no code implementations • 29 Feb 2024 • Joykirat Singh, Sehban Fazili, Rohan Jain, Md Shad Akhtar
In this paper, we propose to enhance the interpretability and readability of policy documents by using controlled abstractive summarization -- we enforce the generated summaries to include critical privacy-related entities (e. g., data and medium) and organization's rationale (e. g., target and reason) in collecting those entities.
1 code implementation • 28 Feb 2024 • Subhabrata Dutta, Joykirat Singh, Soumen Chakrabarti, Tanmoy Chakraborty
Despite superior reasoning prowess demonstrated by Large Language Models (LLMs) with Chain-of-Thought (CoT) prompting, a lack of understanding prevails around the internal mechanisms of the models that facilitate CoT generation.
1 code implementation • 9 Dec 2023 • Subhabrata Dutta, Joykirat Singh, Ishan Pandey, Sunny Manchanda, Soumen Chakrabarti, Tanmoy Chakraborty
In this paper, we start with the hypothesis that much smaller LMs, which are weak at multi-step reasoning, can achieve reasonable arithmetic reasoning if arithmetic word problems are posed as a formalize-then-solve task.
Ranked #11 on Math Word Problem Solving on SVAMP (using extra training data)