3 citations · 3 across the 3 of their papers we have counts for
3 papers
Fine-tuning Smaller Language Models for Question Answering over Financial Documents
Karmvir Singh Phogat, Sai Akhil Puranam, Sridhar Dasaratha +2
Recent research has shown that smaller language models can acquire substantial reasoning abilities when fine-tuned with reasoning exemplars crafted by a significantly larger teache…
Zero-Shot Question Answering over Financial Documents using Large Language Models
Karmvir Singh Phogat, Chetan Harsha, Sridhar Dasaratha +2
We introduce a large language model (LLM) based approach to answer complex questions requiring multi-hop numerical reasoning over financial reports. While LLMs have exhibited remar…
DeepPSL: End-to-end perception and reasoning
Sridhar Dasaratha, Sai Akhil Puranam, Karmvir Singh Phogat +2
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 logi…