2404.12596 2024-04-22 cs.CL cs.AI cs.LG 80%

Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation

Lasal Jayawardena, Prasan Yapa

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

Comments Published in: 2024 5th International Conference on Advancements in Computational Sciences (ICACS) with IEEE

2402.01643 2024-04-16 cs.CL cs.AI cs.LG 80%

L-TUNING: Synchronized Label Tuning for Prompt and Prefix in LLMs

Md. Kowsher, Md. Shohanur Islam Sobuj, Asif Mahmud, Nusrat Jahan Prottasha, Prakash Bhat

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

Comments Published in the ICLR TinyPaper track

2404.07775 2024-04-12 cs.CL cs.AI cs.LG 80%

Discourse-Aware In-Context Learning for Temporal Expression Normalization

Akash Kumar Gautam, Lukas Lange, Jannik Strötgen

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

Comments Accepted at NAACL 2024

2304.14364 2024-04-05 cs.CL cs.AI cs.LG 80%

CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants

Albert Yu Sun, Varun Nair, Elliot Schumacher, Anitha Kannan

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

Comments To appear in NAACL 2024

2402.18700 2024-04-03 cs.CL cs.AI cs.LG 80%

Learning to Compress Prompt in Natural Language Formats

Yu-Neng Chuang, Tianwei Xing, Chia-Yuan Chang, Zirui Liu, Xun Chen, Xia Hu

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

2303.16749 2024-02-26 cs.SE cs.AI cs.CL cs.LG 80%

Improving Code Generation by Training with Natural Language Feedback

Angelica Chen, Jérémy Scheurer, Tomasz Korbak, Jon Ander Campos, Jun Shern Chan, Samuel R. Bowman, Kyunghyun Cho, Ethan Perez

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

Comments Published in (and superceded by) TMLR: https://openreview.net/forum?id=xo3hI5MwvU

1. 效率与部署 22531 篇

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy

Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

UI-JEPA: Towards Active Perception of User Intent through Onscreen User Activity

LlamaF: An Efficient Llama2 Architecture Accelerator on Embedded FPGAs

MILE: A Mutation Testing Framework of In-Context Learning Systems

Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models

How Susceptible are LLMs to Influence in Prompts?

Retrieval Augmented Thought Process for Private Data Handling in Healthcare

Large AI Model Empowered Multimodal Semantic Communications

Talk Less, Interact Better: Evaluating In-context Conversational Adaptation in Multimodal LLMs

Matryoshka Multimodal Models

BOND: Aligning LLMs with Best-of-N Distillation

Beyond KV Caching: Shared Attention for Efficient LLMs

DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs

BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks

Not All Layers of LLMs Are Necessary During Inference

Requirements are All You Need: From Requirements to Code with LLMs

MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases

Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs

Experiential Co-Learning of Software-Developing Agents

Efficient Prompt Optimization Through the Lens of Best Arm Identification

Language-guided Skill Learning with Temporal Variational Inference

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

Parameter Efficient Diverse Paraphrase Generation Using Sequence-Level Knowledge Distillation

L-TUNING: Synchronized Label Tuning for Prompt and Prefix in LLMs

Discourse-Aware In-Context Learning for Temporal Expression Normalization

CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants

Learning to Compress Prompt in Natural Language Formats

Improving Code Generation by Training with Natural Language Feedback