TY - GEN
T1 - Personalized Question Answering with User Profile Generation and Compression
AU - Su, Hang
AU - Yang, Yun
AU - Liu, Tianyang
AU - Liu, Xin
AU - Pu, Peng
AU - Lu, Xuesong
N1 - Publisher Copyright:
©2025 Association for Computational Linguistics.
PY - 2025
Y1 - 2025
N2 - Large language models (LLMs) offer a novel and convenient avenue for humans to acquire knowledge. However, LLMs are prone to providing "midguy" answers regardless of users’ knowledge background, thereby failing to meet each user’s personalized needs. To tackle the problem, we propose to generate personalized answers with LLMs based on users’ past question-answering records. We dynamically generate and update a user’s domain and global profiles as the user asks questions, and use the latest profile as the context to generate the answer for a newly-asked question. To save tokens, we propose to compress the domain profile into a set of keywords and use the keywords to prompt LLMs. We theoretically analyze the effectiveness of the compression strategy. Experimental results show that our method can generate more personalized answers than comparative methods. The code and dataset are available at https://github.com/DaSESmartEdu/PQA.
AB - Large language models (LLMs) offer a novel and convenient avenue for humans to acquire knowledge. However, LLMs are prone to providing "midguy" answers regardless of users’ knowledge background, thereby failing to meet each user’s personalized needs. To tackle the problem, we propose to generate personalized answers with LLMs based on users’ past question-answering records. We dynamically generate and update a user’s domain and global profiles as the user asks questions, and use the latest profile as the context to generate the answer for a newly-asked question. To save tokens, we propose to compress the domain profile into a set of keywords and use the keywords to prompt LLMs. We theoretically analyze the effectiveness of the compression strategy. Experimental results show that our method can generate more personalized answers than comparative methods. The code and dataset are available at https://github.com/DaSESmartEdu/PQA.
UR - https://www.scopus.com/pages/publications/105028956128
U2 - 10.18653/v1/2025.findings-emnlp.255
DO - 10.18653/v1/2025.findings-emnlp.255
M3 - 会议稿件
AN - SCOPUS:105028956128
T3 - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025
SP - 4744
EP - 4763
BT - EMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025
A2 - Christodoulopoulos, Christos
A2 - Chakraborty, Tanmoy
A2 - Rose, Carolyn
A2 - Peng, Violet
PB - Association for Computational Linguistics (ACL)
T2 - 30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
Y2 - 4 November 2025 through 9 November 2025
ER -