About

James Caverlee is a Professor in the Department of Computer Science & Engineering at Texas A&M University. His research interests include web-scale information management, distributed data-intensive systems, information retrieval, databases, and social computing. He has received numerous awards, including the National Science Foundation CAREER Award in 2012, the Air Force Office of Scientific Research Young Investigator Award in 2012, and the DARPA Young Faculty Award in 2010. Dr. Caverlee holds a Ph.D. in Computer Science from Georgia Institute of Technology, an M.S. in Computer Science from Stanford University, an M.S. in Engineering-Economic Systems & Operations Research from Stanford University, and a B.A. in Economics magna cum laude from Duke University. His contributions include research on online reviews, geo-spatial preferences for expert recommendation, local expertise identification, and the dynamics of online memes.

Research topics

• Computer Science
• Artificial Intelligence
• Political Science
• Data Mining
• Computer Security
• Social Science
• Information Retrieval
• Data science
• Sociology
• Statistics
• World Wide Web
• Law
• Geography
• Internet privacy
• Database
• Telecommunications
• Business
• Theoretical computer science
• Cartography
• Advertising

Selected publications

• Language Models as Semantic Augmenters for Sequential Recommenders

  2026-04-30

  preprintOpen accessSenior author

  Large Language Models (LLMs) excel at capturing latent semantics and contextual relationships across diverse modalities. However, in modeling user behavior from sequential interaction data, performance often suffers when such semantic context is limited or absent. We introduce LaMAR, a LLM-driven semantic enrichment framework designed to enrich such sequences automatically. LaMAR leverages LLMs in a few-shot setting to generate auxiliary contextual signals by inferring latent semantic aspects of a user's intent and item relationships from existing metadata. These generated signals, such as inferred usage scenarios, item intents, or thematic summaries, augment the original sequences with greater contextual depth. We demonstrate the utility of this generated resource by integrating it into benchmark sequential modeling tasks, where it consistently improves performance. Further analysis shows that LLM-generated signals exhibit high semantic novelty and diversity, enhancing the representational capacity of the downstream models. This work represents a new data-centric paradigm where LLMs serve as intelligent context generators, contributing a new method for the semi-automatic creation of training data and language resources.

  PublisherOA PDFDOI

• PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactions

  2026-04-13

  articleOpen accessSenior author

  Prompting is central to interaction with AI systems, yet many users struggle to explore alternative directions, articulate creative intent, or understand how variations in prompts shape model outputs. We introduce prompt recommender systems (PRS) as an interaction approach that supports exploration, suggesting contextually relevant follow-up prompts. We present PromptHelper, a PRS prototype integrated into an AI chatbot that surfaces semantically diverse prompt suggestions while users work on real writing tasks. We evaluate PromptHelper in a 2x2 fully within-subjects study (N = 32) across creative and academic writing tasks. Results show that PromptHelper significantly increases users’ perceived exploration and expressiveness without increasing cognitive workload. Qualitative findings illustrate how prompt recommendations help users branch into new directions, overcome uncertainty about what to ask next, and better articulate their intent. We release open-source resources to support research on prompt recommendation. Our findings point to future work on AI interfaces that scaffold exploratory interaction while preserving user agency.

  PublisherDOI

• PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactions

  arXiv (Cornell University) · 2026-01-22

  preprintOpen accessSenior author

  Prompting is central to interaction with AI systems, yet many users struggle to explore alternative directions, articulate creative intent, or understand how variations in prompts shape model outputs. We introduce prompt recommender systems (PRS) as an interaction approach that supports exploration, suggesting contextually relevant follow-up prompts. We present PromptHelper, a PRS prototype integrated into an AI chatbot that surfaces semantically diverse prompt suggestions while users work on real writing tasks. We evaluate PromptHelper in a 2x2 fully within-subjects study (N=32) across creative and academic writing tasks. Results show that PromptHelper significantly increases users' perceived exploration and expressiveness without increasing cognitive workload. Qualitative findings illustrate how prompt recommendations help users branch into new directions, overcome uncertainty about what to ask next, and better articulate their intent. We discuss implications for designing AI interfaces that scaffold exploratory interaction while preserving user agency, and release open-source resources to support research on prompt recommendation.

  PublisherDOI

• PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactions

  ArXiv.org · 2026-01-22

  articleOpen accessSenior author

  Prompting is central to interaction with AI systems, yet many users struggle to explore alternative directions, articulate creative intent, or understand how variations in prompts shape model outputs. We introduce prompt recommender systems (PRS) as an interaction approach that supports exploration, suggesting contextually relevant follow-up prompts. We present PromptHelper, a PRS prototype integrated into an AI chatbot that surfaces semantically diverse prompt suggestions while users work on real writing tasks. We evaluate PromptHelper in a 2x2 fully within-subjects study (N=32) across creative and academic writing tasks. Results show that PromptHelper significantly increases users' perceived exploration and expressiveness without increasing cognitive workload. Qualitative findings illustrate how prompt recommendations help users branch into new directions, overcome uncertainty about what to ask next, and better articulate their intent. We discuss implications for designing AI interfaces that scaffold exploratory interaction while preserving user agency, and release open-source resources to support research on prompt recommendation.

  PublisherOA PDF

• Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models

  Proceedings of the International AAAI Conference on Web and Social Media · 2025-06-07

  articleOpen accessSenior author

  Masculine defaults are widely recognized as a significant type of gender bias, but they are often unseen as they are under-researched. Masculine defaults involve three key parts: (i) the cultural context, (ii) the masculine characteristics or behaviors, and (iii) the reward for, or simply acceptance of, those masculine characteristics or behaviors. In this work, we study discourse-based masculine defaults, and propose a twofold framework for (i) the large-scale discovery and analysis of gendered discourse words in spoken content via our Gendered Discourse Correlation Framework (GDCF); and (ii) the measurement of the gender bias associated with these gendered discourse words in LLMs via our Discourse Word-Embedding Association Test (D-WEAT). We focus our study on podcasts, a popular and growing form of social media, analyzing 15,117 podcast episodes. We analyze correlations between gender and discourse words -- discovered via LDA and BERTopic -- to automatically form gendered discourse word lists. We then study the prevalence of these gendered discourse words in domain-specific contexts, and find that gendered discourse-based masculine defaults exist in the domains of business, technology/politics, and video games. Next, we study the representation of these gendered discourse words from a state-of-the-art LLM embedding model from OpenAI, and find that the masculine discourse words have a more stable and robust representation than the feminine discourse words, which may result in better system performance on downstream tasks for men. Hence, men are rewarded for their discourse patterns with better system performance by one of the state-of-the-art language models -- and this embedding disparity is a representational harm and a masculine default.

  PublisherOA PDFDOI

• DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Management

  2025-01-01

  articleSenior author
  PublisherDOI

• A Survey on LLMs for Story Generation

  2025-01-01 · 2 citations

  articleOpen accessSenior author

  Maria Teleki, Vedangi Bengali, Xiangjue Dong, Sai Tejas Janjur, Haoran Liu, Tian Liu, Cong Wang, Ting Liu, Yin Zhang, Frank Shipman, James Caverlee. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.

  PublisherOA PDFDOI

• BI-DCGAN: A Theoretically Grounded Bayesian Framework for Efficient and Diverse GANs

  ArXiv.org · 2025-10-30

  preprintOpen accessSenior author

  Generative Adversarial Networks (GANs) are proficient at generating synthetic data but continue to suffer from mode collapse, where the generator produces a narrow range of outputs that fool the discriminator but fail to capture the full data distribution. This limitation is particularly problematic, as generative models are increasingly deployed in real-world applications that demand both diversity and uncertainty awareness. In response, we introduce BI-DCGAN, a Bayesian extension of DCGAN that incorporates model uncertainty into the generative process while maintaining computational efficiency. BI-DCGAN integrates Bayes by Backprop to learn a distribution over network weights and employs mean-field variational inference to efficiently approximate the posterior distribution during GAN training. We establishes the first theoretical proof, based on covariance matrix analysis, that Bayesian modeling enhances sample diversity in GANs. We validate this theoretical result through extensive experiments on standard generative benchmarks, demonstrating that BI-DCGAN produces more diverse and robust outputs than conventional DCGANs, while maintaining training efficiency. These findings position BI-DCGAN as a scalable and timely solution for applications where both diversity and uncertainty are critical, and where modern alternatives like diffusion models remain too resource-intensive.

  PublisherOA PDFDOI

• Flow Matching for Collaborative Filtering

  ArXiv.org · 2025-02-11

  preprintOpen accessSenior author

  Generative models have shown great promise in collaborative filtering by capturing the underlying distribution of user interests and preferences. However, existing approaches struggle with inaccurate posterior approximations and misalignment with the discrete nature of recommendation data, limiting their expressiveness and real-world performance. To address these limitations, we propose FlowCF, a novel flow-based recommendation system leveraging flow matching for collaborative filtering. We tailor flow matching to the unique challenges in recommendation through two key innovations: (1) a behavior-guided prior that aligns with user behavior patterns to handle the sparse and heterogeneous user-item interactions, and (2) a discrete flow framework to preserve the binary nature of implicit feedback while maintaining the benefits of flow matching, such as stable training and efficient inference. Extensive experiments demonstrate that FlowCF achieves state-of-the-art recommendation accuracy across various datasets with the fastest inference speed, making it a compelling approach for real-world recommender systems. The code is available at https://github.com/chengkai-liu/FlowCF.

  PublisherOA PDFDOI

• Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models

  2025-01-01 · 1 citations

  articleOpen accessSenior author

  We define masculine discourse words as discourse terms that are both socially normative and statistically associated with male speakers.We propose a twofold framework for (i) the large-scale discovery and analysis of gendered discourse words in spoken content via our Gendered Discourse Correlation Framework; and (ii) the measurement of the gender bias associated with these words in LLMs via our Discourse Word-Embedding Association Test.We focus our study on podcasts, a popular and growing form of social media, analyzing 15,117 podcast episodes.We analyze correlations between gender and discourse words -discovered via LDA and BERTopic.We then find that gendered discourse-based masculine defaults exist in the domains of business, technology/politics, and video games, indicating that these gendered discourse words are socially influential.Next, we study the representation of these words from a state-of-the-art LLM embedding model from OpenAI, and find that the masculine discourse words have a more stable and robust representation than the feminine discourse words, which may result in better system performance on downstream tasks for men.Hence, men are rewarded for their discourse patterns with better system performanceand this embedding disparity constitutes a representational harm and a masculine default.

  PublisherOA PDFDOI

Recent grants

• CAREER: Real-Time Crowd-Oriented Search and Computation Systems

  NSF · $613k · 2012–2018

• FAI: Towards Fairness in Deep Neural Networks with Learning Interpretation

  NSF · $509k · 2020–2025

• EAGER: Fairness-Aware Personalized Recommendations

  NSF · $170k · 2018–2020

• III: Small: Collaborative Research: Modeling and Managing Extremist Group Influence in Massive Social Media Networks

  NSF · $250k · 2019–2022

Frequent coauthors

• Ziwei Zhu

  39 shared

• Jianling Wang

  36 shared

• Kyumin Lee

  31 shared

• Krishna Kamath

  24 shared

• Zhiyuan Cheng

  University of Auckland

  24 shared

• Ling Liu

  20 shared

• Xiangjue Dong

  20 shared

• Calton Pu

  19 shared

Awards & honors

• National Science Foundation CAREER Award (2012)
• Air Force Office of Scientific Research (AFOSR) Young Invest…
• Montague-CTE (Center for Teaching Excellence) Scholar for ex…
• Defense Advanced Research Projects Agency Young Faculty Awar…
• Google Research Award (2009)