2 papers
cs.CL2023
FusionMind -- Improving question and answering with external context fusion
Shreyas Verma, Manoj Parmar, Palash Choudhary +1
Answering questions using pre-trained language models (LMs) and knowledge graphs (KGs) presents challenges in identifying relevant knowledge and performing joint reasoning.We compa…
cs.CL2023
Efficacy of Machine-Generated Instructions
Samaksh Gulati, Anshit Verma, Manoj Parmar +1
Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, th…