语言大模型 / LLM - arXivDaily 专题

2409.13421 2024-09-23 cs.LG cs.SY eess.SY 70%

State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?

Ingvar Ziemann, Nikolai Matni, George J. Pappas

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.LG

2409.11902 2024-09-19 cs.LG 70%

Less Memory Means smaller GPUs: Backpropagation with Compressed Activations

Daniel Barley, Holger Fröning

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Presented at ITEM workshop co-located with ECML PKDD 2024, Vilnius LT

2409.11192 2024-09-18 cs.CY cs.AI cs.HC 70%

Towards Ethical Personal AI Applications: Practical Considerations for AI Assistants with Long-Term Memory

Eunhae Lee

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

2402.03824 2024-09-16 cs.AI 70%

A call for embodied AI

Giuseppe Paolo, Jonas Gonzalez-Billandon, Balázs Kégl

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Published in ICML 2024 Position paper track

Journal ref PMLR 235:39493-39508, 2024

2407.03627 2024-09-10 cs.CL 70%

DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation

Taeho Hwang, Soyeong Jeong, Sukmin Cho, SeungYoon Han, Jong C. Park

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 20 pages

Journal ref KnowledgeNLP@ACL 2024

2405.14213 2024-08-27 cs.CV cs.CL 70%

From Text to Pixel: Advancing Long-Context Understanding in MLLMs

Yujie Lu, Xiujun Li, Tsu-Jui Fu, Miguel Eckstein, William Yang Wang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2408.11490 2024-08-22 cs.CL 70%

DocTabQA: Answering Questions from Long Documents Using Tables

Haochen Wang, Kai Hu, Haoyu Dong, Liangcai Gao

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 18 pages,5 figures

2408.05506 2024-08-13 cs.CL 70%

Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers

MohammadReza Ebrahimi, Sunny Panchal, Roland Memisevic

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Published as a conference paper at COLM 2024

2408.03675 2024-08-09 cs.CL 70%

NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time

Yilong Chen, Guoxia Wang, Junyuan Shang, Shiyao Cui, Zhenyu Zhang, Tingwen Liu, Shuohuan Wang, Yu Sun, Dianhai Yu, Hua Wu

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted by ACL 2024 (main conference, long paper)

2407.15021 2024-07-23 cs.CL 70%

Enhancing Incremental Summarization with Structured Representations

EunJeong Hwang, Yichao Zhou, James Bradley Wendt, Beliz Gunel, Nguyen Vo, Jing Xie, Sandeep Tata

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2407.14885 2024-07-23 cs.CL cs.CV 70%

Falcon2-11B Technical Report

Quentin Malartic, Nilabhra Roy Chowdhury, Ruxandra Cojocaru, Mugariya Farooq, Giulia Campesan, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Ankit Singh, Maksim Velikanov, Basma El Amel Boussaha, Mohammed Al-Yafeai, Hamza Alobeidli, Leen Al Qadi, Mohamed El Amine Seddik, Kirill Fedyanin, Reda Alami, Hakim Hacid

专题命中长上下文与记忆：language model(abstract)；foundation model(abstract)；分类 cs.CL

2407.08454 2024-07-23 cs.CL 70%

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

Zheng Wang, Boxiao Jin, Zhongzhi Yu, Minjia Zhang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2407.13143 2024-07-19 cs.LG cs.AR cs.DC 70%

Integrated Hardware Architecture and Device Placement Search

Irene Wang, Jakub Tarnawski, Amar Phanishayee, Divya Mahajan

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments Accepted at the 41st International Conference on Machine Learning (ICML), 2024

2406.18139 2024-06-27 cs.CL cs.CV 70%

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

Zhongwei Wan, Ziang Wu, Che Liu, Jinfa Huang, Zhihong Zhu, Peng Jin, Longyue Wang, Li Yuan

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2406.17375 2024-06-26 cs.CL 70%

An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla

Jayanta Sadhu, Ayan Antik Khan, Abhik Bhattacharjee, Rifat Shahriyar

专题命中长上下文与记忆：language model(abstract)；prompting(abstract)；分类 cs.CL

Comments Accepted in Findings of ACL, 2024

2406.15325 2024-06-24 cs.AI cs.SE 70%

Bug In the Code Stack: Can LLMs Find Bugs in Large Python Code Stacks

Hokyung Lee, Sumanyu Sharma, Bing Hu

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 8 pages

2308.14508 2024-06-21 cs.CL 70%

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments ACL 2024

2406.06125 2024-06-11 cs.CL 70%

Verifiable Generation with Subsentence-Level Fine-Grained Citations

Shuyang Cao, Lu Wang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments NAACL 2024 Findings

2312.06924 2024-06-10 cs.CL 70%

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack

Yu Fu, Yufei Li, Wen Xiao, Cong Liu, Yue Dong

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to ACL2024 main

2405.18740 2024-05-30 cs.CL 70%

Reverse Image Retrieval Cues Parametric Memory in Multimodal LLMs

Jialiang Xu, Michael Moor, Jure Leskovec

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2405.16571 2024-05-28 cs.CL 70%

A Preliminary Empirical Study on Prompt-based Unsupervised Keyphrase Extraction

Mingyang Song, Yi Feng, Liping Jing

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments work in progress

2405.14591 2024-05-24 cs.CL 70%

Base of RoPE Bounds Context Length

Xin Men, Mingyu Xu, Bingning Wang, Qingyu Zhang, Hongyu Lin, Xianpei Han, Weipeng Chen

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 17 pages

2405.07035 2024-05-16 cs.CL 70%

A Turkish Educational Crossword Puzzle Generator

Kamyar Zeinalipour, Yusuf Gökberk Keptiğ, Marco Maggini, Leonardo Rigutini, Marco Gori

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments This paper has been accepted for presentation at AIED2024 LBR

2404.15574 2024-04-25 cs.CL 70%

Retrieval Head Mechanistically Explains Long-Context Factuality

Wenhao Wu, Yizhong Wang, Guangxuan Xiao, Hao Peng, Yao Fu

专题命中长上下文与记忆：language model(abstract)；pretraining(abstract)；分类 cs.CL

Comments Preprint

2404.13781 2024-04-23 cs.CL cs.IR 70%

Evaluating Retrieval Quality in Retrieval-Augmented Generation

Alireza Salemi, Hamed Zamani

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2311.11547 2024-04-17 cs.AI cs.SE 70%

Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT

Abdelkarim El-Hajjami, Nicolas Fafin, Camille Salinesi

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

2404.05446 2024-04-09 cs.CL 70%

XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies

Xuanfan Ni, Hengyi Cai, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Piji Li

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Work in progress

2404.02835 2024-04-04 cs.CL 70%

Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison

Maxime Bouthors, Josep Crego, Francois Yvon

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2403.11439 2024-03-19 cs.CL 70%

StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation

Jinpeng Li, Zekai Zhang, Quan Tu, Xin Cheng, Dongyan Zhao, Rui Yan

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2401.10910 2024-03-04 q-bio.NC cs.AI 70%

Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior

Jason Toy, Josh MacAdam, Phil Tabor

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments 9 pages, 4 figures

1. 长上下文与记忆 4789 篇

State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?

Less Memory Means smaller GPUs: Backpropagation with Compressed Activations

Towards Ethical Personal AI Applications: Practical Considerations for AI Assistants with Long-Term Memory

A call for embodied AI

DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation

From Text to Pixel: Advancing Long-Context Understanding in MLLMs

DocTabQA: Answering Questions from Long Documents Using Tables

Your Context Is Not an Array: Unveiling Random Access Limitations in Transformers

NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time

Enhancing Incremental Summarization with Structured Representations

Falcon2-11B Technical Report

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

Integrated Hardware Architecture and Device Placement Search

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference

An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla

Bug In the Code Stack: Can LLMs Find Bugs in Large Python Code Stacks

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Verifiable Generation with Subsentence-Level Fine-Grained Citations

Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack

Reverse Image Retrieval Cues Parametric Memory in Multimodal LLMs

A Preliminary Empirical Study on Prompt-based Unsupervised Keyphrase Extraction

Base of RoPE Bounds Context Length

A Turkish Educational Crossword Puzzle Generator

Retrieval Head Mechanistically Explains Long-Context Factuality

Evaluating Retrieval Quality in Retrieval-Augmented Generation

Which AI Technique Is Better to Classify Requirements? An Experiment with SVM, LSTM, and ChatGPT

XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies

Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison

StyleChat: Learning Recitation-Augmented Memory in LLMs for Stylized Dialogue Generation

Metacognition is all you need? Using Introspection in Generative Agents to Improve Goal-directed Behavior