BlackRock researchers on reducing LLM hallucinations in extracting financial information

Researches from BlackRock in the US and India published a recent paper: “Towards reducing hallucination in extracting information from financial reports using Large Language Models”.

For a financial analyst, the question and answer (Q\&A) segment of the company financial report is a crucial piece of information for various analysis and investment decisions. However, extracting valuable insights from the Q\&A section has posed considerable challenges as the conventional methods such as detailed reading and note-taking lack scalability and are susceptible to human errors, and Optical Character Recognition (OCR) and similar techniques encounter difficulties in accurately processing unstructured transcript text, often missing subtle linguistic nuances that drive investor decisions.

Here, the researchers demonstrate the utilization of Large Language Models (LLMs) to efficiently and rapidly extract information from earnings report transcripts while ensuring high accuracy transforming the extraction process as well as reducing hallucination by combining retrieval-augmented generation technique as well as metadata. they evaluate the outcomes of various LLMs with and without using our proposed approach based on various objective metrics for evaluating Q\&A systems, and empirically demonstrate superiority of our method.

Read the full paper

Related Posts

Previous Post
Finadium: Hedge Fund Treasury Technology Vendors in 2023: A Finadium Survey
Next Post
Clearstreet trading division CenterPoint expands to Canada

Fill out this field
Fill out this field
Please enter a valid email address.


Reset password

Create an account