3 citations · 3 across the 6 of their papers we have counts for
6 papers
Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval
Subhendu Khatuya, Shashwat Naidu, Pawan Goyal +1
Despite continuous advancements in the capabilities of large language models (LLMs), numerical reasoning remains a challenging area. Techniques like chain-of-thought prompting, tre…
Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classification
Subhendu Khatuya, Shashwat Naidu, Saptarshi Ghosh +2
The explosion of textual data has made manual document classification increasingly challenging. To address this, we introduce a robust, efficient domain-agnostic generative model f…
Parameter-Efficient Instruction Tuning of Large Language Models For Extreme Financial Numeral Labelling
Subhendu Khatuya, Rajdeep Mukherjee, Akash Ghosh +5
We study the problem of automatically annotating relevant numerals (GAAP metrics) occurring in the financial documents with their corresponding XBRL tags. Different from prior work…
Instruction-Guided Bullet Point Summarization of Long Financial Earnings Call Transcripts
Subhendu Khatuya, Koushiki Sinha, Niloy Ganguly +2
While automatic summarization techniques have made significant advancements, their primary focus has been on summarizing short news articles or documents that have clear structural…
How COVID-19 has Impacted the Anti-Vaccine Discourse: A Large-Scale Twitter Study Spanning Pre-COVID and Post-COVID Era
Soham Poddar, Rajdeep Mukherjee, Subhendu Khatuya +2
The debate around vaccines has been going on for decades, but the COVID-19 pandemic showed how crucial it is to understand and mitigate anti-vaccine sentiments. While the pandemic…
Financial Numeric Extreme Labelling: A Dataset and Benchmarking for XBRL Tagging
Soumya Sharma, Subhendu Khatuya, Manjunath Hegde +3
The U.S. Securities and Exchange Commission (SEC) mandates all public companies to file periodic financial statements that should contain numerals annotated with a particular label…