语言大模型 / LLM - arXivDaily 专题

2409.10525 2024-09-18 cs.MM cs.AI cs.CL 73%

"Is This It?": Towards Ecologically Valid Benchmarks for Situated Collaboration

Dan Bohus, Sean Andrist, Yuwei Bao, Eric Horvitz, Ann Paradiso

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2409.02239 2024-09-06 cs.SD cs.AI cs.CL eess.AS 73%

Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR

Xugang Lu, Peng Shen, Yu Tsao, Hisashi Kawai

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL、cs.AI

Comments Accepted to IEEE SLT 2024

2303.11783 2024-09-05 q-bio.BM cs.AI cs.LG 73%

CCPL: Cross-modal Contrastive Protein Learning

Jiangbin Zheng, Stan Z. Li

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.AI、cs.LG

Comments Accepted to ICPR 2024

2409.00347 2024-09-04 cs.LG cs.CL 73%

Chatting Up Attachment: Using LLMs to Predict Adult Bonds

Paulo Soares, Sean McCurdy, Andrew J. Gerber, Peter Fonagy

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

2409.00331 2024-09-04 cs.CL cs.AI 73%

WikiCausal: Corpus and Evaluation Framework for Causal Knowledge Graph Construction

Oktie Hassanzadeh

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Extended version; poster paper accepted at ISWC 2024

2406.04952 2024-08-30 cs.CL cs.AI 73%

Quantifying Geospatial in the Common Crawl Corpus

Ilya Ilyankou, Meihui Wang, Stefano Cavazzi, James Haworth

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted as a poster to ACM SIGSPATIAL 2024

2408.10392 2024-08-21 cs.CL cs.LG 73%

Value Alignment from Unstructured Text

Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Manish Nagireddy, Pierre Dognin, Kush R. Varshney

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

2312.13303 2024-08-14 cs.LG cs.AI 73%

RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios

Wenhao Ding, Yulong Cao, Ding Zhao, Chaowei Xiao, Marco Pavone

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments Accepted by ECCV 2024, Oral

2408.04303 2024-08-09 cs.CL cs.LG 73%

Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP

François Remy, Pieter Delobelle, Hayastan Avetisyan, Alfiya Khabibullina, Miryam de Lhoneux, Thomas Demeester

专题命中预训练与数据：LLM(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments Accepted at COLM 2024

2408.03319 2024-08-07 cs.CL cs.AI 73%

Training LLMs to Recognize Hedges in Spontaneous Narratives

Amie J. Paige, Adil Soubki, John Murzaku, Owen Rambow, Susan E. Brennan

专题命中预训练与数据：LLM(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments Amie Paige, Adil Soubki, and John Murzaku contributed equally to this study

Journal ref SIGDIAL 2024

2403.02504 2024-08-05 cs.CL cs.AI 73%

A Tutorial on the Pretrain-Finetune Paradigm for Natural Language Processing

Yu Wang, Wen Qu

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL、cs.AI

Comments 29 pages, 6 figures, 3 tables

2408.00144 2024-08-02 cs.CL cs.AI 73%

Distributed In-Context Learning under Non-IID Among Clients

Siqi Liang, Sumyeong Ahn, Jiayu Zhou

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 12 pages

2407.20445 2024-07-31 cs.SD cs.AI cs.LG eess.AS 73%

Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation

Junda Wu, Zachary Novack, Amit Namburi, Jiaheng Dai, Hao-Wen Dong, Zhouhang Xie, Carol Chen, Julian McAuley

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 6 pages

2407.20256 2024-07-31 cs.DB cs.AI cs.LG 73%

Making LLMs Work for Enterprise Data Tasks

Çağatay Demiralp, Fabian Wenz, Peter Baile Chen, Moe Kayali, Nesime Tatbul, Michael Stonebraker

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments Poster at North East Database Day 2024

2401.06461 2024-07-31 cs.SE cs.AI cs.CL 73%

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers

Yuling Shi, Hongyu Zhang, Chengcheng Wan, Xiaodong Gu

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by the 47th International Conference on Software Engineering (ICSE 2025). Code available at https://github.com/YerbaPage/DetectCodeGPT

2407.19262 2024-07-30 cs.CL cs.LG 73%

Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications

Till Speicher, Mohammad Aflah Khan, Qinyuan Wu, Vedant Nanda, Soumi Das, Bishwamittra Ghosh, Krishna P. Gummadi, Evimaria Terzi

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

2407.19173 2024-07-30 cs.CL cs.AI 73%

FarSSiBERT: A Novel Transformer-based Model for Semantic Similarity Measurement of Persian Social Networks Informal Texts

Seyed Mojtaba Sadjadi, Zeinab Rajabi, Leila Rabiei, Mohammad-Shahram Moin

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2305.12517 2024-07-25 cs.CL cs.IR cs.LG 73%

Description-Based Text Similarity

Shauli Ravfogel, Valentina Pyatkin, Amir DN Cohen, Avshalom Manevich, Yoav Goldberg

专题命中预训练与数据：LLM(abstract)；prompting(abstract)；分类 cs.CL、cs.LG

Comments Accepted in COLM 2024

2407.15130 2024-07-24 cs.CL cs.AI 73%

DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer

Jinfeng Wei, Xiaofeng Zhang

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2404.07202 2024-07-19 cs.CV cs.AI cs.CL 73%

UMBRAE: Unified Multimodal Brain Decoding

Weihao Xia, Raoul de Charette, Cengiz Öztireli, Jing-Hao Xue

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments ECCV 2024. Project: https://weihaox.github.io/UMBRAE

2309.12426 2024-07-11 cs.CL cs.AI 73%

Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges

Vinay Samuel, Houda Aynaou, Arijit Ghosh Chowdhury, Karthik Venkat Ramanan, Aman Chadha

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments ACL 2024 SRW

2407.03942 2024-07-08 cs.AI cs.CL cs.HC 73%

Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data

Zihui Gu, Xingwu Sun, Fengzong Lian, Zhanhui Kang, Cheng-Zhong Xu, Ju Fan

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Journal ref AAAI 2024

2407.00361 2024-07-02 cs.CL cs.AI 73%

From RAG to RICHES: Retrieval Interlaced with Sequence Generation

Palak Jain, Livio Baldini Soares, Tom Kwiatkowski

专题命中预训练与数据：LLM(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Comments 18 pages, 3 figures, Preprint

2406.18856 2024-06-28 cs.CL cs.AI cs.CE 73%

FFN: a Fine-grained Chinese-English Financial Domain Parallel Corpus

Yuxin Fu, Shijing Si, Leyi Mai, Xi-ang Li

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments a simplified version of this paper is accepted by International Conference on Asian Language Processing 2024

2406.18305 2024-06-27 cs.CL cs.AI 73%

S3: A Simple Strong Sample-effective Multimodal Dialog System

Elisei Rykov, Egor Malkershin, Alexander Panchenko

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2406.18078 2024-06-27 cs.CL cs.AI 73%

Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction

Yice Zhang, Jie Zeng, Weiming Hu, Ziyi Wang, Shiwei Chen, Ruifeng Xu

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ACL 2024 Main Conference

2406.14785 2024-06-24 cs.CL cs.LG 73%

Understanding Finetuning for Factual Knowledge Extraction

Gaurav Ghosal, Tatsunori Hashimoto, Aditi Raghunathan

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL、cs.LG

Comments To appear in ICML 2024

2406.11930 2024-06-19 cs.SE cs.AI cs.CL 73%

A Critical Study of What Code-LLMs (Do Not) Learn

Abhinav Anand, Shweta Verma, Krishna Narasimhan, Mira Mezini

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2405.08553 2024-06-05 cs.LG cs.CL 73%

Improving Transformers with Dynamically Composable Multi-Head Attention

Da Xiao, Qingye Meng, Shengping Li, Xingyuan Yuan

专题命中预训练与数据：language model(abstract)；pretraining(abstract)；分类 cs.CL、cs.LG

Comments Accepted to the 41st International Conference on Machine Learning (ICML'24 oral)

2310.18913 2024-05-30 cs.CL cs.AI stat.ML 73%

Debiasing Algorithm through Model Adaptation

Tomasz Limisiewicz, David Mareček, Tomáš Musil

专题命中预训练与数据：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to ICLR 2024

1. 预训练与数据 12460 篇

"Is This It?": Towards Ecologically Valid Benchmarks for Situated Collaboration

Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR

CCPL: Cross-modal Contrastive Protein Learning

Chatting Up Attachment: Using LLMs to Predict Adult Bonds

WikiCausal: Corpus and Evaluation Framework for Causal Knowledge Graph Construction

Quantifying Geospatial in the Common Crawl Corpus

Value Alignment from Unstructured Text

RealGen: Retrieval Augmented Generation for Controllable Traffic Scenarios

Trans-Tokenization and Cross-lingual Vocabulary Transfers: Language Adaptation of LLMs for Low-Resource NLP

Training LLMs to Recognize Hedges in Spontaneous Narratives

A Tutorial on the Pretrain-Finetune Paradigm for Natural Language Processing

Distributed In-Context Learning under Non-IID Among Clients

Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation

Making LLMs Work for Enterprise Data Tasks

Between Lines of Code: Unraveling the Distinct Patterns of Machine and Human Programmers

Understanding Memorisation in LLMs: Dynamics, Influencing Factors, and Implications

FarSSiBERT: A Novel Transformer-based Model for Semantic Similarity Measurement of Persian Social Networks Informal Texts

Description-Based Text Similarity

DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer

UMBRAE: Unified Multimodal Brain Decoding

Can LLMs Augment Low-Resource Reading Comprehension Datasets? Opportunities and Challenges

Diverse and Fine-Grained Instruction-Following Ability Exploration with Synthetic Data

From RAG to RICHES: Retrieval Interlaced with Sequence Generation

FFN: a Fine-grained Chinese-English Financial Domain Parallel Corpus

S3: A Simple Strong Sample-effective Multimodal Dialog System

Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction

Understanding Finetuning for Factual Knowledge Extraction

A Critical Study of What Code-LLMs (Do Not) Learn

Improving Transformers with Dynamically Composable Multi-Head Attention

Debiasing Algorithm through Model Adaptation