Jianing Wang

Jianing Wang

Auto-generated profile, based on publicly available information

Jianing Wang

University of California San Diego, La Jolla, CA, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
24 August 2024
Verified
Conference Paper
Open access
JWJunda Wu
Junda Wu
CCCheng-Chun Chang
Cheng-Chun Chang
TYTong Yu
Tong Yu
ZHZhankui He
Zhankui He
JWJianing Wang
Jianing Wang
JMJulian J. McAuley
Julian J. McAuley
The long-tail recommendation is a challenging task for traditional recommender systems, due to data sparsity and data imbalance issues. The recent development of large language models (LLMs) has shown their abilities in complex reasoning, which can help to deduce users' preferences based on very few previous interactions. However, since most LLM-based systems rely on items' semantic meaning as the sole evidence for reasoning, the collaborative information of user-item interactions is neglected, which can cause the LLM's reasoning to be misaligned with task-specific collaborative information of the dataset. To further align LLMs' reasoning to task-specific user-item interaction knowledge, we introduce collaborative retrieval-augmented LLMs, CoRAL, which directly incorporate collaborative evidence into the prompts. Based on the retrieved user-item interactions, the LLM can analyze shared and distinct preferences among users, and summarize the patterns indicating which types of users would be attracted by certain items. The retrieved collaborative evidence prompts the LLM to align its reasoning with the user-item interaction patterns in the dataset. However, since the capacity of the input prompt is limited, finding the minimally-sufficient collaborative information for recommendation tasks can be challenging. We propose to find the optimal interaction set through a sequential decision-making process and develop a retrieval policy learned through a reinforcement learning (RL) framework, CoRAL. Our experimental results show that CoRAL can significantly improve LLMs' reasoning abilities on specific recommendation tasks. Our analysis also reveals that CoRAL can more efficiently explore collaborative information through reinforcement learning.

21 October 2023
Verified
Conference Paper
Open access
JWJianing Wang
Jianing Wang
NCNuo Chen
Nuo Chen
QSQiushi Sun
Qiushi Sun
WHWenkang Huang
Wenkang Huang
CWChengyu Wang
Chengyu Wang
MGMing Gao
Ming Gao

13 March 2023 in arXiv
Verified
Preprint
Open access
PDF file
CWChengyu Wang
Chengyu Wang
MQMinghui Qiu
Minghui Qiu
CSChen Shi
Chen Shi
TZTaolin Zhang
Taolin Zhang
TLTingting Liu
Tingting Liu
WLWei Lin
Wei Lin
The success of Pre-Trained Models (PTMs) has reshaped the development of Natural Language Processing (NLP). Yet, it is not easy to obtain high-performing models and deploy them online for industrial practitioners. To bridge this gap, EasyNLP is designed to make it easy to build NLP applications, which supports a comprehensive suite of NLP algorithms. It further features knowledge-enhanced pre-training, knowledge distillation and few-shot learning functionalities for large-scale PTMs, and provides a unified framework of model training, inference and deployment for real-world applications. Currently, EasyNLP has powered over ten business units within Alibaba Group and is seamlessly integrated to the Platform of AI (PAI) products on Alibaba Cloud. The source code of our EasyNLP toolkit is released at GitHub (https://github.com/alibaba/EasyNLP).

6 May 2022 in arXiv
Verified
Preprint
Open access
PDF file
JWJianing Wang
Jianing Wang
CWChengyu Wang
Chengyu Wang
MQMinghui Qiu
Minghui Qiu
QSQiuhui Shi
Qiuhui Shi
HWHongbin Wang
Hongbin Wang
Ming GaoMing Gao
Ming Gao
Extractive Question Answering (EQA) is one of the most important tasks in Machine Reading Comprehension (MRC), which can be solved by fine-tuning the span selecting heads of Pre-trained Language Models (PLMs). However, most existing approaches for MRC may perform poorly in the few-shot learning scenario. To solve this issue, we propose a novel framework named Knowledge Enhanced Contrastive Prompt-tuning (KECP). Instead of adding pointer heads to PLMs, we introduce a seminal paradigm for EQA that transform the task into a non-autoregressive Masked Language Modeling (MLM) generation problem. Simultaneously, rich semantics from the external knowledge base (KB) and the passage context are support for enhancing the representations of the query. In addition, to boost the performance of PLMs, we jointly train the model by the MLM and contrastive learning objectives. Experiments on multiple benchmarks demonstrate that our method consistently outperforms state-of-the-art approaches in few-shot settings by a large margin.

16 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
JWJianing Wang
Jianing Wang
WHWenkang Huang
Wenkang Huang
QSQiuhui Shi
Qiuhui Shi
HWHongbin Wang
Hongbin Wang
MQMinghui Qiu
Minghui Qiu
Ming GaoMing Gao
Ming Gao
Knowledge-enhanced Pre-trained Language Model (PLM) has recently received significant attention, which aims to incorporate factual knowledge into PLMs. However, most existing methods modify the internal structures of fixed types of PLMs by stacking complicated modules, and introduce redundant and irrelevant factual knowledge from knowledge bases (KBs). In this paper, to address these problems, we introduce a seminal knowledge prompting paradigm and further propose a knowledge-prompting-based PLM framework KP-PLM. This framework can be flexibly combined with existing mainstream PLMs. Specifically, we first construct a knowledge sub-graph from KBs for each context. Then we design multiple continuous prompts rules and transform the knowledge sub-graph into natural language prompts. To further leverage the factual knowledge from these prompts, we propose two novel knowledge-aware self-supervised tasks including prompt relevance inspection and masked prompt modeling. Extensive experiments on multiple natural language understanding (NLU) tasks show the superiority of KP-PLM over other state-of-the-art methods in both full-resource and low-resource settings.

1 October 2023 in Highlights in Art and Design
Verified
Journal Article
Open access
PDF file
JWJianing Wang
Jianing Wang
Stop-motion Animation is a special form of animation. With the development of the times, the Stop-motion Animation is more and more well-known to the public, and the application of the field is more and more extensive. Followed its development in the fields of film, advertising, MV and so on, more and more creative works have appeared, and the creative materials have also become more and more abundant. Material is one of the most important differences between two-dimensional animation and three-dimensional animation, as well as creative media. However, whether it is a Stop-motion Animation or other forms of film and television works, better performance of creativity is the ultimate goal, so the material is also in the Stop-motion Animation for creative services. Therefore, as far as I am concerned, I'm looking at how to select materials and use materials to express creativity is of great significance to the flexible expression of Stop-motion Animation. Compared with the feature-length stop-motion animation, the short film is more abundant in materials and creative in the content, so my research scope is limited to the short-film stop-motion animation. This thesis discusses the relationship between materials and creativity in different types of short film stop-motion animation. The creativity is divided into materials and artistic styles by analyzing the material characteristics and creative cases of different types of short film stop-motion animation. At the three levels of plot, the originality of material, the relationship between material and artistic style, the relationship between material and plot, and finally how to make material are discussed, ultimately coming to the conclusion of a better combination of material and creativity.