2026 ~ 2030

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction. Wu, S.; Liu, L.; Choi, J. D.; and Shu, K. Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL): Findings, 2026.

TRUST: An LLM-Based Dialogue System for Trauma Understanding and Structured Assessments. Tu, S.; Powers, A.; Doogan, S.; and Choi, J. D. Journal of the American Medical Informatics Association (JAMIA), 2026.

Why Are We Lonely? Leveraging LLMs to Measure and Understand Loneliness in Caregivers and Non-caregivers. Kim, M. D.; Paek, E. S.; Lin, Y.; Mroz, E.; Chung, J. and Choi, J. D. EACL Workshop on Linguistic Analysis for Health (HeaLing), 2026.

DyCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs. Choi, N.; Zhang, J.; and Choi, J. D. Transactions of the Association for Computational Linguistics (TACL), 2026.

CRADLE Bench: A Clinician-Annotated Benchmark for Multi-Faceted Mental Health Crisis and Safety Risk Detection. Byun, G.; Lipschutz, R.; Minton, S. T.; Powers, A.; and Choi, J. D. Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026.

Generative Induction of Dialogue Task Schemas with Streaming Refinement and Simulated Interactions. Finch, J. D.; Josyula, Y.; and Choi, J. D. Transactions of the Association for Computational Linguistics (TACL), 2026.