We're excited to share we added #NeevaAI:
✅ Answer support for verified health sites, official programming sites, blogs, etc.
✅ Availability in the News tab
🧵
First, at @Neeva we're passionate about generative search engines combining the best of search & AI.
But it's clear generative AI systems have no notion of sources or authority.
Their content is based on their reading of source material, which is often a copy of the entire Web.
On the other hand, search engines care about authority very intimately.
#PageRank (the algorithm that got @Google going) was committed to a better authority signal to score pages, based on the citations they got from other high scoring pages.
At @Neeva, we believe a great AI search engine should allow you to control the sources that go into your answers.
Here's an example of how we're doing it differently ⤵️
Just two weeks back, #NeevaAI went multi-perspective by adding support for @Neeva’s Bias Buster feature.
This provides multiple perspectives on any topic, transparently.
A deeper dive on our multi-perspective, authoritative, & personalizable AI ⬇️
As we continued to imagine the possibilities of multi-perspective AI, we are proud to add #NeevaAI support for verified health sites & authoritative programming websites.
Here's an example 🔎: [why water is important for maintaining good health]
You may be looking for a more authoritative answer from only verified sites.
In that case just:
1️⃣ Click on the verified facet
2️⃣ See an authoritative #NeevaAI answer from Neeva verified sites.
It's that simple! 👍
Here's another example, we typed in 🔎: [fp32 vs tf32]
1️⃣ Click on Official Docs
2️⃣ See an authoritative #NeevaAI answer!
In addition, users can now access a single #NeevaAI summary directly via the @Neeva News tab.
This includes citation cards, in which a search query returns a search result highlighting authoritative information about the researched topic. 🙌
Here's an example ⬇️
Without links embedded in AI answers, users won’t find their way to a publisher’s website, effecting their referral traffic.
These significant drops will lead to material impacts on ad revenue especially at a time when most publishers are fighting just to stay afloat.
At @Neeva, we are committed to building an equitable ecosystem where content creators and publishers are a part of the conversation.
We are working to help publishers integrate fluent AI search natively in their websites allowing users to discover & consume content seamlessly.
We are always looking for ways to put you in control of your own AI. Not the other way around.
We will continue to use this thinking as we upgrade #NeevaAI search.
Start using our authoritative answers by signing up for a free @Neeva account at neeva.com
• • •
Missing some Tweet in this thread? You can try to
force a refresh
Have you seen ChatGPT combine info on multiple entities into an answer that’s completely WRONG? 😬
Generative AI and LLM models can mix up names or concepts & confidently regurgitate frankenanswers.
Neeva is solving this problem on our AI-powered search engine.
Here’s how 🧵
FYI This is a two-part thread series.
Today, with the help of @rahilbathwal, we’ll explain why the problems happen technically.
Tomorrow, we’ll talk through how we’re implementing our solution with our AI/ML team.
Make sure you're following... 👀
In frankenanswers, a generative AI model combines information about multiple possible entities into an answer that’s wrong.
Ex) On this query for `imran ahmed’ from our early test builds, you see a mix up of many intents corresponding to different entities with the same name.👇
2/ First off, we found that there are far fewer resources available for optimizing encoder-decoder models (when compared to encoder models like BERT and decoder models like GPT).
We hope this thread will fill in the void and serve as a good resource. 📂
3/ We started with a flan-T5-large model and tuned it on our dataset. We picked the large variant because we found it to generate better summaries with fewer hallucinations and fluency issues.
The problem? The latency is too high for a search product.