Online reviews play an inescapable role in influencing consumers' purchase decision-making process. However, the ever-increasing volume of online reviews causes information overload challenges for consumers, resulting in finding relevant reviews harder and eventually overwhelming them. The extant body of research reports that helpful reviews influence consumers' purchase intention more. Prior research also tends to investigate how the textual content of online reviews and the interplay between the textual content and review source characteristics affect review helpfulness (Aghakhani et al., 2022). Recent developments in large language models (LLM), such as ChatGPT, make it feasible to summarize many reviews and present a summary to consumers. Some websites are starting to offer this feature. Generally, LLMs offer numerous ways of summarizing reviews, focusing on specific features like value, food, or service, in addition to sentiment analysis and trends over time (Aghakhani et al., 2022). However, little is known about these summarized reviews' effectiveness and impact on consumer decision-making. This research builds upon the theoretical lenses of information foraging and satisfaction theory, suggesting that consumers follow information scent, navigating through various reviews to maximize their information gain and minimize their cognitive effort. In addition, consumers tend to make decisions that are good enough rather than optimal, meaning that they are not relying on one specific useful review or thoroughly searching for all the reviews. Instead, opt for a selective review that is good enough to make satisfactory decisions. We are in the process of collecting data from the popular restaurant review website Yelp. For this study, we focus on two cities: one large major metro with a population of nearly 2 million and another significantly smaller city with about 500,000. We summarize these reviews using ChatGPT and aim to synthesize the vast consumer reviews into digestible summaries highlighting the overall theme, sentiment trends, and consumer satisfaction. Acknowledging the importance of a collective number of reviews in influencing the consumer decision-making process, our study intends to contribute to the prior literature by leveraging recent advances in LLMs for effective textual and context summarization. In this study, we explore various text summarization techniques based on literature related to consumers' behavior and their search process that could be integrated with online consumer review platforms. The paper discusses theoretical and practical implications and future directions.