Exploring Sonar Market Signals Through News Summarization and LLM Reasoning
During the spring of 2025, we initiated a project with NORBIT focused on using Large Language Models (LLMs) to identify key drivers in the sonar market, with an emphasis on news summarization.
Throughout the semester, we explored various methods for news collection, including web scraping and the GDELT API. We experimented with different LLMs, such as OpenAI’s GPT models and Perplexity’s sonar models. Techniques like chain-of-thought reasoning and few-shot prompting were also utilized to enable the LLMs to reason about the news articles and extract key drivers.
The project is currently in an experimental phase. The goal is to develop a complete pipeline that collects a large volume of news articles, intelligently filters for the most relevant ones, and sends them to an LLM that, through reasoning, summarizes the key drivers in the market.
-
NORBIT is a global provider of tailored technology solutions, structured across three core segments—Oceans, Connectivity, and Product Innovation & Realization (PIR). They support maritime markets with advanced sonar and sub-sea systems, offer smart wireless solutions for identification and tracking, and provide R&D, prototyping, and manufacturing services. Headquartered in Trondheim, Norway, with additional facilities in the US, Hungary, Selbu and Røros, NORBIT employs around 450–600 people globally and maintains a worldwide sales and distribution platform.