Sai Akhil Puranam — accepted AI-conference papers

2024

Fine-tuning Smaller Language Models for Question Answering over Financial Documents

Karmvir Singh Phogat, Sai Akhil Puranam, Sridhar Dasaratha, Chetan Harsha, Shashishekar Ramakrishna

EMNLP 2024finding

Recent research has shown that smaller language models can acquire substantial reasoning abilities when fine-tuned with reasoning exemplars crafted by a significantly larger teacher model. We explore this paradigm for the financial domain, focusing on the challenge of answering questions that requir…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

DeepPSL: End-to-End Perception and Reasoning

Sridhar Dasaratha, Sai Akhil Puranam, Karmvir Singh Phogat, Sunil Reddy Tiyyagura, Nigel P. Duffy

IJCAI 2023poster

We introduce DeepPSL a variant of probabilistic soft logic (PSL) to produce an end-to-end trainable system that integrates reasoning and perception. PSL represents first-order logic in terms of a convex graphical model – hinge-loss Markov random fields (HL-MRFs). PSL stands out among probabilistic l…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗