
Will an LLM be able to match the ground truth >85% of the time when performing PII detection by 2024 end?
25
1kṀ4723Dec 31
84%
chance
1H
6H
1D
1W
1M
ALL
PII - personal identification information
Stuff like people's names, numbers and codes that identify stuff (SSN, phone number, passport etc), places, locations, names of orgs, attributes that can be used to identify a person, etc.
GPT-4 outperforms Presidio, Microsoft's custom built tool for PII detection. GPT-4 matches ground truth ~77.4% of the times, while it misses a single PII element ~13% of the time.
This question is managed and resolved by Manifold.
Get
1,000 to start trading!
Sort by:
@PatrickDelaney I think microsoft tested against their in house system, which does detect PII on real data
People are also trading
Related questions
Will there be an LLM which scores above what a human can do in 2 hours on METR's eval suite before 2026?
70% chance
LLM Hallucination: Will an LLM score >90% on SimpleQA before 2026?
60% chance
Will LLMs be able to formally verify non-trivial programs by the end of 2025?
27% chance
Will one of the major LLMs be capable of continual lifelong learning (learning from inference runs) by EOY 2025?
20% chance
Will an LLM be able to solve Raven's Progressive Matrices from an image in 2025?
65% chance
Will an LLM improve its own ability along some important metric well beyond the best trained LLMs before 2026?
50% chance
What will be true of OpenAI's best LLM by EOY 2025?
Will LLMs become a ubiquitous part of everyday life by June 2026?
84% chance
Will there be any major breakthrough in LLM continual learning before 2028?
71% chance
❓ Which AI model will lead the LLM race by the end of 2025?