[FRIAM] Dissecting Recall of Factual Associations in, Auto-Regressive Language Models

[Russ Abbott]

Interesting that I downloaded this paper this morning also. Haven't yet
looked to see what I could understand about it. From the little I know
about it, this looks like it is related to the self-attention mechanism in
transformers.

-- Russ Abbott
Professor Emeritus, Computer Science
California State University, Los Angeles


On Sun, May 7, 2023 at 9:29 AM Steve Smith <sasmyth at swcp.com> wrote:

> https://arxiv.org/pdf/2304.14767.pdf
>
> I am pretty much over my head in this literature, but continue to be
> fascinated as I watch people who are not try to untangle some explanatory
> power in their models...
>
> The details of this analysis or framing this as *information flow* rather
> than *static data/structure* is reminiscent of some very nascent work we
> *tried* to do 15 years ago, attempting to analyze/understand huge Systems
> Dynamics models of Critical Infrastructure joined together/coupled to try
> to predict the potential for cascading failures through these coupled
> systems.   The representation *as* SD models were natural for this framing
> but we made only the tiniest progress IMO in extracting hints of
> *explanatory* narratives.    I was primarily doing visualization on those
> tasks but tried to focus on clustering of the Dual Graph/Network  to find
> structure in the *flow* during extreme events rather than in the
> engineered/designed structure of the network itself.
>
> I know there are others on this list who have worked with complex, dynamic
> networks  (I'm thinking of Frank's colleagues and Causal Discovery in
> Graphical Models,   various project Glen has alluded to, and a wide variety
> of problems Stephen has related to me over the years, but I'm sure there
> are plenty of others)...  I'm curious if anyone else is wading in this deep
> (and more to the point, finding any traction)?
>
> From the paper:
>
> -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
> FRIAM Applied Complexity Group listserv
> Fridays 9a-12p Friday St. Johns Cafe   /   Thursdays 9a-12p Zoom
> https://bit.ly/virtualfriam
> to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
> FRIAM-COMIC http://friam-comic.blogspot.com/
> archives:  5/2017 thru present
> https://redfish.com/pipermail/friam_redfish.com/
>   1/2003 thru 6/2021  http://friam.383.s1.nabble.com/
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20230507/3e6c4ac7/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Screen Shot 2023-05-07 at 10.13.09 AM.png
Type: image/png
Size: 66829 bytes
Desc: not available
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20230507/3e6c4ac7/attachment.png>