@article{leveragingdomainknowledgeforefficient,
  title = {Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization},
  author = {Swaroop Nath and Tejpalsingh Siledar and Sankara Sri Raghava Ravindra Muddu and Rupasai Rangaraju and Harshad Khadilkar and Pushpak Bhattacharyya and Suman Banerjee and Amey Patil and Sudhanshu Shekhar Singh and Muthusamy Chelliah and Nikesh Garera},
  year = {2024},
  eprint = {2402.15473},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.15473v2},
}