Papers by Debrup Das
MATHSENSEI: A Tool-Augmented Large Language Model for Mathematical Reasoning (2024.naacl-long)
Copied to clipboard
| Challenge: | TALMs have been successfully employed in question-answering benchmarks, but their efficacy on complex mathematical reasoning benchmarks are open research questions. |
| Approach: | They propose a tool-augmented large language model for mathematical reasoning that enhances the skillset of large language models (LLMs) by 13.5%. |
| Outcome: | The proposed model achieves better accuracy and better knowledge retrieval performance than existing tools. |
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation (2025.naacl-long)
Copied to clipboard
| Challenge: | a scalable approach to classify text with sensitivity is costly because of exponential time complexity. |
| Approach: | They propose a framework for calculating word-level local and global sensitivities . they use a CHECKLIST-generated sentiment analysis dataset to test their approach . |
| Outcome: | The proposed framework can be used to calculate word-level local and global sensitivities . it improves attacks by 15.58%, while using sensitivity as an additional reward improves . |
RaDeR: Reasoning-aware Dense Retrieval Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | RaDeR retrievers outperform strong baselines in reasoning tasks . large language models (LLMs) have impressive reasoning capabilities on a wide range of tasks - however, they face challenges when reasoning is needed for relevance prediction. |
| Approach: | They propose a set of reasoning-based dense retrieval models trained with data derived from mathematical problem solving using large language models. |
| Outcome: | The proposed model outperforms baselines on the BRIGHT and RAR-b benchmarks and achieves comparable or superior performance while using only 2.5% of the training data used by the concurrent work ReasonIR. |