语言大模型 / LLM - arXivDaily 专题

2403.03102 2024-10-15 cs.CL cs.AI 73%

"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning

Chuanqi Cheng, Quan Tu, Shuo Shang, Cunli Mao, Zhengtao Yu, Wei Wu, Rui Yan

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted by EMNLP 2024

2409.20042 2024-10-11 cs.CL cs.AI 73%

Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback

Menna Fateen, Bo Wang, Tsunenori Mine

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2410.06508 2024-10-10 cs.LG cs.CL 73%

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

Xiyao Wang, Linfeng Song, Ye Tian, Dian Yu, Baolin Peng, Haitao Mi, Furong Huang, Dong Yu

专题命中指令微调：LLM(abstract)；SFT(abstract)；分类 cs.CL、cs.LG

2410.04691 2024-10-08 cs.LG cs.CL 73%

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning

Qingyu Yin, Xuzheng He, Luoao Deng, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments EMNLP'24 Findings

2404.07815 2024-10-07 cs.LG cs.AI stat.ML 73%

Post-Hoc Reversal: Are We Selecting Models Prematurely?

Rishabh Ranjan, Saurabh Garg, Mrigank Raman, Carlos Guestrin, Zachary Lipton

专题命中指令微调：LLM(abstract)；instruction tuning(abstract)；分类 cs.AI、cs.LG

Comments accepted at NeurIPS 2024; v2 adds an intuitions section

2410.02426 2024-10-04 cs.CL cs.AI 73%

Learning the Latent Rules of a Game from Data: A Chess Story

Ben Fauber

专题命中指令微调：language model(abstract)；small language model(abstract)；分类 cs.CL、cs.AI

2310.04484 2024-10-04 cs.CL cs.AI 73%

Ada-Instruct: Adapting Instruction Generators for Complex Reasoning

Wanyun Cui, Qianle Wang

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2409.19173 2024-10-01 cs.CL cs.AI 73%

HM3: Heterogeneous Multi-Class Model Merging

Stefan Hackmann

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2210.17437 2024-09-24 cs.LG cs.CL 73%

Learning New Tasks from a Few Examples with Soft-Label Prototypes

Avyav Kumar Singh, Ekaterina Shutova, Helen Yannakoudakis

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments Proceedings of the 9th Workshop on Representation Learning for NLP (2024), Pages 215 to 236

2409.11114 2024-09-23 cs.CL cs.AI 73%

Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection

Bo Liu, Liming Zhan, Yujie Feng, Zexin Lu, Chengqiang Xie, Lei Xue, Albert Y. S. Lam, Xiao-Ming Wu

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments work in progress

2407.10671 2024-09-11 cs.CL cs.AI 73%

Qwen2 Technical Report

An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jianxin Yang, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang Lin, Kai Dang, Keming Lu, Keqin Chen, Kexin Yang, Mei Li, Mingfeng Xue, Na Ni, Pei Zhang, Peng Wang, Ru Peng, Rui Men, Ruize Gao, Runji Lin, Shijie Wang, Shuai Bai, Sinan Tan, Tianhang Zhu, Tianhao Li, Tianyu Liu, Wenbin Ge, Xiaodong Deng, Xiaohuan Zhou, Xingzhang Ren, Xinyu Zhang, Xipin Wei, Xuancheng Ren, Xuejing Liu, Yang Fan, Yang Yao, Yichang Zhang, Yu Wan, Yunfei Chu, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zhifang Guo, Zhihao Fan

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 26 pages, 1 figure

2408.16889 2024-09-02 cs.CL cs.LG 73%

LLaVA-Chef: A Multi-modal Generative Model for Food Recipes

Fnu Mohbat, Mohammed J. Zaki

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

2408.15300 2024-08-29 cs.LG cs.AI 73%

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs

Maxim Zhelnin, Viktor Moskvoretskii, Egor Shvetsov, Egor Venediktov, Mariya Krylova, Aleksandr Zuev, Evgeny Burnaev

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

2408.09540 2024-08-20 cs.CL cs.AI 73%

Using ChatGPT to Score Essays and Short-Form Constructed Responses

Mark D. Shermis

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 35 pages, 8 tables, 2 Figures, 27 references

2408.04575 2024-08-19 cs.AI cs.CL 73%

SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals

Haoran Zheng, Utku Pamuksuz

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2407.20775 2024-08-14 cs.LG cs.AI eess.SP 73%

Interpretable Pre-Trained Transformers for Heart Time-Series Data

Harry J. Davies, James Monsen, Danilo P. Mandic

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments 14 pages, 5 figures

2408.04639 2024-08-12 cs.CL cs.IR cs.LG eess.AS 73%

Abstractive summarization from Audio Transcription

Ilia Derkach

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments 36 pages, Master's thesis, 14 figures

2408.02584 2024-08-06 cs.CL cs.AI cs.IR 73%

Leveraging the Power of LLMs: A Fine-Tuning Approach for High-Quality Aspect-Based Summarization

Ankan Mullick, Sombit Bose, Rounak Saha, Ayan Kumar Bhowmick, Aditya Vempaty, Pawan Goyal, Niloy Ganguly, Prasenjit Dey, Ravi Kokku

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2408.01008 2024-08-05 cs.LG cs.AI 73%

Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs

Afia Anjum, Maksim E. Eren, Ismael Boureima, Boian Alexandrov, Manish Bhattarai

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.AI、cs.LG

Comments LA-UR-24-28177

2404.07221 2024-08-02 cs.IR cs.CL cs.LG q-fin.GN 73%

Improving Retrieval for RAG based Question Answering Models on Financial Documents

Spurthi Setty, Harsh Thakkar, Alyssa Lee, Eden Chung, Natan Vidra

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

2402.17934 2024-08-02 cs.CL cs.AI 73%

Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures

Chu-Cheng Lin, Xinyi Wang, Jonathan H. Clark, Han Lu, Yun Zhu, Chenxi Whitehouse, Hongkun Yu

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Revised version

2407.21739 2024-08-01 cs.CV cs.AI cs.LG eess.IV 73%

A Federated Learning-Friendly Approach for Parameter-Efficient Fine-Tuning of SAM in 3D Segmentation

Mothilal Asokan, Joseph Geo Benjamin, Mohammad Yaqub, Karthik Nandakumar

专题命中指令微调：foundation model(abstract)；pretraining(abstract)；分类 cs.AI、cs.LG

2407.12620 2024-07-30 cs.CL cs.AI 73%

Harnessing the Power of Artificial Intelligence to Vitalize Endangered Indigenous Languages: Technologies and Experiences

Claudio Pinhanez, Paulo Cavalin, Luciana Storto, Thomas Finbow, Alexander Cobbinah, Julio Nogima, Marisa Vasconcelos, Pedro Domingues, Priscila de Souza Mizukami, Nicole Grell, Majoí Gongora, Isabel Gonçalves

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

2407.03748 2024-07-30 cs.CL cs.AI 73%

Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques

Anar Yeginbergen, Maite Oronoz, Rodrigo Agerri

专题命中指令微调：language model(abstract)；prompting(abstract)；分类 cs.CL、cs.AI

Journal ref ACL 2024

2407.18061 2024-07-26 cs.CL cs.AI 73%

Difficulty Estimation and Simplification of French Text Using LLMs

Henri Jamet, Yash Raj Shrestha, Michalis Vlachos

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments 10 pages, 4 figures

2401.05811 2024-07-23 cs.CL cs.AI 73%

Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages

Zhuoyuan Mao, Yen Yu

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted to LoResMT 2024

2405.17249 2024-07-19 cs.CL cs.AI 73%

Assessing LLMs Suitability for Knowledge Graph Completion

Vasile Ionut Remus Iga, Gheorghe Cosmin Silaghi

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.AI

Comments Accepted at 18th International Conference on Neural-Symbolic Learning and Reasoning, NESY 2024. Evaluating Mixtral-8x7b-Instruct-v0.1, GPT-3.5-Turbo-0125 and GPT-4o for Knowledge Graph Completion task with prompts formatted according to the TELeR taxonomy

2407.10870 2024-07-16 cs.CV cs.AI cs.HC cs.LG 73%

GPT Sonograpy: Hand Gesture Decoding from Forearm Ultrasound Images via VLM

Keshav Bimbraw, Ye Wang, Jing Liu, Toshiaki Koike-Akino

专题命中指令微调：language model(abstract)；foundation model(abstract)；分类 cs.AI、cs.LG

Comments 8 pages, 9 figures

2407.09276 2024-07-15 cs.CL cs.LG 73%

H2O-Danube3 Technical Report

Pascal Pfeiffer, Philipp Singer, Yauhen Babakhin, Gabor Fodor, Nischay Dhankhar, Sri Satish Ambati

专题命中指令微调：language model(abstract)；small language model(abstract)；分类 cs.CL、cs.LG

2402.13468 2024-07-15 cs.LG cs.CL 73%

STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning

Nathan Beck, Adithya Iyer, Rishabh Iyer

专题命中指令微调：large language model(abstract)；language model(abstract)；分类 cs.CL、cs.LG

Comments 10 pages, 1 figure

1. 指令微调 11789 篇

"In Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue Learning

Beyond Scores: A Modular RAG-Based System for Automatic Short Answer Scoring with Feedback

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning

Post-Hoc Reversal: Are We Selecting Models Prematurely?

Learning the Latent Rules of a Game from Data: A Chess Story

Ada-Instruct: Adapting Instruction Generators for Complex Reasoning

HM3: Heterogeneous Multi-Class Model Merging

Learning New Tasks from a Few Examples with Soft-Label Prototypes

Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection

Qwen2 Technical Report

LLaVA-Chef: A Multi-modal Generative Model for Food Recipes

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs

Using ChatGPT to Score Essays and Short-Form Constructed Responses

SCENE: Evaluating Explainable AI Techniques Using Soft Counterfactuals

Interpretable Pre-Trained Transformers for Heart Time-Series Data

Abstractive summarization from Audio Transcription

Leveraging the Power of LLMs: A Fine-Tuning Approach for High-Quality Aspect-Based Summarization

Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs

Improving Retrieval for RAG based Question Answering Models on Financial Documents

Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures

A Federated Learning-Friendly Approach for Parameter-Efficient Fine-Tuning of SAM in 3D Segmentation

Harnessing the Power of Artificial Intelligence to Vitalize Endangered Indigenous Languages: Technologies and Experiences

Argument Mining in Data Scarce Settings: Cross-lingual Transfer and Few-shot Techniques

Difficulty Estimation and Simplification of French Text Using LLMs

Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages

Assessing LLMs Suitability for Knowledge Graph Completion

GPT Sonograpy: Hand Gesture Decoding from Forearm Ultrasound Images via VLM

H2O-Danube3 Technical Report

STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning