Kaixin Wu

Kaixin Wu

Auto-generated profile, based on publicly available information

Kaixin Wu

Ant Group, Hangzhou, 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
18 December 2024 in IEEE Transactions on Audio, Speech and Language Processing
Verified
Journal Article
Closed access
BJBaijun Ji
Baijun Ji
XDXiangyu Duan
Xiangyu Duan
YZYue Zhang
Yue Zhang
KWKaixin Wu
Kaixin Wu
Min ZhangMin Zhang
Min Zhang
One promising aspect of using large language models (LLMs) for translation is their ability to adapt effectively to unseen domains without fine-tuning, through strategic prompting. However, the success of this approach largely depends on the selection of relevant examples from domain-specific databases to construct the few-shot prompt for the given input. This work propose a novel zero-shot technique that circumvents data limitations by generating synthetic translation examples from monolingual domain-specific target texts. Our preliminary experiments suggest that LLMs demonstrate increased sensitivity to noise on the target side of examples, while maintaining a tolerance for variations in example quality. Based on these findings, we generate pseudo-examples by using a cross-lingual sentence encoder to identify sentences in the target language that correspond to the input, and then pairing them with coarse translations derived from a dictionary. To improve the retrieval of better pseudo-examples for translation tasks, we enhance the sentence encoder by incorporating domain information through conditional layer normalization and introducing two innovative training objectives: LLM Preference Prediction and Windowed Sentence Prediction. Experiments conducted across various domains demonstrate that our approach not only significantly outperforms previous zero-shot methods but is also comparable to the robust NLLB-3.3B and ALMA-13B(-R) model.

13 July 2025
Verified
Conference Paper
Open access
YSYedan Shen
Yedan Shen
KWKaixin Wu
Kaixin Wu
YDYuechen Ding
Yuechen Ding
JWJingyuan Wen
Jingyuan Wen
HLHong Liu
Hong Liu
LMLinjian Mo
Linjian Mo

21 October 2024
Verified
Conference Paper
Open access
HLHong Liu
Hong Liu
SGSaisai Gong
Saisai Gong
YJYixin Ji
Yixin Ji
KWKaixin Wu
Kaixin Wu
JXJia Xu
Jia Xu
JGJinjie Gu
Jinjie Gu
Relevance modeling plays a crucial role in e-commerce search engines, striving to identify the utmost pertinent items corresponding to a given search query. With the rapid advancement of pre-trained large language models (LLMs), recent endeavors have leveraged the capabilities of LLMs in relevance modeling, resulting in enhanced performance. This is usually done through the process of fine-tuning LLMs on specifically annotated datasets to determine the relevance between queries and items. However, there are two limitations when LLMs are naively employed for relevance modeling through fine-tuning and inference. First, it is not inherently efficient for performing nuanced tasks beyond simple yes or no answers, such as assessing search relevance. It may therefore tend to be overconfident and struggle to distinguish fine-grained degrees of relevance (e.g., strong relevance, weak relevance, irrelevance) used in search engines. Second, it exhibits significant performance degradation when confronted with data distribution shift in real-world scenarios. In this paper, we propose a novel Distribution-Aware Robust Learning framework (DaRL) for relevance modeling in Alipay Search. Specifically, we design an effective loss function to enhance the discriminability of LLM-based relevance modeling across various fine-grained degrees of query-item relevance. To improve the generalizability of LLM-based relevance modeling, we first propose the Distribution-Aware Sample Augmentation (DASA) module. This module utilizes out-of-distribution (OOD) detection techniques to actively select appropriate samples that are not well covered by the original training set for model fine-tuning. Furthermore, we adopt a multi-stage fine-tuning strategy to simultaneously improve in-distribution (ID) and OOD performance, bridging the performance gap between them. DaRL has been deployed online to serve the Alipay's insurance product search. Both offline experiments on real-world industry data and online A/B testing show that DaRL effectively improves the performance of relevance modeling.

13 July 2025
Verified
Conference Paper
Open access
QZQi Zheng
Qi Zheng
MZMingjie Zhong
Mingjie Zhong
SGSaisai Gong
Saisai Gong
HJHuimin Jiang
Huimin Jiang
KWKaixin Wu
Kaixin Wu
LMLinjian Mo
Linjian Mo