Papers by Md Nahid
NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in parsing textual data and generating code. |
| Approach: | They propose a framework that normalizes web tables to support symbolic reasoning . they compare NormTab to a stand-alone framework that can normalize tabular data . |
| Outcome: | The proposed framework outperforms traditional models on symbolic reasoning tasks on tabular data. |
TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models struggle with large tables due to their limited input length . a novel method that decomposes tables into smaller and relevant sub-tables reduces the computational load on LLMs . |
| Approach: | They propose a method that leverages text-to-SQL generation to decompose tables into smaller and relevant sub-tables . the method can reduce the input context length significantly, making it more scalable and efficient . |
| Outcome: | The proposed method performs remarkably well on the WikiTQ benchmark and on the TabFact benchmark. |