Among the various papers you referred to, the one on the forecasting capacity of LLMs caught my attention. Not only for the research itself; but also because it is potentially linked to various papers that concern how AI positively (or negatively) influences decision making in risk, investment or "high-stakes" scenario situations. A paper that I found very useful and interesting in this sense is: https://journals.sagepub.com/doi/abs/10.1177/17456916231181102
Hi Riccardo. The paper that you linked in your comment is great.
It is quite interesting how LLMs can be created for specific tasks like investing, and still fall victim to biases and influences from its training data.
In my very first post, I featured a paper titled “What Does ChatGPT Make of Historical Stock Returns? Extrapolation and Miscalibration in LLM Stock Return Forecasts.” Ultimately, this paper found that ChatGPT falls victim to recency biases when forecasting stock prices.
Among the various papers you referred to, the one on the forecasting capacity of LLMs caught my attention. Not only for the research itself; but also because it is potentially linked to various papers that concern how AI positively (or negatively) influences decision making in risk, investment or "high-stakes" scenario situations. A paper that I found very useful and interesting in this sense is: https://journals.sagepub.com/doi/abs/10.1177/17456916231181102
Hi Riccardo. The paper that you linked in your comment is great.
It is quite interesting how LLMs can be created for specific tasks like investing, and still fall victim to biases and influences from its training data.
In my very first post, I featured a paper titled “What Does ChatGPT Make of Historical Stock Returns? Extrapolation and Miscalibration in LLM Stock Return Forecasts.” Ultimately, this paper found that ChatGPT falls victim to recency biases when forecasting stock prices.
Link to first post: https://open.substack.com/pub/alphainacademia/p/recent-academic-research?r=1v99qs&utm_campaign=post&utm_medium=web