paper-with-me

Papers

Reasoning-Based Personalized Generation for Users with Sparse Data

2026-01-31 · Bo Ni, Branislav Kveton, Samyadeep Basu, Subhojyoti Mukherjee, Leyao Wang, Franck Dernoncourt, Sungchul Kim, Seunghyun Yoon, Zichao Wang, Ruiyi Zhang, Puneet Mathur, Jihyung Kil, Jiuxiang Gu, Nedim Lipka, Yu Wang, Ryan A. Rossi, Tyler Derr arxiv

Large Language Model (LLM) personalization holds great promise for tailoring responses by leveraging personal context and history. However, real-world users usually possess sparse interaction histories with limited personal context, such as cold-start users in social platforms and newly registered customers in online E-commerce platforms, compromising the LLM-based personalized generation. To address this challenge, we introduce GraSPer (Graph-based Sparse Personalized Reasoning), a novel framework for enhancing personalized text generation under sparse context. GraSPer first augments user context by predicting items that the user would likely interact with in the future. With reasoning alignment, it then generates texts for these interactions to enrich the augmented context. In the end, it generates personalized outputs conditioned on both the real and synthetic histories, ensuring alignment with user style and preferences. Extensive experiments on three benchmark personalized generation datasets show that GraSPer achieves significant performance gain, substantially improving personalization in sparse user context settings.

📄 PDF Abstract BibTeX arXiv:2602.21219

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Similar Papers 제목 키워드 기반

Sparse Personalized Text Generation with Multi-Trajectory Reasoning

2026-04-27 · Bo Ni, Haowei Fu, Qinwen Ge, Franck Dernoncourt 외 arxiv

As Large Language Models (LLMs) advance, personalization has become a key mechanism for tailoring outputs to individual user needs. However, most existing methods rely heavily on dense interaction histories, making them …

Reinforcement LearningText Generation

Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation

2025-12-07 · Chengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao 외 arxiv

Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level preferences, overlooking individual users. Personalization is e…

Response Generation

Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

2022-04-18 · NAACL 2022 7 · Hanxun Zhong, Zhicheng Dou, Yutao Zhu, Hongjin Qian 외

Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which has raised much attention in recent years. Existing personalized dialogue systems have trie…

Dialogue GenerationResponse Generation

Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Personalized dialogue systems explore the problem of generating responses that are consistent with the user's personality, which have raised much attention in recent years. Existing personalized dialogue systems have tri…

Dialogue GenerationResponse Generation

ODYSSE: Episode-wise Policy Optimization for Personalized Agentic Reasoning

2026-07-28 · Jiaqi Zhang, Tong Chen, Junliang Yu, Quoc Viet Hung Nguyen 외 arxiv

Agentic systems have rapidly advanced in their ability to interact with real-world environments, leverage external tools, and provide services for users. However, unlike natural-world tasks that assume well-defined instr…