Chen Luo
Research Subjects
Chen Luo has a total of 95 co-authors. Here are the top co-authors by number of shared publications:
- Xianfeng Tang
Amazon, Palo Alto, CA, USA
5 shared publications - Hamed Zamani
Center for Intelligent Information Retrieval, University of Massachusetts Amherst, Amherst, MA, USA
3 shared publications - Hui Liu
Amazon, Palo Alto, CA, USA
3 shared publications - Jiliang Tang
Michigan State University, East Lansing, MI, USA
3 shared publications - Monica Cheng
Amazon, Palo Alto, CA, USA
3 shared publications - Qi He
Amazon, Palo Alto, CA, USA
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2424-2434
AutoCSF: A Provably Safe Indexing Framework for Filter-Augmented Compressed Static Functions
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2424-2434
Open AccessAutoCSF: A Provably Safe Indexing Framework for Filter-Augmented Compressed Static Functions
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1673-1681
Which LLM to Fine-Tune? Agent-Driven Model Selection at Scale
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1673-1681
Open AccessWhich LLM to Fine-Tune? Agent-Driven Model Selection at Scale
- Open Access
- 12 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
How Far Are LLMs from Real Search: Rethinking the Complementary Roles of Search and Learning
Search plays a fundamental role in problem-solving across various domains, with most real-world decision-making problems being solvable through systematic search. Drawing inspiration from recent discussions on search and learning, we systematically explore the complementary relationship between search and Large Language Models (LLMs) from three perspectives. First, we analyze how learning can enhance search efficiency and propose Se arch vi a L earning ( SeaL ), a framework that leverages LLMs for effective and efficient search. Second, we further extend SeaL to SeaL-C to ensure rigorous completeness during search. Our evaluation across three real-world planning tasks demonstrates that SeaL achieves near-perfect accuracy while reducing search spaces by up to 99.1% compared to traditional approaches. Finally, we explore how far LLMs are from real search by investigating whether they can develop search capabilities independently. Our analysis reveals that while current LLMs struggle with efficient search in complex problems, incorporating systematic search strategies significantly enhances their problem-solving capabilities. These findings not only validate the effectiveness of our approach but also highlight the need for improving LLMs’ search abilities for real-world applications. Our code is available at https://github.com/ventr1c/SeaL .
- 12 August 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
Open AccessHow Far Are LLMs from Real Search: Rethinking the Complementary Roles of Search and Learning
Search plays a fundamental role in problem-solving across various domains, with most real-world decision-making problems being solvable through systematic search. Drawing inspiration from recent discussions on search and learning, we systematically explore the complementary relationship between search and Large Language Models (LLMs) from three perspectives. First, we analyze how learning can enhance search efficiency and propose Se arch vi a L earning ( SeaL ), a framework that leverages LLMs for effective and efficient search. Second, we further extend SeaL to SeaL-C to ensure rigorous completeness during search. Our evaluation across three real-world planning tasks demonstrates that SeaL achieves near-perfect accuracy while reducing search spaces by up to 99.1% compared to traditional approaches. Finally, we explore how far LLMs are from real search by investigating whether they can develop search capabilities independently. Our analysis reveals that while current LLMs struggle with efficient search in complex problems, incorporating systematic search strategies significantly enhances their problem-solving capabilities. These findings not only validate the effectiveness of our approach but also highlight the need for improving LLMs’ search abilities for real-world applications. Our code is available at https://github.com/ventr1c/SeaL .
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4790-4794
Building a Production Shopping Agent at Scale
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4790-4794
Open AccessBuilding a Production Shopping Agent at Scale
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6278-6279
The 2nd Workshop on Large Language Models for E-Commerce
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6278-6279
Open AccessThe 2nd Workshop on Large Language Models for E-Commerce
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4244-4248
Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4244-4248
Open AccessExamples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4314-4318
Language Model Alignment for Conversational Shopping at Amazon
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 4314-4318
Open AccessLanguage Model Alignment for Conversational Shopping at Amazon
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2699-2700
Large Language Model for E-Commerce Workshop
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2699-2700
Open AccessLarge Language Model for E-Commerce Workshop
- 21 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (4) , 3465-3482
Enabling Generalized Zero-Shot Vulnerability Classification
Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This paper introduces $\mathsf{VulnSense}$, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem. $\mathsf{VulnSense}$ learns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically, $\mathsf{VulnSense}$ learns from three main resources: (1) seen classes with labeled code instances; (2) descriptions of these seen classes; and (3) descriptions of “unseen” classes which have no labeled instances. Our experiments underscore $\mathsf{VulnSense}$'s superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities. $\mathsf{VulnSense}$ demonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work.- 21 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (4) , 3465-3482
Enabling Generalized Zero-Shot Vulnerability Classification
Regarding computer security, the growth of code vulnerability types presents a persistent challenge. These vulnerabilities, which may cause severe consequences, necessitate precise classification for effective mitigation. However, the rapid emergence of new vulnerability types complicates the classification process. Traditional methodologies, which often involve human expertise and the manual labeling or generation of example instances, are not only resource-intensive but also struggle to adapt to the dynamic nature of these vulnerabilities. This paper introduces $\mathsf{VulnSense}$, an innovative method that harnesses the capabilities of Generalized Zero-Shot Learning (GZSL) to address the vulnerability classification problem. $\mathsf{VulnSense}$ learns about unseen vulnerability classes from the descriptions of these unseen classes, while not requiring to see any instances of these unseen classes. Specifically, $\mathsf{VulnSense}$ learns from three main resources: (1) seen classes with labeled code instances; (2) descriptions of these seen classes; and (3) descriptions of “unseen” classes which have no labeled instances. Our experiments underscore $\mathsf{VulnSense}$'s superiority over existing GZSL methods in classifying instances of unseen classes. Concurrently, it maintains a performance parity with traditional labeled-example based learning methods in classifying instances of seen vulnerabilities. $\mathsf{VulnSense}$ demonstrates the potential of using GZSL for vulnerability classification, while also highlighting challenges that inspire future work.- Open Access
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 71-82
Understanding Inter-Session Intentions via Complex Logical Reasoning
Understanding user intentions is essential for improving product recommendations, navigation suggestions, and query reformulations. However, user intentions can be intricate, involving multiple sessions and attribute requirements connected by logical operators such as And, Or, and Not. For instance, a user may search for Nike or Adidas running shoes across various sessions, with a preference for purple. In another example, a user may have purchased a mattress in a previous session and is now looking for a matching bed frame without intending to buy another mattress. Existing research on session understanding has not adequately addressed making product or attribute recommendations for such complex intentions. In this paper, we present the task of logical session complex query answering (LS-CQA), where sessions are treated as hyperedges of items, and we frame the problem of complex intention understanding as an LS-CQA task on an aggregated hypergraph of sessions, items, and attributes. This is a unique complex query answering task with sessions as ordered hyperedges. We also introduce a new model, the Logical Session Graph Transformer (LSGT), which captures interactions among items across different sessions and their logical connections using a transformer structure. We analyze the expressiveness of LSGT and prove the permutation invariance of the inputs for the logical operators. By evaluating LSGT on three datasets, we demonstrate that it achieves state-of-the-art results.
- 24 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 71-82
Open AccessUnderstanding Inter-Session Intentions via Complex Logical Reasoning
Understanding user intentions is essential for improving product recommendations, navigation suggestions, and query reformulations. However, user intentions can be intricate, involving multiple sessions and attribute requirements connected by logical operators such as And, Or, and Not. For instance, a user may search for Nike or Adidas running shoes across various sessions, with a preference for purple. In another example, a user may have purchased a mattress in a previous session and is now looking for a matching bed frame without intending to buy another mattress. Existing research on session understanding has not adequately addressed making product or attribute recommendations for such complex intentions. In this paper, we present the task of logical session complex query answering (LS-CQA), where sessions are treated as hyperedges of items, and we frame the problem of complex intention understanding as an LS-CQA task on an aggregated hypergraph of sessions, items, and attributes. This is a unique complex query answering task with sessions as ordered hyperedges. We also introduce a new model, the Logical Session Graph Transformer (LSGT), which captures interactions among items across different sessions and their logical connections using a transformer structure. We analyze the expressiveness of LSGT and prove the permutation invariance of the inputs for the logical operators. By evaluating LSGT on three datasets, we demonstrate that it achieves state-of-the-art results.