Haoxin Zhang

Haoxin Zhang

Auto-generated profile, based on publicly available information

Haoxin Zhang

Xiaohongshu Inc., Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 July 2025
Verified
Conference Paper
Open access
CZChao Zhang
Chao Zhang
HZHaoxin Zhang
Haoxin Zhang
SWShiwei Wu
Shiwei Wu
DWDi Wu
Di Wu
Tong XuTong Xu
Tong Xu
ECEnhong Chen
Enhong Chen

13 May 2024
Verified
Conference Paper
Open access
CZChao Zhang
Chao Zhang
SWShiwei Wu
Shiwei Wu
HZHaoxin Zhang
Haoxin Zhang
Tong XuTong Xu
Tong Xu
YGYan Gao
Yan Gao
ECEnhong Chen
Enhong Chen
People enjoy sharing "notes" including their experiences within online communities. Therefore, recommending notes aligned with user interests has become a crucial task. Existing online methods only input notes into BERT-based models to generate note embeddings for assessing similarity. However, they may underutilize some important cues, e.g., hashtags or categories, which represent the key concepts of notes. Indeed, learning to generate hashtags/categories can potentially enhance note embeddings, both of which compress key note information into limited content. Besides, Large Language Models (LLMs) have significantly outperformed BERT in understanding natural languages. It is promising to introduce LLMs into note recommendation. In this paper, we propose a novel unified framework called NoteLLM, which leverages LLMs to address the item-to-item (I2I) note recommendation. Specifically, we utilize Note Compression Prompt to compress a note into a single special token, and further learn the potentially related notes' embeddings via a contrastive learning approach. Moreover, we use NoteLLM to summarize the note and generate the hashtag/category automatically through instruction tuning. Extensive validations on real scenarios demonstrate the effectiveness of our proposed method compared with the online baseline and show major improvements in the recommendation system of Xiaohongshu.

13 June 2026 in ACM Transactions on Information Systems
Verified
Journal Article
Open access
CZChao Zhang
Chao Zhang
YWYuhao Wang
Yuhao Wang
DXDerong Xu
Derong Xu
HZHaoxin Zhang
Haoxin Zhang
YLYuanjie Lyu
Yuanjie Lyu
ECEnhong Chen
Enhong Chen
Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models’ (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent agentic RAG has improved via reinforcement learning, they often incur substantial token overhead from search and reasoning. This trade-off prioritizes accuracy over efficiency. To address this issue, this work proposes TeaRAG, a T oken- e fficient a gentic RAG framework capable of compressing both retrieval content and reasoning steps. 1) First, the retrieved content is compressed by augmenting chunk-based semantic retrieval with a graph retrieval using concise triplets. A knowledge association graph is then built from semantic similarity and co-occurrence. Finally, Personalized PageRank is leveraged to highlight key knowledge within this graph, reducing the number of tokens per retrieval. 2) Besides, to reduce reasoning steps, Iterative Process-aware Direct Preference Optimization (IP-DPO) is proposed. Specifically, our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps. This design can produce high-quality preference-pair datasets, supporting iterative DPO to improve reasoning conciseness. Across six datasets, improves the average Exact Match by \(4\%\) and \(2\%\) while reducing output tokens by \(61\%\) and \(59\%\) on Llama3‑8B‑Instruct and Qwen2.5‑14B‑Instruct, respectively. Code is available at https://github.com/Applied-Machine-Learning-Lab/TeaRAG .