Welcome

Texas NLP Symposium is a one-day workshop featuring invited talks, oral presentations, and poster sessions. Our goal is to bring together NLP researchers across Texas to share and discuss ongoing or published research, as well as to foster future collaborations. Participants from outside Texas are also welcome.

Important Dates

Submission Deadline: February 20, 2026 [Submission Portal]
Acceptance Notification: March 6, 2026
Registration Deadline: March 22, 2026 [Registration Link]
Symposium Day: April 3, 2026

Call for Papers

We invite contributions from a wide range of domains that apply computational methods to explore various aspects of natural language processing, large language models, and related fields. Submissions reporting planned, ongoing, or completed research projects are welcome, including previously published results, current work, and negative findings. The symposium is non-archival and will not publish proceedings. All accepted submissions will be presented as either oral presentations or posters.

Submission Deadline: February 20 (11:59pm AoE), 2026 [Submission Portal]
Acceptance Notification: March 6, 2026

• Authors are required to submit a two-page short paper (including abstract, introduction, and main sections), with an unlimited-page appendix, in the ACL format. However, submissions of a longer length will also be considered.
• If the paper is published in a recent conference or journal, you can directly submit the paper without modification. Please indicate where the paper is published in Abstract when submitting the paper.
• The review process is single-blind, meaning that reviewers remain anonymous while authors’ identities are visible. Please display the author names when submitting.

Invited Speakers

Raymond Mooney
The University of Texas at Austin

Kai-Wei Chang
University of California, Los Angeles

Schedule

Venue

📍 EABB 106 & 113, Engineering Activities Building B (EABB), Texas A&M University

🅿️ Parking: University Center Garage (7-min walk to EABB), Daily Rate: $15

Accepted Work

Non-archival, randomly ordered. Poster size: A1 (59.4cm× 84.1cm)

Poster Session 1

1. CaseFacts: A Benchmark for Legal Fact-Checking and Precedent Retrieval
   Akshith Reddy Putta, Jacob Devasier, Chengkai Li
2. Spherical Steering: Geometry-Aware Activation Rotation for Language Models
   Zejia You, Chunyuan Deng, Hanjie Chen
3. Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers
   Kaiyu He, Mian Zhang, Peilin Wu, Xinya Du, Zhiyu Chen
4. Z-Scores: A Metric for Linguistically Assessing Disfluency Removal
   Maria Teleki, Sai Tejas Janjur, Haoran Liu, Oliver Grabner, Thomas Docog, Xiangjue Dong, Lingfeng Shi, Cong Wang, Stephanie Birkelbach, Jason Kim, Yin Zhang, James Caverlee
5. A Multi-Agent Framework for Faithful Evaluation of Medical Summaries
   Md Sohanur Rahman, Anudeep Bonagiri, Shreyansh Rath, Anthony Rios, Ke Yang
6. First Drop of Ink: Nonlinear Impact of Misleading Information in Long-Context Reasoning
   Muhan Gao, Zih-Ching Chen, Kuan-Hao Huang
7. Can Speech LLMs Think while Listening?
   Yi-Jen Shih, Desh Raj, Chunyang Wu, Wei Zhou, SK Bong, Yashesh Gaur, Jay Mahadeokar, Ozlem Kalinli, Mike Seltzer
8. Scaling Rich Style-Prompted Text-to-Speech Datasets
   Anuj Diwan, Zhisheng Zheng, David Harwath, Eunsol Choi
9. Are Safety Refusals Invariant to Linguistic Variation?
   Đorđe Klisura, Faruk Dziho, Philip Menard, Anthony Rios
10. OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
    Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen
11. A Modular Framework for LLM-Assisted Pattern Analysis
    Alankrit Jacinth Moses
12. AlgoSimBench: Identifying Algorithmically Similar Problems for Competitive Programming
    Jierui Li, Ray Mooney
13. A Causal Investigation of Latent Visual Reasoning
    Haotian Xia, Hanjie Chen
14. PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models
    Oscar Chew, Po-Yi Lu, Jayden Lin, Kuan-Hao Huang, Hsuan-Tien Lin
15. INSIGHT: A Domain-specialized Retrieval Augmented Generation for Integrating Global Human & Animal Health Technology
    Praneet Sai Madhu Surabhi, Dheeraj Mudireddy, Luis O. Tedeschi, Nicole Greer, Karun Kaniyamattam, Robert Strong, Ashley Wang, Jian Tao
16. Understanding Clinical Cognitive Dialogues Using Large Language Models
    Vishalakshi Arumugam,, Dan Schumacher, Veronica Rammouz, Enrique Gonzalez Guerrero, Jeremy Davis, Anthony Rios
17. Toward Canine Vocalization Processing and Understanding
    Theron S. Wang, Kenny Q. Zhu
18. Detecting and Mitigating Demographic Bias in LLM-Based Resume Evaluation
    Oluwadayo Bamgbelu, Maria Teleki, Xiangjue Dong, James Caverlee

Poster Session 2

19. GraphDancer: Training LLMs to Explore and Reason over Graphs via Curriculum Reinforcement Learning
    Yuyang Bai, Zhuofeng Li, Ping Nie, Jianwen Xie, Yu Zhang
20. Prompting Underestimates LLM Capability for Time Series Classification
    Dan Schumacher, Erfan Nourbakhsh, Rocky Slavin, Anthony Rios
21. *Less* Prune, *MoRE* Experts: Recognizing and Restructuring Latent Experts for Model Compression
    Jiamu Zhang, Alessandro Mason, Ning Xie, Aarav Swami, Ashley Chen, Shuai Xu, Vipin Chaudhary, Hanjie Chen
22. AnnoComm: A Large-Scale, LLM-Curated Corpus and Interactive Dashboard for Animal Linguistics and Bioacoustics
    Hridayesh Lekhak, Kenny Q. Zhu
23. Multilingual vs Multicultural: A Unified Multi-Paradigm Framework for Evaluating Culture Bias in Large Language Models
    Rusali Saha, Oscar Chew, Kuan-Hao Huang
24. Alignment Replay: Preserving Safety Alignment During Fine-tuning via Generative Replay
    Zhouxiang Fang, Jiawei Zhou, Hanjie Chen
25. Rapid Damage Estimation Using NLP: BERT-Based Damage Assessment from Geo-tagged Social Media Text
    Akash Pillai, Yalong Pi, Shoujia Li, Yuning Ye, Xinyue Ye, David Retchless, Richard Dally, Nick Duffield
26. PromptHelper: A Prompt Recommender System for Encouraging Creativity in AI Chatbot Interactions
    Jason Kim, Maria Teleki, James Caverlee
27. KG-Agnostic Question Answering via Agentic Navigation & ExampleBootstrapping
    Essam Wisam, Chengkai Li
28. Left Behind: Cross-Lingual Transfer as a Bridge for Low-Resource Languages in Large Language Models
    Abdul-Salem Beibitkhan
29. HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
    Peilin Wu, Mian Zhang, Kun Wan, Wentian Zhao, Kaiyu He, Xinya Du, Zhiyu Chen
30. A Mechanistic Interpretability Perspective for Targeted Multimodal Unlearning
    Kunal Jain, Kuan-Hao Huang
31. MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting
    Kangda Wei, Ruihong Huang
32. Designing Explainable Conversational Agentic Systems for Guaraní Speakers
    Samantha Adorno, Akshata Kishore Moharir, Ratna Kandala
33. Absolute Error Is Not Enough: Ranking Model Performance Without Labels
    Veronica Rammouz, Aaron O. Gonzalez, Carlos Cruzportillo, Adrian Tan, Nicole Lang Beebe, Ke Yang, Anthony Rios
34. Learning to Search: Improving Exploration Efficiency in LLM-Based Agents Through Adaptive Memory
    Bhaskar Ruthvik Bikkina, Kuan-Hao Huang
35. DRES: Benchmarking LLMs for Disfluency Removal
    Oliver Grabner, Maria Teleki, Sai Tejas Janjur, Haoran Liu, Ketan Verma, Thomas Docog, Xiangjue Dong, Lingfeng Shi, Cong Wang, Stephanie Birkelbach, Jason Kim, Yin Zhang, James Caverlee
36. Context matching is not reasoning when performing generalized clinical evaluation of generative language models
    Andrew Wen, Qiuhao Lu, Yu-Neng Chuang, Guanchu Wang, Jiayi Yuan, Jiamu Zhang, Liwei Wang, Sunyang Fu, Kurt D. Miller, Heling Jia, Steven D. Bedrick, William R. Hersh, Kirk E. Roberts, Xia Hu, Hongfang Liu

Poster Session 3

37. Harnessing Occupant Intention for Occupant-Centric Control with Large Language Models (LLMs) in Residential Buildings
    Zixuan Qi, Zhiyao Yang, Mingzhe Liu, Zheng O'Neill
38. Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation
    Albert Yu, Chengshu Li, Luca Macesanu, Arnav Balaji, Ruchira Ray, Ray Mooney, Roberto Martín-Martín
39. Improving Text-to-Chart Generation with Checklist-Based Multi-Agent Refinement
    James Ford, Kyrie Zhixuan Zhou, Anthony Rios
40. Preference Learning Unlocks LLMs’ Psycho-Counseling Skills
    Mian Zhang, Shaun M. Eack, Zhiyu Chen
41. The Interspeech 2026 Challenge on Transfer of Pragmatic Intent in Speech-to-Speech Translation
    Nigel G. Ward, Marcel de Korte, Javier Vazquez, Montserrat Molina, Vanessa Bolado, Carol Figueroa, Eliya Nachmani, John E. Ortega, Satoshi Nakamura
42. Eliciting Multimodal Large Language Model In-Context Learning by Instruction Induction
    Po-Yi Lu, Oscar Chew, Hsuan-Tien Lin, Kuan-Hao Huang
43. When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
    Lingxi Zhang, Guangtao Zheng, Hanjie Chen
44. Exposure- and Clustering-Aware Self-Play for LLM-based Recommendation
    ChuanHsin Wang, Xiangjue Dong, James Caverlee
45. Transforming Unstructured Accident Narratives into Structured Causal Models for Safety Management
    Hung Nguyen, Jaehoon Lee, Namgyun Kim, Kuan-Hao Huang
46. Detecting Incompleteness in Feature Requests: Leveraging Codebase-Augmented LLMs in Open-Source Software
    Erfan Nourbakhsh, Rocky Slavin
47. CHOIR: Harmonizing Structured Prompt Diversity for Robust LLM Reasoning
    Xiangjue Dong, Cong Wang, Maria Teleki, Millennium Bismay, Ruihong Huang, James Caverlee
48. SwissProt-Evidence & Pannot-FG: Fine-Grained Evidence-Grounded Protein Function Annotation with Homology Shift
    Yining Yang, Zhiyan Song, Yuhan Zheng, Dongkwan Kim, Yiming Gao, Yihong Yang, Ruihong Huang, Yang Shen
49. Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models
    Oscar Chew, Serhii Honcharenko, Kuan-Hao Huang
50. Hidden Markov Modeling of Reasoning Dynamics in Large Language Models
    Ruidi Chang, Hanjie Chen
51. SciImpact: A Multi-Dimensional, Multi-Field Benchmark for Scientific Impact Prediction
    Hangxiao Zhu, Yuyu Zhang, Ping Nie, Yu Zhang
52. Towards a structured understanding of dynamics of Full Fine-Tuning of Large Language Models
    Amin Ghasemi
53. BacktrackBench:Evaluating Future-Aware Planning and Consistency in Language Model Generation
    Rithik Kapoor, Md Messal Monem Miah, Ruihong Huang
54. From Scores to Support: Detecting and Enhancing Reflective Listening Learning with Large Language Models
    Dhruvil Thummar, Veronica Perez-Rosas

Organizers

Kuan-Hao Huang
Texas A&M Univeristy

Yu Zhang
Texas A&M Univeristy

Ruihong Huang
Texas A&M Univeristy

James Caverlee
Texas A&M Univeristy

Reviewers: Jiongran Wang, Kangda Wei, Yining Yang, Xinqi Su, Dishant Parag Zaveri, Md Messal Monem Miah, Rithik Kapoor, Hangxiao Zhu, Oscar Chew, Muhan Gao, Hsin-Ling Hsu, Hung Nguyen, Po-Yi Lu, Serhii Honcharenko, Neeraja Kirtane, Junggeun Do, Rusali Saha, Bhaskar Ruthvik Bikkina, Sicong Liang, Yuyang Bai, Kunal Jain

Sponsors

Contact

If you need accommodations or have questions or comments, please contact us at khhuang@tamu.edu.