Yibo Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yibo Wang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Philip S. Yu
University of Illinois Chicago
3 shared publications - Amara Tariq
Department of Radiology, Mayo Clinic, Phoenix, USA
1 shared publication - Bo Liu
Hefei University of Technology, Hefei, China
1 shared publication - Congying Xia
University of Illinois at Chicago, Chicago, IL, USA
1 shared publication - Fiza Khan
Department of Radiology, Emory School of Medicine, Atlanta, GA 303224, USA
1 shared publication - Guan Wang
Huski Inc
1 shared publication
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 722-727
Personalized Recommendation Tool Learning via Autonomous Language Agents
Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based Personalized Recommendation Tool learning via autonomous language Agents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of PRTA over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance. Our code implementation is available online1.
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 722-727
Open AccessPersonalized Recommendation Tool Learning via Autonomous Language Agents
Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based Personalized Recommendation Tool learning via autonomous language Agents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of PRTA over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance. Our code implementation is available online1.
- Open Access
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1884-1888
Click-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce
Position bias, the phenomenon whereby users tend to focus on higher-ranked items of the search result list regardless of the actual relevance to queries, is prevailing in many ranking systems. Position bias in training data biases the ranking model, leading to increasingly unfair item rankings, click-through-rate (CTR), and conversion rate (CVR) predictions. To jointly mitigate position bias in both item CTR and CVR prediction, we propose two position-bias-free CTR and CVR prediction models: Position-Aware Click-Conversion (PACC) and PACC via Position Embedding (PACC-PE). PACC is built upon probability decomposition and models position information as a probability. PACC-PE utilizes neural networks to model product-specific position information as embedding. Experiments on the E-commerce sponsored product search dataset show that our proposed models have better ranking effectiveness and can greatly alleviate position bias in both CTR and CVR prediction.
- 18 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 1884-1888
Open AccessClick-Conversion Multi-Task Model with Position Bias Mitigation for Sponsored Search in eCommerce
Position bias, the phenomenon whereby users tend to focus on higher-ranked items of the search result list regardless of the actual relevance to queries, is prevailing in many ranking systems. Position bias in training data biases the ranking model, leading to increasingly unfair item rankings, click-through-rate (CTR), and conversion rate (CVR) predictions. To jointly mitigate position bias in both item CTR and CVR prediction, we propose two position-bias-free CTR and CVR prediction models: Position-Aware Click-Conversion (PACC) and PACC via Position Embedding (PACC-PE). PACC is built upon probability decomposition and models position information as a probability. PACC-PE utilizes neural networks to model product-specific position information as embedding. Experiments on the E-commerce sponsored product search dataset show that our proposed models have better ranking effectiveness and can greatly alleviate position bias in both CTR and CVR prediction.
- Open Access
Continuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing
The explosion of e-commerce has caused the need for processing and analysis of product titles, like entity typing in product titles. However, the rapid activity in e-commerce has led to the rapid emergence of new entities, which is difficult to be solved by general entity typing. Besides, product titles in e-commerce have very different language styles from text data in general domain. In order to handle new entities in product titles and address the special language styles problem of product titles in e-commerce domain, we propose our textual entailment model with continuous prompt tuning based hypotheses and fusion embeddings for e-commerce entity typing. First, we reformulate the entity typing task into a textual entailment problem to handle new entities that are not present during training. Second, we design a model to automatically generate textual entailment hypotheses using a continuous prompt tuning method, which can generate better textual entailment hypotheses without manual design. Third, we utilize the fusion embeddings of BERT embedding and CharacterBERT embedding with a two-layer MLP classifier to solve the problem that the language styles of product titles in e-commerce are different from that of general domain. To analyze the effect of each contribution, we compare the performance of entity typing and textual entailment model, and conduct ablation studies on continuous prompt tuning and fusion embeddings. We also evaluate the impact of different prompt template initialization for the continuous prompt tuning. We show our proposed model improves the average F1 score by around 2% compared to the baseline BERT entity typing model.
Open AccessContinuous Prompt Tuning Based Textual Entailment Model for E-commerce Entity Typing
The explosion of e-commerce has caused the need for processing and analysis of product titles, like entity typing in product titles. However, the rapid activity in e-commerce has led to the rapid emergence of new entities, which is difficult to be solved by general entity typing. Besides, product titles in e-commerce have very different language styles from text data in general domain. In order to handle new entities in product titles and address the special language styles problem of product titles in e-commerce domain, we propose our textual entailment model with continuous prompt tuning based hypotheses and fusion embeddings for e-commerce entity typing. First, we reformulate the entity typing task into a textual entailment problem to handle new entities that are not present during training. Second, we design a model to automatically generate textual entailment hypotheses using a continuous prompt tuning method, which can generate better textual entailment hypotheses without manual design. Third, we utilize the fusion embeddings of BERT embedding and CharacterBERT embedding with a two-layer MLP classifier to solve the problem that the language styles of product titles in e-commerce are different from that of general domain. To analyze the effect of each contribution, we compare the performance of entity typing and textual entailment model, and conduct ablation studies on continuous prompt tuning and fusion embeddings. We also evaluate the impact of different prompt template initialization for the continuous prompt tuning. We show our proposed model improves the average F1 score by around 2% compared to the baseline BERT entity typing model.
- 21 September 2021
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 123, 103918
Query bot for retrieving patients’ clinical history: A COVID-19 use-case
- 21 September 2021
- Published by Elsevier in Journal of Biomedical Informatics
- Vol. 123, 103918
Query bot for retrieving patients’ clinical history: A COVID-19 use-case
- Open Access
- 1 June 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1948 (1) , 012014
An Automotive Unknown-Environment Explorer Robot Based on Braitenberg Vehicle Four
Environment exploration is an essential task in robotics, but it requires lots of high-tech sensors, which will make the robot very costly. To complete the exploration, a huge number of robots are required. Then, how to explore an unknown environment using simple robots with simple sensors is a significant problem to be studied. In this paper, robots are built based on Braitenberg Vehicle 4 and the robots are made to explore an unknown environment without a human. Braitenberg Vehicles are a series concept created by V. Braitenberg. Braitenberg Vehicle 4, particularly, is a robot that only has reflection level intelligence. The Robot’s logic is only four parts, going straight, turning left, turning right, and turning around. The simplicity of the design allows putting the Robot into mass production. MATLAB is used to simulate the working process of the Robot to test the Robot’s feasibility. Then, the map drawn by the Robot with the actual environment is compared. The result has shown that the map we got is almost the same as the real surroundings.
- 1 June 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 1948 (1) , 012014
Open AccessAn Automotive Unknown-Environment Explorer Robot Based on Braitenberg Vehicle Four
Environment exploration is an essential task in robotics, but it requires lots of high-tech sensors, which will make the robot very costly. To complete the exploration, a huge number of robots are required. Then, how to explore an unknown environment using simple robots with simple sensors is a significant problem to be studied. In this paper, robots are built based on Braitenberg Vehicle 4 and the robots are made to explore an unknown environment without a human. Braitenberg Vehicles are a series concept created by V. Braitenberg. Braitenberg Vehicle 4, particularly, is a robot that only has reflection level intelligence. The Robot’s logic is only four parts, going straight, turning left, turning right, and turning around. The simplicity of the design allows putting the Robot into mass production. MATLAB is used to simulate the working process of the Robot to test the Robot’s feasibility. Then, the map drawn by the Robot with the actual environment is compared. The result has shown that the map we got is almost the same as the real surroundings.