zlacker
[parent]
[thread]
3 comments
1. attemp+(OP)
[view]
[source]
2025-06-03 06:35:10
We were talking about linear improvements and I have yet to see it
replies(1):
>>mounta+Xk1
◧
2. mounta+Xk1
[view]
[source]
2025-06-03 17:04:48
>>attemp+(OP)
check the benchmarks or make one of your own
replies(1):
>>attemp+xS1
◧◩
3. attemp+xS1
[view]
[source]
[discussion]
2025-06-03 20:20:04
>>mounta+Xk1
I checked the BlEU-Score and Perplexity of popular models and both have stagnated around 2021. As a disclaimer this was a cursory check and I didn't dive into the details of how individuals scores were evaluated.
replies(1):
>>mounta+Y24
◧◩◪
4. mounta+Y24
[view]
[source]
[discussion]
2025-06-04 16:37:03
>>attemp+xS1
on what benchmarks? pretty much every major one is linear improvement
[go to top]