Papers by Md Tanzib Hosain
B-REASO: A Multi-Level Multi-Faceted Bengali Evaluation Suite for Foundation Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | B-REASO is the first inclusive assessment suite for advanced foundation model knowledge and reasoning skills in a Bengali language setup. |
| Approach: | We provide a Bengali assessment suite to assess advanced foundation model knowledge and reasoning skills in a language setup. |
| Outcome: | The B-REASO includes multiple-choice questions with four different degrees of difficulty . the questions cover 50 different fields, from science and engineering to the humanities . |
Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems? (2025.acl-srw)
Copied to clipboard
| Challenge: | Among the hardest tasks for humans are those found in competitive programming . language models (LMs) have not received enough attention as a domain to assess . |
| Approach: | They develop and evaluate a variety of LM inference techniques for competitive programming with these resources. |
| Outcome: | The proposed LM inference technique can solve 17 out of 18 problems that were previously unsolvable by any model or technique with just a few specific instructions. |