We extract contextualized representations of news text to predict returns using the state-of-the-art large language models in natural language processing. Unlike the traditional word-based methods, e.g., bag-of-words or word vectors, the contextualized representation captures both the syntax and semantics of text, thus providing a more comprehensive understanding of its meaning. Notably, word-based approaches are more susceptible to errors when negation words are present in news articles. Our study includes data from 16 international equity markets and news articles in 13 different languages, providing polyglot evidence of news-induced return predictability. We observe that information in newswires is incorporated into prices with an inefficient delay that aligns with the limits-to-arbitrage, yet can still be exploited in real-time trading strategies. Additionally, we find that a trading strategy that capitalizes on fresh news alerts results in even higher Sharpe ratios.

I introduce a methodology to generate economic expectations by applying large language models to historical news. Leveraging this methodology, I make three key contributions. (1) I show generated expectations closely match existing survey measures and capture many of the same deviations from full-information rational expectations. (2) I use my method to generate 120 years of economic expectations from which I construct a measure of economic sentiment capturing systematic errors in generated expectations. (3) I then employ this measure to investigate behavioral theories of bubbles. Using a sample of industry-level run-ups over the past 100 years, I find that an industry’s exposure to economic sentiment is associated with a higher probability of a crash and lower future returns. Additionally, I find a higher degree of feedback between returns and sentiment during run-ups that crash, consistent with return extrapolation as a key mechanism behind bubbles.

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.