How Will the LLM Hallucination Problem Be Solved? | Manifold

How Will the LLM Hallucination Problem Be Solved?

Plus

21

Ṁ642

2029

4%

Other

9%

Vector Embeddings (as with Pinecone https://www.pinecone.io/)

1.2%

Filtering (as with Deepmind AlphaCode https://www.deepmind.com/blog/competitive-programming-with-alphacode)

0.1%

Ensemble Combined with Fine Tuning

0.6%

Joint Embedding Predictive Architecture (https://arxiv.org/pdf/2301.08243.pdf)

0.3%

Feed Forward Algorithms (https://www.cs.toronto.edu/~hinton/FFA13.pdf)

19%

Bigger model trained on more data + RL

1.6%

Vigger models + prompt engineering

43%

It won't be

22%

Giving all LLMs access to the internet and databases of scientific papers

By the year 2028, how will the Hallucination Problem have been solved for the vast majority of applications out there?

This question is managed and resolved by Manifold.

#️ AI Alignment

#— LLM & AI Capabilities—

Get

1,000

and

3.00

Sort by:

I'm guessing models will eventually be taught to express uncertainty in their answers. When asked "who is [person that does not exist]" many of them already correctly say they don't know who they are. I see no theoretical reason this capability couldn't be broadened

Related:

@LukeFrymire this would imply that either the options in my market are overvalued or your market is overvalued.

@PatrickDelaney I think the resolution criteria is fairly different. Mine requires that a scale-based solution is possible, yours requires it to be the primary method in production.

@LukeFrymire "larger models alone," doesn't even appear as an option on my market yet.

@VictorLevoso ught hit v instead of b in keyboard and didn't look at the question properly before clicking submit and now can't edit it or erase it.

@VictorLevoso you can sell and re-buy

How does this market resolve if it hasn't been?

@IsaacKing you could put that as an option

Related questions

Will LLM hallucinations be a fixed problem by the end of 2028?

+7% 1d57% chance

LLM Hallucination: Will an LLM score >90% on SimpleQA before 2026?

Will LLMs be banned at the 2026 MIT Mystery Hunt?

-3% 1d25% chance

Will LLM hallucinations be "largely eliminated" by 2025?

Will hallucinations (made up facts) created by LLMs go below 1% on specific corpora before 2025?

Will LLM hallucinations be a fixed problem by the end of 2025?

Will an LLM be able to solve a Rubik's Cube by 2025?

Will scaling current methods be enough to eliminate LLM hallucination?

Will an LLM be able to solve confusing but elementary geometric reasoning problems in 2024? (strict LLM version)

Will LLMs mostly overcome the Reversal Curse by the end of 2025?

Related questions

Will LLM hallucinations be a fixed problem by the end of 2028?

Will LLM hallucinations be a fixed problem by the end of 2025?

LLM Hallucination: Will an LLM score >90% on SimpleQA before 2026?

Will an LLM be able to solve a Rubik's Cube by 2025?

Will LLMs be banned at the 2026 MIT Mystery Hunt?

Will scaling current methods be enough to eliminate LLM hallucination?

Will LLM hallucinations be "largely eliminated" by 2025?

Will an LLM be able to solve confusing but elementary geometric reasoning problems in 2024? (strict LLM version)

Will hallucinations (made up facts) created by LLMs go below 1% on specific corpora before 2025?

Will LLMs mostly overcome the Reversal Curse by the end of 2025?

© Manifold Markets, Inc.•Terms + Mana-only Terms•Privacy•Rules