3 papers · 1 filter
Distilling Opinions at Scale: Incremental Opinion Summarization using XL-OPSUMM
Sri Raghava Muddu, Rupasai Rangaraju, Tejpalsingh Siledar +8
Opinion summarization in e-commerce encapsulates the collective views of numerous users about a product based on their reviews. Typically, a product on an e-commerce platform has t…
One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation
Tejpalsingh Siledar, Swaroop Nath, Sankara Sri Raghava Ravindra Muddu +8
Evaluation of opinion summaries using conventional reference-based metrics rarely provides a holistic evaluation and has been shown to have a relatively low correlation with human…
Leveraging Domain Knowledge for Efficient Reward Modelling in RLHF: A Case-Study in E-Commerce Opinion Summarization
Swaroop Nath, Tejpalsingh Siledar, Sankara Sri Raghava Ravindra Muddu +8
Reinforcement Learning from Human Feedback (RLHF) has become a dominating strategy in aligning Language Models (LMs) with human values/goals. The key to the strategy is learning a…