# From Transcripts to Insights: Uncovering Corporate Risks Using Generative AI

arXiv: https://arxiv.org/abs/2310.17721 · HTML: https://mlsanity.com/paper/2310.17721/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 42 references that are in the map.
- First posted on arXiv 26 Oct 2023.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models](https://mlsanity.com/paper/2304.07619/) (2023)
- [Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words](https://mlsanity.com/paper/2005.01810/) (2020)
- [An Exploratory Study on Long Dialogue Summarization: What Works and What's Next](https://mlsanity.com/paper/2109.04609/) (2021)
- [Bloated Disclosures: Can ChatGPT Help Investors Process Information?](https://mlsanity.com/paper/2306.10224/) (2023)
- [Predictive Patentomics: Forecasting Innovation Success and Valuation with ChatGPT](https://mlsanity.com/paper/2307.01202/) (2023)

## Built on by (most cited first, 3 of 3)

- [Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer](https://mlsanity.com/paper/2408.16978/) (2024)
- [A Scoping Review of ChatGPT Research in Accounting and Finance](https://mlsanity.com/paper/2412.05731/) (2024)
- [Bridging Language Models and Financial Analysis](https://mlsanity.com/paper/2503.22693/) (2025)

## Abstract (arXiv)

We explore the value of generative AI tools, such as ChatGPT, in helping investors uncover dimensions of corporate risk. We develop and validate firm-level measures of risk exposure to political, climate, and AI-related risks. Using the GPT 3.5 model to generate risk summaries and assessments from the context provided by earnings call transcripts, we show that GPT-based measures possess significant information content and outperform the existing risk measures in predicting (abnormal) firm-level volatility and firms' choices such as investment and innovation. Importantly, information in risk assessments dominates that in risk summaries, establishing the value of general AI knowledge. We also find that generative AI is effective at detecting emerging risks, such as AI risk, which has soared in recent quarters. Our measures perform well both within and outside the GPT's training window and are priced in equity markets. Taken together, an AI-based approach to risk measurement provides useful insights to users of corporate disclosures at a low cost.