ACL Findings2025
Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization
Yilun Qiu, Xiaoyan Zhao, Yang Zhang, Yimeng Bai, Wenjie Wang, Hong Cheng, Fuli Feng, Tat-Seng Chua
Abstract
Personalizing Large Language Models (LLMs) has become a critical step in facilitating their widespread application to enhance individual life experiences. In pursuit of personalization, distilling key preference information from an individual's historical data as instructional preference context to customize LLM generation has emerged as a promising direction. However, these methods face a fundamental limitation by overlooking the inter-user comparative analysis, which is essential for identifying the inter-user differences that truly shape preferences. To address this limitation, we propose Differenceaware Personalization Learning (DPL), a novel approach that emphasizes extracting inter-user differences to enhance LLM personalization. DPL strategically selects representative users for comparison and establishes a structured standard to extract meaningful, task-relevant differences for customizing LLM generation. Extensive experiments on real-world datasets demonstrate that DPL significantly enhances LLM personalization. We release our code at https://github.com/SnowCharmQ/DPL.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
12 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Personalized Generation In Large Model Era: A Survey cites HYDRA: Model Factorization Framework for Black-Box LLM Personalization
- Personalized Generation In Large Model Era: A Survey cites G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment
- Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment cites HYDRA: Model Factorization Framework for Black-Box LLM Personalization
- Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment cites Efficient Memory Management for Large Language Model Serving with PagedAttention
- NextQuill: Causal Preference Modeling for Enhancing LLM Personalization cites Harnessing Large Language Models for Text-Rich Sequential Recommendation
- NextQuill: Causal Preference Modeling for Enhancing LLM Personalization cites HYDRA: Model Factorization Framework for Black-Box LLM Personalization
- L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models cites Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
- Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation cites Harnessing Large Language Models for Text-Rich Sequential Recommendation
- Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation cites NextQuill: Causal Preference Modeling for Enhancing LLM Personalization
Cited by top-tier papers12
- Personalized Generation In Large Model Era: A SurveyYiyan Xu, Jinghao Zhang, Alireza Salemi, Xinting Hu et al.ACL 2025 · 45 citations
- NextQuill: Causal Preference Modeling for Enhancing LLM PersonalizationXiaoyan Zhao, Juntao You, Yang Zhang, Wenjie Wang et al.ICLR 2026 · 38 citations
- Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form GenerationChengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao et al.ICLR 2026 · 35 citations
- Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized AlignmentWeixiang Zhao, Xingyu Sui, Yulin Hu, Jiahe Guo et al.NeurIPS 2025 · 34 citations
- L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language ModelsXiaohao Liu, Xiaobo Xia, Weixiang Zhao, Manyi Zhang et al.NeurIPS 2025 · 16 citations
Builds on23
- Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
- G-Eval: NLG Evaluation using Gpt-4 with Better Human AlignmentYang Liu, Dan Iter, Yichong Xu, Shuohang Wang et al.EMNLP 2023 · 549 citations
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic EncodersYupeng Hou, Jiacheng Li, Xiangjun Fu, Zhankui He et al.ACL 2026 · 346 citations
- Harnessing Large Language Models for Text-Rich Sequential RecommendationZhi Zheng, Wenshuo Chao, Zhaopeng Qiu, Hengshu Zhu et al.WWW 2024 · 114 citations
- HYDRA: Model Factorization Framework for Black-Box LLM PersonalizationYuchen Zhuang, Haotian Sun, Yue Yu, Rushi Qiang et al.NeurIPS 2024 · 79 citations
Related papers
- Latent Inter-User Difference Modeling for LLM PersonalizationYilun Qiu, Tianhao Shi, Xiaoyan Zhao, Fengbin Zhu et al.EMNLP 2025 · 1 citation
- LLMs + Persona-Plug = Personalized LLMsJiongnan Liu, Yutao Zhu, Shuting Wang, Xiaochi Wei et al.ACL 2025 · 19 citations
- Guided Profile Generation Improves Personalization with Large Language ModelsJiarui ZhangEMNLP Findings 2024 · 6 citations
- Personalizing LLMs with Binary Feedback: A Preference-Calibrated Optimization FrameworkXilai Ma, Liye Zhao, Weijun Yao, Haibing Di et al.ACL 2026
- Optimization Methods for Personalizing Large Language Models through Retrieval AugmentationAlireza Salemi, Surya Kallumadi, Hamed ZamaniSIGIR 2024 · 52 citations
