From Volume to Value: Preference-Aligned Memory Construction for On-Device RAG
Department of Computer Science and Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea(计算机科学与工程系,全州国立科学与技术研究所(UNIST),全州,韩国)
With the rapid emergence of personal AI agents based on Large Language Models (LLMs), implementing them on-device has become essential for privacy and responsiveness. To handle the inherently personal and context-dependent nature of real-world requests, such agents must ground their generation in device-resident personal context. However, under tight memory budgets, the core bottleneck is what to store so that retrieval remains aligned with the user. We propose EPIC (Efficient Preference-aligned Index Construction), which focuses on user preferences as a compact and stable form of personal context and integrates them throughout the RAG pipeline. EPIC selectively retains preference-relevant information from raw data and aligns retrieval toward preference-aligned contexts. Across four benchmarks covering conversations, debates, explanations, and recommendations, EPIC reduces indexing memory by 2,404 times, improves preference-following accuracy by 18.79 %p, and achieves 32.17 times lower retrieval latency over the best-performing baseline. In on-device experiments, EPIC maintains under 1 MB memory and achieves 5.21 to 29.35 ms/query latency across three platforms, while supporting streaming updates under preference drift. Our code and data are available at https://github.com/UbiquitousAILab/EPIC.
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院)
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization
School of Data Science and Engineering, East China Normal University(华东师范大学数据科学与工程学院);Chinese Academy of Sciences(中国科学院);Baidu Inc(百度公司);Peking University(北京大学)
Hit-RAG: Learning to Reason with Long Contexts via Preference Alignment
Tongji University(同济大学);The City University of New York(纽约城市大学);University of Technology Sydney(悉尼大学);Huazhong University of Science and Technology(华中科技大学);Shenzhen University of Advanced Technology(深圳先进技术大学)
Culinary Crossroads: A RAG Framework for Enhancing Diversity in Cross-Cultural Recipe Adaptation
Aarhus University(奥胡斯大学);University of Copenhagen(哥本哈根大学);Dept. of Computer Science and Artificial Intelligence, University of Granada(格拉纳达大学计算机科学与人工智能系);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
Elmore Family School of Electrical and Computer Engineering, Purdue University(普渡大学埃尔莫尔电气与计算机工程学院);Yonsei University(延世大学);University at Buffalo–SUNY(纽约州立大学布法罗分校)
Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Soochow University(苏州大学);University of Technology Sydney(悉尼科技大学);The Hong Kong University of Science and Technology(香港科技大学)
针对成对偏好蒸馏忽视回复差异程度的问题,本文提出 PAD 框架,将师生内在偏好建模为分布并进行对齐,在多个基准上显著提升 SLM 的人类偏好对齐效果。
Less is More for RAG: Information Gain Pruning for Generator-Aligned Reranking and Evidence Selection
organization= School of Computer Science;Technology, Dalian University of Technology , addressline= No.2 Linggong Road, Ganjingzi District , city= Dalian , postcode= 116024 , country= China;organization= College of Health-Preservation;Wellness, Dalian Medical University , addressline= No. 9 West Section of Lvshun South Road, Lvshunkou District , city= Dalian , postcode= 116044 , country= China;organization= School of Information Engineering, Dalian Ocean University , addressline= No. 2-52, Heishijiao Street, Shahekou District , city= Dalian , postcode= 116023 , country= China;organization= School of Information Engineering, Liaodong University , addressline= No.116 Linjiang Back Street, Zhenan District , city= Dandong , postcode= 118001 , country= China;organization= Information Technology Center, Qinghai University , addressline= 251 Ningda Road, Chengbei District , city= Xining , postcode= 810016 , country= China;organization= School of Electronic;Information Engineering, Liaoning Technical University , addressline= 188 Longwan South Street, Sijiatun District , city= Huludao , postcode= 125105 , country= China;organization= Tencent (Dalian Northern Interactive Entertainment Technology Co., Ltd.) , addressline= 21/F, Tencent Building, No. 26 Jingxian St, Ganjingzi District , city= Dalian , postcode= 116085 , country= China
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Tsinghua University(清华大学);Zhipu AI(智谱AI)
ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing
School of Engineering and Materials Science, Queen Mary University of London(伦敦玛丽女王大学工程与材料科学学院);Department of Engineering Science, University of Oxford(牛津大学工程科学系)
KARE-RAG: Knowledge-Aware Refinement and Enhancement for RAG
School of Biomedical Engineering, Tsinghua, China(清华大学生物医学工程学院);School of Informatics, Xiamen University, China(厦门大学信息学院);Department of Computer Science and Technology, Institute for AI, Tsinghua University, China(清华大学计算机科学与技术系);Dept. of Computer Science and Technology, Northeastern University, Shenyang, China(东北大学沈阳校区计算机科学与技术系);Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(中国科学院信息工程研究所)
RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China(语音与语言信息处理国家工程研究中心,中国科学技术大学);State Key Laboratory of Cognitive Intelligence, iFLYTEK Research(认知智能国家重点实验室,iFLYTEK研究院)
1SimpleWay.AI 2McGill University 3University of Toronto 4University of California, Los Angeles 5The Chinese University of Hong Kong 6University of Manitoba 7Universit\'e de Montr\'eal 8Boston University 9Mila - Quebec AI Institute 10CG Matrix Technology Limited 11Lakehead University 12McMaster University