← Back to Blogs
Skip to main content

Long context prompting for Claude 2.1

· One min read
Zain Hasan

Using prompt engineering to solve the 'lost in the middle' problem.

Anthropic was able to solve the "lost in the middle" problem "by adding the sentence “Here is the most relevant sentence in the context:” to the start of Claude’s response. This was enough to raise Claude 2.1’s score from 27% to 98% on the original evaluation."

Does it just take a little bit of prompt engineering to solve low accuracy when needing to retrieve from the middle of a context window??

🔗 Article Link

Ready to start building?

Check out the Quickstart tutorial, or build amazing apps with a free trial of Weaviate Cloud (WCD).

Don't want to miss another blog post?

Sign up for our bi-weekly newsletter to stay updated!


By submitting, I agree to the Terms of Service and Privacy Policy.