语言大模型 / LLM - arXivDaily 专题

2503.07591 2025-04-08 cs.CV cs.AI cs.LG 84%

Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuning

Bardia Safaei, Faizan Siddiqui, Jiacong Xu, Vishal M. Patel, Shao-Yuan Lo

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

Comments Accepted at CVPR 2025 (Highlight)

2502.17823 2025-03-25 cs.LG cs.CL 84%

A General Framework to Enhance Fine-tuning-based LLM Unlearning

Jie Ren, Zhenwei Dai, Xianfeng Tang, Hui Liu, Jingying Zeng, Zhen Li, Rahul Goutam, Suhang Wang, Yue Xing, Qi He, Hui Liu

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

2503.14900 2025-03-20 cs.CL cs.AI 84%

Deep Contrastive Unlearning for Language Models

Estrid He, Tabinda Sarwar, Ibrahim Khalil, Xun Yi, Ke Wang

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

2503.12667 2025-03-18 cs.CL cs.AI 84%

Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility

Jacob Chmura, Jonah Dauvet, Sebastian Sabry

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

2503.00691 2025-03-10 cs.SE cs.AI cs.CL 84%

How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code

Seonghyeon Lee, Heejae Chon, Joonwon Jang, Dongha Lee, Hwanjo Yu

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

2503.02989 2025-03-06 cs.CL cs.AI 84%

Effectively Steer LLM To Follow Preference via Building Confident Directions

Bingqing Song, Boran Han, Shuai Zhang, Hao Wang, Haoyang Fang, Bonan Min, Yuyang Wang, Mingyi Hong

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

2502.16343 2025-02-25 cs.LG cs.AI cs.CE cs.MA 84%

Exploring Sentiment Manipulation by LLM-Enabled Intelligent Trading Agents

David Byrd

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

2502.15828 2025-02-25 cs.LG cs.AI 84%

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

Mengyang Sun, Yihao Wang, Tao Feng, Dan Zhang, Yifan Zhu, Jie Tang

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

2502.02028 2025-02-18 cs.CL cs.AI 84%

Fine-tuning Language Models for Recipe Generation: A Comparative Analysis and Benchmark Study

Anneketh Vij, Changhao Liu, Rahul Anil Nair, Theodore Eugene Ho, Edward Shi, Ayan Bhowmick

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

Comments 18 pages, 10 figures,14 tables

2502.03884 2025-02-07 cs.LG cs.AI 84%

Rank Also Matters: Hierarchical Configuration for Mixture of Adapter Experts in LLM Fine-Tuning

Peizhuang Cong, Wenpu Liu, Wenhan Yu, Haochen Zhao, Tong Yang

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

2410.13116 2025-01-28 cs.CL cs.AI 84%

Learning to Summarize from LLM-generated Feedback

Hwanjun Song, Taewon Yun, Yuho Lee, Jihwan Oh, Gihun Lee, Jason Cai, Hang Su

专题命中指令微调：LLM(title,abstract)；preference optimization(abstract)；分类 cs.CL、cs.AI

Comments Accepted at NAACL 2025 (main, long)

2501.13985 2025-01-27 cs.LG cs.AI cs.CV 84%

Pilot: Building the Federated Multimodal Instruction Tuning Framework

Baochen Xiong, Xiaoshan Yang, Yaguang Song, Yaowei Wang, Changsheng Xu

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

2408.05200 2025-01-24 cs.CL cs.AI 84%

KIF: Knowledge Identification and Fusion for Language Model Continual Learning

Yujie Feng, Xu Chu, Yongxin Xu, Zexin Lu, Bo Liu, Philip S. Yu, Xiao-Ming Wu

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

Comments This version updates the model name from Task Skill Localization and Consolidation (TaSL) to Knowledge Identification and Fusion (KIF). It is an extension of the ACL 2024 paper titled Continual Dialog State Tracking via Task Skill Localization and Consolidation

2411.11531 2025-01-15 cs.CL cs.AI 84%

Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality

Viktoriia Chekalina, Anton Razzhigaev, Elizaveta Goncharova, Andrey Kuznetsov

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

2501.06434 2025-01-14 cs.CL cs.AI 84%

Synthetic Feature Augmentation Improves Generalization Performance of Language Models

Ashok Choudhary, Cornelius Thiels, Hojjat Salehinejad

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

Comments Accepted for presentation at IEEE SSCI 2025

2501.02683 2025-01-09 cs.CL cs.AI 84%

From Superficial Patterns to Semantic Understanding: Fine-Tuning Language Models on Contrast Sets

Daniel Petrov

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

2501.00418 2025-01-03 cs.LG cs.AI 84%

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models

Martin Pawelczyk, Lillian Sun, Zhenting Qi, Aounon Kumar, Himabindu Lakkaraju

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

Comments The first two authors contributed equally

2412.17365 2024-12-24 cs.CL cs.AI 84%

Boosting LLM via Learning from Data Iteratively and Selectively

Qi Jia, Siyu Ren, Ziheng Qin, Fuzhao Xue, Jinjie Ni, Yang You

专题命中指令微调：LLM(title)；instruction tuning(abstract)；post-training(abstract)；分类 cs.CL、cs.AI

2412.08392 2024-12-12 cs.CL cs.AI 84%

The Roles of English in Evaluating Multilingual Language Models

Wessel Poelman, Miryam de Lhoneux

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

Comments NoDaLiDa 2025

2411.03817 2024-12-10 cs.AI cs.CL cs.HC cs.RO 84%

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning

Zhirui Deng, Zhicheng Dou, Yutao Zhu, Ji-Rong Wen, Ruibin Xiong, Mang Wang, Weipeng Chen

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

2411.02785 2024-12-06 cs.LG cs.AI 84%

Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment

Jason Vega, Junsheng Huang, Gaokai Zhang, Hangoo Kang, Minjia Zhang, Gagandeep Singh

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

Comments v2: Updated with changes from peer review rebuttal. v1: Version under peer review

2412.01078 2024-12-04 cs.CL cs.AI cs.HC 84%

Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data

Shuaijiang Zhao, Tingwei Guo, Bajian Xiang, Tongtang Wan, Qiang Niu, Wei Zou, Xiangang Li

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

Comments KE-Omni, Ke-SpeechChat

2411.15831 2024-11-26 cs.LG cs.AI 84%

Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models

Olivia Ma, Jonathan Passerat-Palmbach, Dmitrii Usynin

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

2405.19581 2024-11-22 cs.SE cs.AI cs.CL 84%

Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases

Zian Su, Xiangzhe Xu, Ziyang Huang, Kaiyuan Zhang, Xiangyu Zhang

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

2311.14736 2024-11-12 cs.CL cs.LG 84%

Data Diversity Matters for Robust Instruction Tuning

Alexander Bukharin, Shiyang Li, Zhengyang Wang, Jingfeng Yang, Bing Yin, Xian Li, Chao Zhang, Tuo Zhao, Haoming Jiang

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

Comments 22 pages, 18 figures

2410.09699 2024-10-15 cs.CL cs.AI 84%

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG

Xinxi Chen, Li Wang, Wei Wu, Qi Tang, Yiyao Liu

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

Journal ref 2024 KDD Cup Workshop for Retrieval Augmented Generation at the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

2410.07706 2024-10-11 cs.CL cs.AI 84%

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li

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

Comments Findings of EMNLP 2024

2402.10353 2024-10-08 cs.CL cs.LG 84%

Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models

Kang He, Yinghan Long, Kaushik Roy

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

Comments EMNLP 2024 Findings

2409.17745 2024-10-08 cs.IR cs.CL cs.LG 84%

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

Nilanjan Sinhababu, Andrew Parry, Debasis Ganguly, Debasis Samanta, Pabitra Mitra

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

Comments Accepted to EMNLP 2024

2405.14394 2024-10-04 cs.CL cs.AI 84%

Instruction Tuning With Loss Over Instructions

Zhengyan Shi, Adam X. Yang, Bin Wu, Laurence Aitchison, Emine Yilmaz, Aldo Lipani

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

Comments NeurIPS 2024. Code is available at https://github.com/ZhengxiangShi/InstructionModelling

1. 指令微调 11619 篇

Filter Images First, Generate Instructions Later: Pre-Instruction Data Selection for Visual Instruction Tuning

A General Framework to Enhance Fine-tuning-based LLM Unlearning

Deep Contrastive Unlearning for Language Models

Plausibility Vaccine: Injecting LLM Knowledge for Event Plausibility

How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code

Effectively Steer LLM To Follow Preference via Building Confident Directions

Exploring Sentiment Manipulation by LLM-Enabled Intelligent Trading Agents

A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models

Fine-tuning Language Models for Recipe Generation: A Comparative Analysis and Benchmark Study

Rank Also Matters: Hierarchical Configuration for Mixture of Adapter Experts in LLM Fine-Tuning

Learning to Summarize from LLM-generated Feedback

Pilot: Building the Federated Multimodal Instruction Tuning Framework

KIF: Knowledge Identification and Fusion for Language Model Continual Learning

Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality

Synthetic Feature Augmentation Improves Generalization Performance of Language Models

From Superficial Patterns to Semantic Understanding: Fine-Tuning Language Models on Contrast Sets

Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models

Boosting LLM via Learning from Data Iteratively and Selectively

The Roles of English in Evaluating Multilingual Language Models

From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning

Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment

Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data

Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models

Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases

Data Diversity Matters for Robust Instruction Tuning

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories

Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

Instruction Tuning With Loss Over Instructions