Ehsan Doostmohammadi
Publications
2026
Toward Understanding and Enhancing the Training and Evaluation of Language Models: A Study on Vision, Instruction Tuning, and Retrieval Augmentation
(Doctoral thesis, comprehensive summary)
https://dx.doi.org/10.3384/9789181184440
2025
Studying the Role of Input-Neighbor Overlap in Retrieval-Augmented Language Models Training Efficiency
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, p. 26847-26856
(Conference paper)
https://dx.doi.org/10.18653/v1/2025.emnlp-main.1363
2024
How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?
Findings of the Association for Computational Linguistics: EMNLP 2024, p. 6321-6336
(Conference paper)
https://dx.doi.org/10.18653/v1/2024.findings-emnlp.367
2023
On the Generalization Ability of Retrieval-Enhanced Transformers
Findings of the Association for Computational Linguistics: EACL 2023, p. 1485-1493
(Conference paper)
https://dx.doi.org/10.18653/v1/2023.findings-eacl.109
Making Instruction Finetuning Accessible to Non-English Languages: A Case Study on Swedish Models
Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), p. 634-642
(Conference paper)
