Show HN: Steerling-8B, a language model that can explain any token it generates

Is there a reason people don't use SHAP [1] to interpret language models more often? The in-context attribution of outputs seems very similar.

[1] https://shap.readthedocs.io/en/latest/

Maybe I’m not creative enough to see the potential, but what value does this bring ?

Given the example I saw about CRISPR, what does this model give over a different, non explaining model in the output ? Does it really make me more confident in the output if I know the data came from Arxiv or Wikipedia ?

I find the LLM outputs are subtlety wrong not obviously wrong

This is very interesting. I don't see much discussion of interpretability in day to the day discourse of AI builders. I wonder if everyone assumes it to either be solved, or to be too out of reach to bother stopping and thinking about.

Now this is something which is very interesting to see and might be the answer to the explainability issue with LLMs, which can unlock a lot more use-cases that are off limits.

We'll see.