Papers by Md. Mahadi Hassan
The Path Not Taken: Duality in Reasoning about Program Execution (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks focus on predicting program properties tied to specific inputs, resulting in a narrow view of dynamic code reasoning and data contamination. |
| Approach: | They instantiate dual-path reasoning in a benchmark and evaluate 13 LLMs. |
| Outcome: | The proposed model provides a robust and discriminative proxy for dynamic code understanding. |
LLMs as Meta-Reviewers’ Assistants: A Case Study (2025.naacl-long)
Copied to clipboard
Eftekhar Hossain, Sanjeev Kumar Sinha, Naman Bansal, R. Alexander Knipper, Souvika Sarkar, John Salvador, Yash Mahajan, Sri Ram Pavan Kumar Guttikonda, Mousumi Akter, Md. Mahadi Hassan, Matthew Freestone, Matthew C. Williams Jr., Dongji Feng, Santu Karmaker
| Challenge: | Meta-reviews are a critical step in the overall scientific peer-reviewed process, which focuses on understanding the consensus of expert opinions on a scholarly work and making informed judgments on its scientific merit. |
| Approach: | They propose to use large language models to generate a controlled multi-perspective-summary (MPS) of their opinions to help meta-reviewers better comprehend multiple experts' perspectives. |
| Outcome: | The proposed model can help meta-reviewers better comprehend multiple experts’ perspectives by generating a controlled multi-perspective-summary (MPS) of their opinions. |
Large Language Models for IT Automation Tasks: Are We There Yet? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks rely on synthetic tasks that fail to capture the needs of practitioners who use IT automation tools. |
| Approach: | They evaluate 14 open-source and 3 proprietary LLMs and find that GPT-4.1-Mini achieves the best pass@10 rate of 23.9%, while Claude-3.5-Sonnet achieves best pass @1 performance. |
| Outcome: | The evaluated LLMs perform poorly in 126 tasks and show that they lack state reconciliation capabilities and lack module knowledge. |
Analogy-Guided Evolutionary Pretraining of Binary Word Embeddings (2022.aacl-main)
Copied to clipboard
| Challenge: | Existing binary word embeddings are derived from pretrained real-valued embeddables through different simple transformations, which often break the semantic consistency and the “arithmetic” properties of the embedded words. |
| Approach: | They propose a genetic algorithm to learn binary word embeddings from scratch by preserving the semantic relationships between words and the arithmetic properties of the embeddables themselves. |
| Outcome: | Evaluating 16, 32, and 64-bit word embeddings on Mikolov’s word analogy task shows that 95% of the time, the best fit is ranked in the top 5 most similar words in terms of cosine similarity. |