语言大模型 / LLM - arXivDaily 专题

2406.13269 2024-06-21 cs.AI cs.CL cs.HC eess.SP 84%

Investigating Low-Cost LLM Annotation for~Spoken Dialogue Understanding Datasets

Lucas Druart, Valentin Vielzeuf, Yannick Estève

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

Journal ref 27th International Conference on Text, Speech and Dialogue, Sep 2024, Brno (R{é}p. Tch{è}que), Czech Republic

2406.04606 2024-06-10 cs.LG cs.AI 84%

Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions

Jingtan Wang, Xiaoqiang Lin, Rui Qiao, Chuan-Sheng Foo, Bryan Kian Hsiang Low

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

Comments Accepted to ICML 2024

2402.12336 2024-06-06 cs.LG cs.AI cs.CV stat.ML 84%

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein

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

Comments ICML 2024 Oral

2405.20495 2024-06-03 cs.CL cs.LG 84%

Transfer Q Star: Principled Decoding for LLM Alignment

Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin, Dinesh Manocha, Mengdi Wang, Amrit Singh Bedi, Furong Huang

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

2405.12656 2024-05-22 cs.CL cs.AI 84%

Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Prediction

Yu-Hsiang Lin, Huang-Ting Shieh, Chih-Yu Liu, Kuang-Ting Lee, Hsiao-Cheng Chang, Jing-Lun Yang, Yu-Sheng Lin

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

2402.12147 2024-05-01 cs.CL cs.AI 84%

Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models

Vinay Setty

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

Comments Accepted in SIGIR 2024 (industry track)

2402.16472 2024-04-18 cs.CL cs.AI 84%

mEdIT: Multilingual Text Editing via Instruction Tuning

Vipul Raheja, Dimitris Alikaniotis, Vivek Kulkarni, Bashar Alhafni, Dhruv Kumar

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

Comments Accepted to NAACL 2024 (Main). 23 pages, 8 tables, 11 figures

2403.11124 2024-04-02 cs.CL cs.AI 84%

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment

Feifan Song, Bowen Yu, Hao Lang, Haiyang Yu, Fei Huang, Houfeng Wang, Yongbin Li

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

Comments Accepted by LREC-COLING 2024

2403.10088 2024-03-18 cs.CL cs.AI 84%

Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF

Amey Hengle, Aswini Kumar, Sahajpreet Singh, Anil Bandhakavi, Md Shad Akhtar, Tanmoy Chakroborty

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

2211.00635 2024-03-14 cs.CL cs.LG 84%

Two-stage LLM Fine-tuning with Less Specialization and More Generalization

Yihan Wang, Si Si, Daliang Li, Michal Lukasik, Felix Yu, Cho-Jui Hsieh, Inderjit S Dhillon, Sanjiv Kumar

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

Comments ICLR 2024

2402.15833 2024-02-27 cs.CL cs.LG 84%

Prompt Perturbation Consistency Learning for Robust Language Models

Yao Qiang, Subhrangshu Nandi, Ninareh Mehrabi, Greg Ver Steeg, Anoop Kumar, Anna Rumshisky, Aram Galstyan

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

2402.07872 2024-02-13 cs.RO cs.CL cs.CV cs.LG 84%

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Soroush Nasiriany, Fei Xia, Wenhao Yu, Ted Xiao, Jacky Liang, Ishita Dasgupta, Annie Xie, Danny Driess, Ayzaan Wahid, Zhuo Xu, Quan Vuong, Tingnan Zhang, Tsang-Wei Edward Lee, Kuang-Huei Lee, Peng Xu, Sean Kirmani, Yuke Zhu, Andy Zeng, Karol Hausman, Nicolas Heess, Chelsea Finn, Sergey Levine, Brian Ichter

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

2311.01378 2024-02-06 cs.RO cs.AI cs.LG 84%

Vision-Language Foundation Models as Effective Robot Imitators

Xinghang Li, Minghuan Liu, Hanbo Zhang, Cunjun Yu, Jie Xu, Hongtao Wu, Chilam Cheang, Ya Jing, Weinan Zhang, Huaping Liu, Hang Li, Tao Kong

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

Comments Fix typos. Project page: https://roboflamingo.github.io

2401.04151 2024-01-10 cs.LG cs.CL 84%

Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning

Wenhan Xia, Chengwei Qin, Elad Hazan

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

Comments Work in progress

2311.04046 2023-11-08 cs.LG cs.CL 84%

Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features

Diogo Cruz, Edoardo Pona, Alex Holness-Tofts, Elias Schmied, Víctor Abia Alonso, Charlie Griffin, Bogdan-Ionut Cirstea

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

2311.02702 2023-11-07 cs.CL cs.AI 84%

Extraction of Atypical Aspects from Customer Reviews: Datasets and Experiments with Language Models

Smita Nannaware, Erfan Al-Hossami, Razvan Bunescu

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

Comments Proceedings of the Knowledge-aware and Conversational Recommender Systems Workshop (KaRS) @ RecSys, September 19, 2023

2310.17788 2023-10-30 cs.AI cs.CL 84%

Utilizing Language Models for Energy Load Forecasting

Hao Xue, Flora D. Salim

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

Comments BuildSys 2023 Accepted

2310.16040 2023-10-25 cs.CL cs.AI 84%

Instruct and Extract: Instruction Tuning for On-Demand Information Extraction

Yizhu Jiao, Ming Zhong, Sha Li, Ruining Zhao, Siru Ouyang, Heng Ji, Jiawei Han

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

Comments EMNLP 2023

2305.09857 2023-10-25 cs.CL cs.AI 84%

CoEdIT: Text Editing by Task-Specific Instruction Tuning

Vipul Raheja, Dhruv Kumar, Ryan Koo, Dongyeop Kang

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

Comments Accepted to EMNLP 2023 (Findings). 18 pages, 13 tables, 2 figures

2310.14152 2023-10-24 cs.CL cs.LG 84%

Orthogonal Subspace Learning for Language Model Continual Learning

Xiao Wang, Tianze Chen, Qiming Ge, Han Xia, Rong Bao, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

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

Comments EMNLP 2023 findings

2310.14034 2023-10-24 cs.CL cs.LG 84%

Tree Prompting: Efficient Task Adaptation without Fine-Tuning

John X. Morris, Chandan Singh, Alexander M. Rush, Jianfeng Gao, Yuntian Deng

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

Comments Both first authors contributed equally; accepted to EMNLP 2023

2309.12109 2023-09-22 cs.CL cs.AI 84%

PEFTT: Parameter-Efficient Fine-Tuning for low-resource Tibetan pre-trained language models

Zhou Mingjun, Daiqing Zhuoma, Qun Nuo, Nyima Tashi

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

2309.10808 2023-09-21 cs.LG cs.AI physics.ao-ph 84%

AI Foundation Models for Weather and Climate: Applications, Design, and Implementation

S. Karthik Mukkavilli, Daniel Salles Civitarese, Johannes Schmude, Johannes Jakubik, Anne Jones, Nam Nguyen, Christopher Phillips, Sujit Roy, Shraddha Singh, Campbell Watson, Raghu Ganti, Hendrik Hamann, Udaysankar Nair, Rahul Ramachandran, Kommy Weldemariam

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

Comments 44 pages, 1 figure, updated Fig. 1

2308.16824 2023-09-06 cs.CL cs.AI cs.PL cs.SE 84%

Can Programming Languages Boost Each Other via Instruction Tuning?

Daoguang Zan, Ailun Yu, Bo Shen, Jiaxin Zhang, Taihong Chen, Bing Geng, Bei Chen, Jichuan Ji, Yafen Yao, Yongji Wang, Qianxiang Wang

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

Comments Work in progress

2309.00240 2023-09-04 cs.CL cs.AI 84%

FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checking

Tsun-Hin Cheung, Kin-Man Lam

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

Comments Accepted in APSIPA ASC 2023

2306.11270 2023-07-13 cs.CL cs.LG 84%

Evaluating the Zero-shot Robustness of Instruction-tuned Language Models

Jiuding Sun, Chantal Shaib, Byron C. Wallace

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

2307.05228 2023-07-12 cs.CL cs.LG 84%

Attribute Controlled Dialogue Prompting

Runcheng Liu, Ahmad Rashid, Ivan Kobyzev, Mehdi Rezagholizadeh, Pascal Poupart

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

Comments Accepted at ACL 2023 In Findings

2306.06234 2023-06-13 cs.CL cs.AI 84%

Using Foundation Models to Detect Policy Violations with Minimal Supervision

Sid Mittal, Vineet Gupta, Frederick Liu, Mukund Sundararajan

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

Comments 16 pages

2306.04597 2023-06-08 cs.CL cs.LG 84%

Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions

Himanshu Thakur, Atishay Jain, Praneetha Vaddamanu, Paul Pu Liang, Louis-Philippe Morency

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

Comments Accepted to ACL 2023 Main Conference

2210.05643 2023-06-07 cs.LG cs.CL 84%

A Kernel-Based View of Language Model Fine-Tuning

Sadhika Malladi, Alexander Wettig, Dingli Yu, Danqi Chen, Sanjeev Arora

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

Comments Accepted at ICML 2023. Code and pre-computed kernels are publicly available at https://github.com/princeton-nlp/LM-Kernel-FT

1. 指令微调 11601 篇

Investigating Low-Cost LLM Annotation for~Spoken Dialogue Understanding Datasets

Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Transfer Q Star: Principled Decoding for LLM Alignment

Retrieval-Augmented Language Model for Extreme Multi-Label Knowledge Graph Link Prediction

Surprising Efficacy of Fine-Tuned Transformers for Fact-Checking over Larger Language Models

mEdIT: Multilingual Text Editing via Instruction Tuning

Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment

Intent-conditioned and Non-toxic Counterspeech Generation using Multi-Task Instruction Tuning with RLAIF

Two-stage LLM Fine-tuning with Less Specialization and More Generalization

Prompt Perturbation Consistency Learning for Robust Language Models

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs

Vision-Language Foundation Models as Effective Robot Imitators

Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning

Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features

Extraction of Atypical Aspects from Customer Reviews: Datasets and Experiments with Language Models

Utilizing Language Models for Energy Load Forecasting

Instruct and Extract: Instruction Tuning for On-Demand Information Extraction

CoEdIT: Text Editing by Task-Specific Instruction Tuning

Orthogonal Subspace Learning for Language Model Continual Learning

Tree Prompting: Efficient Task Adaptation without Fine-Tuning

PEFTT: Parameter-Efficient Fine-Tuning for low-resource Tibetan pre-trained language models

AI Foundation Models for Weather and Climate: Applications, Design, and Implementation

Can Programming Languages Boost Each Other via Instruction Tuning?

FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checking

Evaluating the Zero-shot Robustness of Instruction-tuned Language Models

Attribute Controlled Dialogue Prompting

Using Foundation Models to Detect Policy Violations with Minimal Supervision

Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions

A Kernel-Based View of Language Model Fine-Tuning