no code implementations • 13 May 2024 • Priyanshu Gupta, Shashank Kirtania, Ananya Singha, Sumit Gulwani, Arjun Radhakrishna, Sherry Shi, Gustavo Soares
Our results demonstrate a notable improvement, with METARELECTION outperforming GPT-4 by 16. 82% (IAC), 31. 33% (COT), and 15. 42% (REACT), underscoring the potential of METAREFLECTION as a viable method for enhancing the efficiency of LLMs.
no code implementations • 2 Jun 2023 • Tejasvee Bisen, Mohammed Javed, Shashank Kirtania, P. Nagabhushan
For any digital application with document images such as retrieval, the classification of document images becomes an essential stage.