I am a final-year PhD Student in Computer Science at Texas A&M University, advised by Prof. James Caverlee.
My research focuses on AI Agents, LLM Reasoning and Personalization, Trustworthy AI, and Conversational AI. I aim to build personalized language agents that are trustworthy, collaborative, and aligned with human needs — agents capable of reasoning reliably, working collectively with other agents, and adapting to individual users and contexts.
If you would like to chat about life, career, or research ideas related to Agents/LLM/NLP, feel free to reach out.
Marathon (Personal best: 3:43:15). Bouldering (previous TAMU climbing team). Piano (Grade 10 Certificate, highest honor for amateur pianists). Strava
* equal contribution; † mentored student. See also Google Scholar.
CHOIR: Collaborative Harmonization fOr Inference Robustness.
Under review at ACL 2026; presented at NeurIPS 2025 Workshop.
DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management.
Under review at ACL 2026.
DisastQA: A Comprehensive Benchmark for Question Answering Evaluation in Disaster Management.
Under review at ACL 2026.
Probing the Limits of Embodied Spatial Planning in LLMs.
NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI.
A Survey on LLM Inference-Time Improvement.
Preprint.
Probing, Measuring, and Mitigating Gender Affiliations in Large Language Models.
Preprint.
Multi-Scale Model Compression via Nested Matrix Learning.
The Fifteenth biennial Language Resources and Evaluation Conference (LREC 2026). Oral.
Language Models as Semantic Augmenters for Sequential Recommenders.
The Fifteenth biennial Language Resources and Evaluation Conference (LREC 2026).
Z-Scores: A Metric for Linguistically Assessing Disfluency Removal.
2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026).
DisastIR: A Comprehensive Information Retrieval Benchmark for Disaster Management.
Findings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025 Findings).
A Survey on LLMs for Story Generation.
Findings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025 Findings).
ReasoningRec: Bridging Personalized Recommendations and Human-Interpretable Explanations through LLM Reasoning.
Findings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL 2025 Findings).
Masculine Defaults via Gendered Discourse in Podcasts and Large Language Models.
International AAAI Conference on Web and Social Media (ICWSM 2025).
Also presented at IC2S2 2025 (nominated for a methodology award) and SICon@ACL 2025.
DA3: A Distribution-Aware Adversarial Attack against Language Models.
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024). Oral.
The Neglected Tails in Vision-Language Models.
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024).
Also accepted at DMLR@ICML 2024 (Oral).
Comparing ASR Models in the Context of Speech Disfluencies.
Interspeech 2024.
Quantifying the Impact of Disfluency on Spoken Content Summarization.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024).
Disfluency Augmented Curriculum Learning for Fluent Text Generation.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024).
Everything Perturbed All at Once: Enabling Differentiable Graph Attacks.
The Web Conference 2024 (WWW 2024). Short.
Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning.
Findings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 Findings).
PromptAttack: Probing Dialogue State Trackers with Adversarial Prompts.
Findings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023 Findings).
Also accepted at TrustNLP Workshop@ACL 2023 and presented at CRA-W 2023.
Closed-book Question Generation via Contrastive Learning.
The 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023). Oral.
Weakly Supervised Concept Map Generation through Task-Guided Graph Translation.
IEEE Transactions on Knowledge and Data Engineering (TKDE 2023).
Howdy Y'all: An Alexa TaskBot.
1st Proceedings of Alexa Prize TaskBot, 2022.
Quarterfinals.
Emora: An Inquisitive Social Chatbot Who Cares For You.
3rd Proceedings of Alexa Prize, 2020.
1st Place Winner.
Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation.
Socially Responsible Language Modelling Research Workshop (SoLaR@NeurIPS 2023).
Transformer-based Context-aware Sarcasm Detection in Conversation Threads from Social Media.
ACL Workshop on Figurative Language Processing (FigLang@ACL 2020).
2nd Place Winner.