When to Retrieve?
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
presents an approach to train LLMs to effectively utilize information retrieval; it first proposes a training approach to teach an LLM to generate a special token, <RET>, when it's not confident or doesn't know the answer to a question; the fine-tuned model outperforms a base LLM in two fixed alternate settings that include never retrieving and always retrieving context
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack