语言大模型 / LLM - arXivDaily 专题

2505.20336 2025-05-28 cs.CL cs.AI 82%

MOSLIM:Align with diverse preferences in prompts through reward classification

Yu Zhang, Wanli Jiang, Zhengyu Yang

机构 * Alibaba Group（阿里巴巴集团）

专题命中指令微调：large language model(abstract)；language model(abstract)；SFT(abstract)；prompting(abstract)

2410.03124 2025-05-27 cs.CL cs.LG 82%

In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement

Zhen-Yu Zhang, Jiandong Zhang, Huaxiu Yao, Gang Niu, Masashi Sugiyama

机构 * Center for Advanced Intelligence Project, RIKEN（RIKEN先进智能项目中心）； Northeastern University（东北大学）； UNC-Chapel Hill（北卡罗来纳大学教堂山分校）； Center for Advanced Intelligence Project, RIKEN Graduate School of Frontier Sciences, The University of Tokyo（RIKEN前沿科学研究生院、东京大学先进智能项目中心）

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2502.14645 2025-05-26 cs.CL cs.AI 82%

Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs

Yuchen Wu, Liang Ding, Li Shen, Dacheng Tao

专题命中指令微调：large language model(abstract)；language model(abstract)；instruction tuning(abstract)；preference optimization(abstract)

Comments ACL 2025 Findings

2505.12038 2025-05-20 cs.LG cs.AI cs.CR 82%

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Ning Lu, Shengcai Liu, Jiahao Wu, Weiyu Chen, Zhirui Zhang, Yew-Soon Ong, Qi Wang, Ke Tang

机构 * Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Department of CSE, SUSTech（脑启发智能计算广东省重点实验室，计算机科学与工程系，华南理工大学）； Department of CSE, HKUST（计算机科学与工程系，香港科技大学）； Department of CSE, PolyU（计算机科学与工程系，PolyU）； Department of CSE, SUSTech（计算机科学与工程系，华南理工大学）； Huawei Technologies CO.（华为技术有限公司）； College of Computing（计算学院）

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；post-training(abstract)

Comments ICML 2025 Camera Ready

2503.11197 2025-05-15 cs.SD cs.AI cs.CL eess.AS 82%

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

Gang Li, Jizhong Liu, Heinrich Dinkel, Yadong Niu, Junbo Zhang, Jian Luan

机构 * Xiaomi Corporation（小米公司）

专题命中指令微调：large language model(abstract)；language model(abstract)；post-training(abstract)；SFT(abstract)

2505.07888 2025-05-14 cs.CL cs.AI 82%

Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mapping

Yusen Wu, Xiaotie Deng

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2504.08207 2025-04-14 cs.SE cs.AI cs.LG 82%

DRAFT-ing Architectural Design Decisions using LLMs

Rudra Dhar, Adyansh Kakran, Amey Karan, Karthik Vaidhyanathan, Vasudeva Varma

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2504.06271 2025-04-10 cs.IR cs.AI cs.CL 82%

ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources

Yikuan Xia, Jiazun Chen, Yirui Zhan, Suifeng Zhao, Weipeng Jiang, Chaorui Zhang, Wei Han, Bo Bai, Jun Gao

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；preference optimization(abstract)

2410.22767 2025-03-28 cs.CL cs.AI 82%

Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot

Sejin Lee, Dongha Kim, Min Song

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments There are 10 chapters, including references, and 2 figures used. To be presented at the 15th IEEE International Conference on Knowledge Graphs (ICKG2024)

Journal ref IEEE International Conference on Knowledge Graph (ICKG), 2024, pp. 177-185

2503.03796 2025-03-10 cs.MA cs.AI cs.LG cs.RO 82%

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm

Hyeonjun Kim, Kanghoon Lee, Junho Park, Jiachen Li, Jinkyoo Park

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；RLHF(abstract)

Comments 7 pages, 4 figures

2410.13213 2025-03-04 cs.AI cs.LG 82%

LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch

Caigao Jiang, Xiang Shu, Hong Qian, Xingyu Lu, Jun Zhou, Aimin Zhou, Yang Yu

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

2407.08223 2025-03-03 cs.CL cs.AI 82%

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

Zilong Wang, Zifeng Wang, Long Le, Huaixiu Steven Zheng, Swaroop Mishra, Vincent Perot, Yuwei Zhang, Anush Mattapalli, Ankur Taly, Jingbo Shang, Chen-Yu Lee, Tomas Pfister

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments Accepted to ICLR 2025

2502.16414 2025-02-25 cs.LG cs.AI 82%

TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation

Liancheng Fang, Aiwei Liu, Hengrui Zhang, Henry Peng Zou, Weizhi Zhang, Philip S. Yu

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2407.19568 2025-02-25 cs.CL cs.AI 82%

Are LLMs Good Annotators for Discourse-level Event Relation Extraction?

Kangda Wei, Aayush Gautam, Ruihong Huang

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

2502.14628 2025-02-21 cs.LG cs.CL 82%

PEARL: Towards Permutation-Resilient LLMs

Liang Chen, Li Shen, Yang Deng, Xiaoyan Zhao, Bin Liang, Kam-Fai Wong

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments ICLR 2025

2502.08657 2025-02-14 cs.CL cs.AI 82%

Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions

Jingxin Xu, Guoshun Nan, Sheng Guan, Sicong Leng, Yilian Liu, Zixiao Wang, Yuyang Ma, Zhili Zhou, Yanzhao Hou, Xiaofeng Tao

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments This work has been submitted to the IEEE for possible publication

2411.02688 2025-02-04 cs.CL cs.LG 82%

On the Loss of Context-awareness in General Instruction Fine-tuning

Yihan Wang, Andrew Bai, Nanyun Peng, Cho-Jui Hsieh

专题命中指令微调：large language model(abstract)；language model(abstract)；post-training(abstract)；SFT(abstract)

2409.15825 2025-01-22 cs.CL cs.AI 82%

60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering

Junjie Ye, Yuming Yang, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

2404.16375 2025-01-22 cs.CV cs.AI cs.CL 82%

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs

An Yan, Zhengyuan Yang, Junda Wu, Wanrong Zhu, Jianwei Yang, Linjie Li, Kevin Lin, Jianfeng Wang, Julian McAuley, Jianfeng Gao, Lijuan Wang

专题命中指令微调：large language model(abstract)；language model(abstract)；instruction tuning(abstract)；prompting(abstract)

Comments published at COLM-2024

2412.16500 2025-01-06 eess.AS cs.AI cs.CL 82%

Speech Retrieval-Augmented Generation without Automatic Speech Recognition

Do June Min, Karel Mundnich, Andy Lapastora, Erfan Soltanmohammadi, Srikanth Ronanki, Kyu Han

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；SLM(abstract)

Comments ICASSP 2025

2501.00039 2025-01-03 eess.AS cs.CL cs.LG cs.SD 82%

Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning

Chirag Nagpal, Subhashini Venugopalan, Jimmy Tobin, Marilyn Ladewig, Katherine Heller, Katrin Tomanek

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；RLHF(abstract)

Comments Accepted at ICASSP 2025

2412.20382 2024-12-31 cs.CL cs.AI 82%

Natural Language Fine-Tuning

Jia Liu, Yue Wang, Zhiqi Lin, Min Chen, Yixue Hao, Long Hu

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

2412.04305 2024-12-06 cs.CL cs.LG 82%

ALMA: Alignment with Minimal Annotation

Michihiro Yasunaga, Leonid Shamis, Chunting Zhou, Andrew Cohen, Jason Weston, Luke Zettlemoyer, Marjan Ghazvininejad

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；SFT(abstract)

2411.15004 2024-12-06 cs.CL cs.AI 82%

ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data

Junhong Shen, Atishay Jain, Zedian Xiao, Ishan Amlekar, Mouad Hadji, Aaron Podolny, Ameet Talwalkar

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2406.04625 2024-11-20 cs.CL cs.AI 82%

Key-Element-Informed sLLM Tuning for Document Summarization

Sangwon Ryu, Heejin Do, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments Interspeech 2024

2408.05365 2024-11-19 cs.CL cs.AI cs.CE 82%

FiSTECH: Financial Style Transfer to Enhance Creativity without Hallucinations in LLMs

Sohini Roychowdhury, Marko Krema, Brian Moore, Xingjian Lai, Dike Effedua, Bharat Jethwani

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 10 pages, 14 figures, 5 tables, conference

Journal ref IEEE Big Data 2024

2410.24198 2024-11-04 cs.CL cs.LG cs.SE 82%

SelfCodeAlign: Self-Alignment for Code Generation

Yuxiang Wei, Federico Cassano, Jiawei Liu, Yifeng Ding, Naman Jain, Zachary Mueller, Harm de Vries, Leandro von Werra, Arjun Guha, Lingming Zhang

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；instruction tuning(abstract)

Comments Accepted to NeurIPS 2024

2410.23535 2024-11-01 cs.CL cs.AI cs.RO 82%

Simulating User Agents for Embodied Conversational-AI

Daniel Philipov, Vardhan Dongre, Gokhan Tur, Dilek Hakkani-Tür

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 8 pages, 5 figures, 4 tables

Journal ref NeurIPS 2024 Workshop on Open-World Agents

2409.19001 2024-10-01 cs.CL cs.AI 82%

Pay Attention to What Matters

Pedro Luiz Silva, Antonio de Domenico, Ali Maatouk, Fadhel Ayed

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

2409.10790 2024-09-18 cs.CL cs.AI 82%

Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering

Qingru Zhang, Xiaodong Yu, Chandan Singh, Xiaodong Liu, Liyuan Liu, Jianfeng Gao, Tuo Zhao, Dan Roth, Hao Cheng

专题命中指令微调：LLM(abstract)；large language model(abstract)；language model(abstract)；prompting(abstract)

Comments 12 pages, 4 figures

1. 指令微调 11619 篇

MOSLIM:Align with diverse preferences in prompts through reward classification

In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement

Edit Once, Update Everywhere: A Simple Framework for Cross-Lingual Knowledge Synchronization in LLMs

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mapping

DRAFT-ing Architectural Design Decisions using LLMs

ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources

Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot

Human Implicit Preference-Based Policy Fine-tuning for Multi-Agent Reinforcement Learning in USV Swarm

LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch

Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting

TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation

Are LLMs Good Annotators for Discourse-level Event Relation Extraction?

PEARL: Towards Permutation-Resilient LLMs

Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions

On the Loss of Context-awareness in General Instruction Fine-tuning

60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering

List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs

Speech Retrieval-Augmented Generation without Automatic Speech Recognition

Speech Recognition With LLMs Adapted to Disordered Speech Using Reinforcement Learning

Natural Language Fine-Tuning

ALMA: Alignment with Minimal Annotation

ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data

Key-Element-Informed sLLM Tuning for Document Summarization

FiSTECH: Financial Style Transfer to Enhance Creativity without Hallucinations in LLMs

SelfCodeAlign: Self-Alignment for Code Generation

Simulating User Agents for Embodied Conversational-AI

Pay Attention to What Matters

Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering