2
$\begingroup$

I'm interested in the topic of Explainability for LLM: the attempts to find some higher understandable structures inside the LLMs or, to put it simply (though may be not completely correctly), the attempts to understand how LLMs "think".

Would anybody please recommend where to start?

I'm both interested in foundational papers at this topic and in important latest research.

The great survey or a curated list of papers would be wonderful, although I'm not sure they exist give the speed the field is moving with.

Improve this question
$\endgroup$
1
  • $\begingroup$ Is there a specific reason why you asked Large Language Models specifically? Are you interested only in the Sequence Generation task or also in classification and other tasks? $\endgroup$
    – Ciodar
    Commented May 23, 2023 at 8:40

1 Answer 1

Reset to default
1
$\begingroup$

As you have already mentioned, it's a rapidly evolving research area. These can be the first steps in hunting for foundations.

  1. https://arxiv.org/abs/2303.06223

  2. https://www.sciencedirect.com/science/article/pii/S0950705123000230

Improve this answer
$\endgroup$
1
  • $\begingroup$ Could you please provide at least the title for each article (not just the link)? $\endgroup$
    – nbro
    Commented Nov 27 at 10:22

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .