Viewing profile — npip99

Bradley-Terry and Elo scores are equivalent mathematical models! The fundamental presumption is the same Thurstone model - that an individual's skill in a particular game is a norm…

Yeah absolutely. In your link, it iterates on _ = ^{_}, until it finds the fixed point. In our training pipeline, we had to convert the fixed point iteration to be on _ directly fo…

In our case training and inferencing the models takes days, calculating all of the ELOs take 1min haha. So we didn't need to optimize the calculation. But, we did need to work on n…

We tried a bradley-terry loss function, as calculated with https://hackmd.io/@-Gjw1zWMSH6lMPRlziQFEw/SJ8sRl1Zge We found that MSE after elo-adjustment worked equally well. And, MSE…

Yes our pairwise method is based entirely on 2AFC comparisons, for both intra-query and inter-query ELO calculations. It's definitely the best if not only way to get extremely high…

Yeah that's exactly what we observed. Our goal was to create an absolute score that's completely independent from the Corpus, which is difficult because naturally all ELO distribut…

I often see it rendered as "Elo" but I've always found it more natural to capitalize as "ELO", but perhaps I should swap to "Elo" given this. Pronouncing "ee-low" is certainly the …

Hey! We actually did a lot of research into ELO consistency, i.e. to check whether or not the NxN pairwise matrix followed the ELO model. It was a long road that's probably grounds…

Yes, a step where you do a structured extraction into a database column would be a potential solution. But, it requires a preprocessing step. It all depends on the use-case, someti…

The vast majority of AI systems in production rely on basic semantic search to provide context. A single retrieval call into a vector database powers most Retrieval-Augmented Gener…

Good question! For long documents we have a rolling window strategy. So, we cut the document into 5,000 token groupings for use in inference. There's also a 400 token overlap, and …

Yep benchmarks are available at https://github.com/ZeroEntropy-AI/llama-chunk?tab=readme-ov-... , we used this dataset https://github.com/ZeroEntropy-AI/legalbenchrag which is a re…

Hey HN! I've written a lot of RAG pipelines over the last year, and one consistent pain-point is writing regex to chunk the documents correctly. Right now, the most common chunking…

"Who wouldn’t prefer to stay home if they had the choice? I could spend my days traveling" It's not travelling... If you're staying at home...

That's because the $50M were owned by a large percentage of the users of Ethereum, not a single person. It represented 15% of the total ETH in circulation, back when the currency w…

Wait a second, am I missing out right now? I have an opportunity at Jane Street, but I haven't been exposed to any of the other small name firms. Where do I look to find the higher…