ConText-LE: Cross-Distribution Generalization for Longitudinal Experiential Data via Narrative-Based LLM Representations

Ahatsham Hayat, Bilal Khan, Mohammad Rashedul Hasan


Abstract
Longitudinal experiential data offers rich insights into dynamic human states, yet building models that generalize across diverse contexts remains challenging. We propose ConText-LE, a framework that systematically investigates text representation strategies and output formulations to maximize large language model cross-distribution generalization for behavioral forecasting. Our novel Meta-Narrative representation synthesizes complex temporal patterns into semantically rich narratives, while Prospective Narrative Generation reframes prediction as a generative task aligned with LLMs’ contextual understanding capabilities. Through comprehensive experiments on three diverse longitudinal datasets addressing the underexplored challenge of cross-distribution generalization in mental health and educational forecasting, we show that combining Meta-Narrative input with Prospective Narrative Generation significantly outperforms existing approaches. Our method achieves up to 12.28% improvement in out-of-distribution accuracy and up to 11.99% improvement in F1 scores over binary classification methods. Bidirectional evaluation and architectural ablation studies confirm the robustness of our approach, establishing ConText-LE as an effective framework for reliable behavioral forecasting across temporal and contextual shifts.
Anthology ID:
2025.findings-emnlp.830
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15335–15360
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.830/
DOI:
Bibkey:
Cite (ACL):
Ahatsham Hayat, Bilal Khan, and Mohammad Rashedul Hasan. 2025. ConText-LE: Cross-Distribution Generalization for Longitudinal Experiential Data via Narrative-Based LLM Representations. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 15335–15360, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
ConText-LE: Cross-Distribution Generalization for Longitudinal Experiential Data via Narrative-Based LLM Representations (Hayat et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.830.pdf
Checklist:
 2025.findings-emnlp.830.checklist.pdf