Re: AI KR Strategist, explainabiilty, state of the art

From my perspective, this exchange might be more productive if it focused directly on the elements of the plan, if any, that we aim to craft and pursue together.
At this point, I am unable to decipher those elements from this exchange of E-mail messages.  It reminds me of an assertion relating to the Capability Maturity Model (CMM):  

E-mail is a stage of immaturity through which we must pass.

Plans previously considered by the AIKR CG are available in StratML format at https://stratml.us/drybridge/index.htm#AIKRCG
Perhaps we might at least revisit and perhaps update this one:  https://stratml.us/docs/AIKRCG.xml  
It would be nice to report any progress that may have been made on any of the objectives it sets forth for us.  
It is available for comments at https://stratml.us/carmel/iso/part2/AIKRCGforComment.xml and for editing in StratML Part 2, Performance Plan/Report, format at https://stratml.us/drybridge/index.htm#AIKRCG 
Owen Amburhttps://www.linkedin.com/in/owenambur/
 

    On Saturday, November 9, 2024 at 07:34:28 AM EST, carl mattocks <carlmattocks@gmail.com> wrote:   

 Paola
To be explicit ... I am not proposing to focus exclusively on 
Explainable Artificial Intelligence
 (a suite of machine learning techniques that: Produce more explainable models )I do expect to have discussions about models used in the explanations about KR used in AI.
cheers
Carl

It was a pleasure toclarify


On Sat, Nov 9, 2024 at 2:10 AM Paola Di Maio <paoladimaio10@gmail.com> wrote:

Carl,following my earlier email response, let me make explicit (...) 
a fundamental point that perhaps came across as implied (...)

misrepresentation  miscategorization  correctnesstransparency, accountability,reliability verifiabilityand all sorts of AI flaws and errors  = AI challenges  can be addressed at least in part with KR
and mitigated through explainabilityhowever
and that the  field of XAI, based on a review of the state of the art,has become paradoxically inextricable  and unexplainable in its own right
Proposed approaches must tackle directly the challenges, and possibly be supported with some evidence/proof of their effectiveness(usefulness notwithstanding)

P

s, or making AI more transparent, more reliable, more accountable that 

On Sat, Nov 9, 2024 at 12:42 AM carl mattocks <carlmattocks@gmail.com> wrote:

Paola
Please note in the email chain there are statements about 'explainability' which continues to be an issue . .. thus the focus of the proposed effort. 
Carl
On Fri, Nov 8, 2024, 5:41 PM Paola Di Maio <paola.dimaio@gmail.com> wrote:

Carl, good to hear from you and thanksfor picking up where you left .

Btw the attachment you sent never made it into W3C Group reports, maybe at some point you d like to publish them with some notes explaining how these addressed the challenges discussed? The documents you send do not seem to explain how the proposed work fits in the AI KR mission (which problem they solve).
As previously discussed StratML can be a useful mechanism represent knowledge, at syntactic level. A markup language by itself it does not address nor resolve the key challenges faced by AI today that KR (thinking semantics here) as a whole could tackle. (irrespective of any implementation language of choice).

In the work you propose, there is strong coupling between AI KR and StratML as a syntax
(your construct binds the two) This approach may be suitable in a Stratml CG (is the one by the way)? rather than an AI KR CG  The focus is AI KR, rather than a modeling language by itself
If the line you are interested to explore is StratML only, it could be useful if you (or other proponents of this line of work) could  summarise   how it address the broader AI KR challenges.
For example, say, knowledge misrepresentation - or miscategorization - or wrong recommendations, or making AI more transparent, more reliable, more accountable etc.
Perhaps  show how these can be addressed  with use cases or other proof of concept.
So basically, I encourage discussions to be focused on AI KR  and whatever line of work members propose, please make it clear which problem each construct intends to resolve in relation to the overall mission.

Thank  you! 

Paola Di Maio, PhD


On Thu, Nov 7, 2024 at 6:09 PM carl mattocks <carlmattocks@gmail.com> wrote:

Greetings All - It has been a while.
Given the interest in AI , I am proposing that we set up a series of online meetings to expand on the AI Strategist work that focused on leveraging StratML. (see attached).
The topics include:   
   - AI Observability Mechanisms (monitor behavior, data, and performance)
   - KR Models used in the explanations (to a given audience, and what concepts are needed for this)
   - KR ID needed for Knowledge Content (UID, URI) Logistics management
   - Roles of Humans in the Loop (as a creator, and an audience type)
   - Agents having Authority awarded by a Human in the Loop
   - Catalogs of AI capabilities ( see Data Catalog (DCAT) Vocabulary )
   - AIKR Using / Used in DPROD (specification provides unambiguous and sharable semantics) https://ekgf.github.io/dprod/

Timeslots for meetings  will be determined by participants.  Please let me know if you are interested.
Thanks 
Carl Mattocks
CarlMattocks@WellnessIntelligence.InstituteIt was a pleasure toclarify


On Tue, Jun 11, 2024 at 5:24 AM Dave Raggett <dsr@w3.org> wrote:

First my thanks to Paola for this CG. I’m hoping we can attract more people with direct experience. Getting the CG noticed more widely is quite a challenge! Any suggestions?


It has been proposed that without knowledge representation. there cannot be AI explainability 

That sounds somewhat circular as it presumes a shared understanding of what “AI explainability” is.  Humans can explain themselves in ways that are satisfactory to other humans.  We’re now seeing a similar effort to enable LLMs to explain themselves, despite having inscrutable internal representations as is also true for the human brain.
I would therefore suggest that for explainability, knowledge representation is more about the models used in the explanations rather than in the internals of an AI system. Given that, we can discuss what kinds of explanations are effective to a given audience, and what concepts are needed for this.
Explanations further relate to how to making an effective argument that convinces people to change their minds.  This also relates to the history of work on rhetoric, as well as to advertising and marketing!
Best regards,
Dave Raggett <dsr@w3.org>