语言大模型 / LLM - arXivDaily 专题

2404.10678 2024-04-17 cs.SE cs.LG 83%

Automating REST API Postman Test Cases Using LLM

S Deepika Sri, Mohammed Aadil S, Sanjjushri Varshini R, Raja CSP Raman, Gopinath Rajagopal, S Taranath Chan

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

2305.02869 2024-04-09 cs.CL 83%

Masked Structural Growth for 2x Faster Language Model Pre-training

Yiqun Yao, Zheng Zhang, Jing Li, Yequan Wang

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

Comments ICLR 2024 camera ready

2403.13301 2024-03-21 cs.HC cs.CL 83%

Reading Users' Minds from What They Say: An Investigation into LLM-based Empathic Mental Inference

Qihao Zhu, Leah Chong, Maria Yang, Jianxi Luo

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

Comments Submitted to IDETC-CIE2024

2403.12983 2024-03-21 cs.CV cs.LG 83%

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization

Xiang Meng, Shibal Ibrahim, Kayhan Behdin, Hussein Hazimeh, Natalia Ponomareva, Rahul Mazumder

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

2308.03449 2024-03-18 cs.CL 83%

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

Seungcheol Park, Hojun Choi, U Kang

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

2403.08481 2024-03-14 cs.LG cs.CR 83%

SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks

Guy Amit, Abigail Goldsteen, Ariel Farkash

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

Comments preliminary version

2310.20589 2024-03-12 cs.CL 83%

Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building

Omar Momen, David Arps, Laura Kallmeyer

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

Comments Accepted at the BabyLM shared task at CoNLL 2023

2312.10665 2023-12-19 cs.CV cs.CL 83%

Silkie: Preference Distillation for Large Visual Language Models

Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong

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

Comments Project page: https://vlf-silkie.github.io

2312.06685 2023-12-13 cs.AI 83%

Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models

Shitian Zhao, Zhuowan Li, Yadong Lu, Alan Yuille, Yan Wang

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

2310.07944 2023-12-05 cs.AI 83%

AutoRepo: A general framework for multi-modal LLM-based automated construction reporting

Hongxu Pu, Xincong Yang, Jing Li, Runhao Guo, Heng Li

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

Comments We believe that keeping this version of the paper publicly available may lead to confusion or misinterpretation regarding our current research direction and findings

2310.09930 2023-10-17 cs.CL 83%

FiLM: Fill-in Language Models for Any-Order Generation

Tianxiao Shen, Hao Peng, Ruoqi Shen, Yao Fu, Zaid Harchaoui, Yejin Choi

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

2310.05318 2023-10-17 cs.CL 83%

Resolving the Imbalance Issue in Hierarchical Disciplinary Topic Inference via LLM-based Data Augmentation

Xunxin Cai, Meng Xiao, Zhiyuan Ning, Yuanchun Zhou

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

Comments 6 pages, accepted by ICDM 2023

2309.16898 2023-10-02 cs.RO cs.CL cs.CV cs.HC 83%

A Sign Language Recognition System with Pepper, Lightweight-Transformer, and LLM

JongYoon Lim, Inkyu Sa, Bruce MacDonald, Ho Seok Ahn

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

2308.16259 2023-09-04 cs.LG cond-mat.mtrl-sci physics.chem-ph 83%

Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Prediction

Hongshuo Huang, Rishikesh Magar, Changwen Xu, Amir Barati Farimani

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

2308.05600 2023-08-11 cs.LG cs.CV 83%

NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search

Edouard Yvinec, Arnaud Dapogny, Kevin Bailly

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

2307.03897 2023-07-11 cs.CL 83%

Answering Ambiguous Questions via Iterative Prompting

Weiwei Sun, Hengyi Cai, Hongshen Chen, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Zhaochun Ren

专题命中效率与部署：prompting(title,abstract)；pretraining(abstract)；分类 cs.CL

Comments To be published in ACL 2023

2307.02628 2023-07-07 cs.CL 83%

SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Luciano Del Corro, Allie Del Giorno, Sahaj Agarwal, Bin Yu, Ahmed Awadallah, Subhabrata Mukherjee

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

2301.12507 2023-06-16 cs.AI 83%

Distilling Internet-Scale Vision-Language Models into Embodied Agents

Theodore Sumers, Kenneth Marino, Arun Ahuja, Rob Fergus, Ishita Dasgupta

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

Comments 9 pages, 7 figures. Presented at ICML 2023

2306.01061 2023-06-05 cs.CL cs.DB 83%

Reimagining Retrieval Augmented Language Models for Answering Queries

Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez, Richard James, Xi Victoria Lin, Alon Halevy, Scott Yih

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

2305.14847 2023-05-25 cs.CL 83%

Drafting Event Schemas using Language Models

Anisha Gunjal, Greg Durrett

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

2305.14002 2023-05-24 cs.CL 83%

Improving Language Models via Plug-and-Play Retrieval Feedback

Wenhao Yu, Zhihan Zhang, Zhenwen Liang, Meng Jiang, Ashish Sabharwal

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

2305.12458 2023-05-23 cs.CL 83%

Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model

Wenxi Tan

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

2305.12330 2023-05-23 cs.CL 83%

Task-agnostic Distillation of Encoder-Decoder Language Models

Chen Zhang, Yang Yang, Jingang Wang, Dawei Song

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

Comments 11 pages, 4 figure, 5 tables, work in progress. Code will be released

2305.04044 2023-05-09 cs.CL 83%

Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation

Kun Zhou, Yifan Li, Wayne Xin Zhao, Ji-Rong Wen

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

Comments 14 pages, Working in progress

2206.04959 2023-03-22 cs.LG cs.DC cs.MA 83%

Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models

Zhiquan Lai, Shengwei Li, Xudong Tang, Keshi Ge, Weijie Liu, Yabo Duan, Linbo Qiao, Dongsheng Li

专题命中效率与部署：foundation model(title,abstract)；pretraining(abstract)；分类 cs.LG

Journal ref IEEE Transactions on Parallel and Distributed Systems, vol. 34, no. 5, pp. 1466-1478, May 2023

2302.05406 2023-02-13 cs.CL 83%

Adversarial Transformer Language Models for Contextual Commonsense Inference

Pedro Colon-Hernandez, Henry Lieberman, Yida Xin, Claire Yin, Cynthia Breazeal, Peter Chin

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

Comments Submitted to Semantic Web Journal special edition. https://semantic-web-journal.org/content/adversarial-transformer-language-models-contextual-commonsense-inference-1

2210.12022 2022-10-24 cs.CL 83%

Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks

Laura Aina, Nikos Voskarides, Roi Blanco

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

Comments AACL-IJCNLP 2022

2205.12986 2022-10-20 cs.CL 83%

Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling

Kaitao Song, Yichong Leng, Xu Tan, Yicheng Zou, Tao Qin, Dongsheng Li

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

2206.03354 2022-06-10 cs.CL cs.CV 83%

cViL: Cross-Lingual Training of Vision-Language Models using Knowledge Distillation

Kshitij Gupta, Devansh Gautam, Radhika Mamidi

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

Comments Accepted at ICPR 2022; 9 pages

2112.08786 2022-05-04 cs.CL 83%

Efficient Hierarchical Domain Adaptation for Pretrained Language Models

Alexandra Chronopoulou, Matthew E. Peters, Jesse Dodge

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

Comments NAACL 2022 accepted paper camera ready version

1. 效率与部署 22456 篇

Automating REST API Postman Test Cases Using LLM

Masked Structural Growth for 2x Faster Language Model Pre-training

Reading Users' Minds from What They Say: An Investigation into LLM-based Empathic Mental Inference

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks

Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building

Silkie: Preference Distillation for Large Visual Language Models

Causal-CoG: A Causal-Effect Look at Context Generation for Boosting Multi-modal Language Models

AutoRepo: A general framework for multi-modal LLM-based automated construction reporting

FiLM: Fill-in Language Models for Any-Order Generation

Resolving the Imbalance Issue in Hierarchical Disciplinary Topic Inference via LLM-based Data Augmentation

A Sign Language Recognition System with Pepper, Lightweight-Transformer, and LLM

Materials Informatics Transformer: A Language Model for Interpretable Materials Properties Prediction

NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search

Answering Ambiguous Questions via Iterative Prompting

SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Distilling Internet-Scale Vision-Language Models into Embodied Agents

Reimagining Retrieval Augmented Language Models for Answering Queries

Drafting Event Schemas using Language Models

Improving Language Models via Plug-and-Play Retrieval Feedback

Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model

Task-agnostic Distillation of Encoder-Decoder Language Models

Diffusion-NAT: Self-Prompting Discrete Diffusion for Non-Autoregressive Text Generation

Merak: An Efficient Distributed DNN Training Framework with Automated 3D Parallelism for Giant Foundation Models

Adversarial Transformer Language Models for Contextual Commonsense Inference

Performance-Efficiency Trade-Offs in Adapting Language Models to Text Classification Tasks

Transcormer: Transformer for Sentence Scoring with Sliding Language Modeling

cViL: Cross-Lingual Training of Vision-Language Models using Knowledge Distillation

Efficient Hierarchical Domain Adaptation for Pretrained Language Models