Natural language question answering

Abstract

Techniques for finetuning a large language model (LLM) are described. The finetuned LLM is generated by sequentially tuning a trained LLM using: (i) pairs of questions and corresponding context received from at least one source different from the trained LLM; and (ii) the questions without the context. The finetuned LLM may be used to generate an answer to a question, and user feedback and context may be used to update a trained machine learning (ML) configured to determine context for input to the finetuned LLM at inference. The updated trained ML model may thereafter process a question to determine context usable to answer the question; the question and the context may be processed by the finetuned LLM to determine an answer to the question; and the question, context, and answer may be used to further finetune the LLM.