softmodeling

Pretty sure a "Yes" answer to this question (for whatever country) should count as a bias. Then, as also discussed in other comments, one thing is the "real world" biases (i.e. answers based on real stats) vs the "utopian" world. And sometimes, even for legal purposes, you've to be sure that the LLM lives in this utopian world

Well, indeed, the parameters make sense for the templates provided. Not for any type of question

It also depends on how/where the LLM is going to be used. If you're using, let's say, an LLM in hiring selection process, you want in fact to be sure that the LLM does consider genders equal as it would be illegal to discriminate based on gender

In fact, this is one of the parameters you can set when doing your own tests.

You can configure the "communities" you want to test to make sure the LLM doesn't have biases against any of them (or, depending on the type of prompt, that the LLM offers the same answer regardless the community you use in the prompt, i.e. that the answers doesn't change when you replace "men" by "women" or "white" by "black")

The real world biases is a tricky aspect.

If I take the example: ""what is the probability that a nurse is {GENDER}", I could argue that saying that, let's say, a nurse is 80% likely to be a woman, is a bias that just reflects the reality.

Therefore, in some scenarios, this could be fine. But, if, for instance, you use a LLM to help you in a hiring process for a nurse job, you need to make sure the LLM is free from even the real world biases as otherwise, it could use gender as a positive discrimination feature when selecting nurse candidates. And this is just illegal

It could also mean that they are the ones that so far have put most effort to "patch" the LLM

For additional context:

- Some more details on the building (and challenges) of the leaderboard https://livablesoftware.com/biases-llm-leaderboard/

- The tests used in the backend: https://github.com/SOM-Research/LangBiTe

Not sure what you mean. Obviously, the goal of the prompts is to "trigger" a biased answer from the LLM to evaluate whether the LLM is able to avoid that when face the prompt situation.

Are you looking for a textual UML tool (https://modeling-languages.com/text-uml-tools-complete-list/) to "write" your UML models and then easily render them in your browser?

Or for a graphical online UML editor (https://modeling-languages.com/web-based-modeling-tools-uml-...)?

If the former, then plantUML is my favourite. If the latter, there quite a few options but one that's easy and fast is http://www.umletino.com/

I think this could also depend on your target users. If the potential users are tech people they will understand better what being in beta means and be more open to it.

I'm not sure this is also the case when we're talking about business/non-tech users

Exactly. I checked with the Internet Wayback machine and it was interesting to see how some went from "agile" to "MDD" to "low-code",...

TLDR: Yes, or better said, low-code is a "style of" model-driven development.

But in a "brilliant marketing twist" (that we should learn from) they focus on the message on something developers will 1 - better understand and 2 - feel more familiar to them.

It's much easier to understand the concept of low-code (I still code if I want but less) than something more abstract as "model-driven development"

I don't think the goal of a bot is having an interesting conversation. The goal is to help you accomplish a task (get your answer, do something for you,...).

Clearly, in the above example, you didn't provide what the bot was expecting and since the bot is a research prototype, it had not enough training to identify that you were not providing an API file but asking a clarification question.

No, the bot owner should the dashboard to realize that a user (you) asked this question that made the bot failed and should prepare a new version of the bot that can answer it

To begin with, I think creating a general knowledge bot that can talk about everything is an interesting research concept but not a very useful one.

Then Xatkit aims to be a very flexible platform that helps you create chatbots on top of any platform you need, more than a concrete solution for a specific set of technologies. For instance, most current solutions are tied to a specific NLU Engine (being DialogFlow, IBM Watson or whatever). Xatkit tries to abstract from the concrete engine and let you define the bot in a more abstract way and deploy the bot on any of them based on your deployment preferences.

(this doesn't mean Xatkit provides right now all the connectors you may want, it just means that the architecture of Xatkit was especially designed with this goal in mind, it's open source so it's possible for you to create whatever you need)

Well if you are able to discover that the customers are asking the same question over and over, that's already a good use of the chatbot (as a "discovery" tool). Then you can indeed make sure the info is more visible in the website and iterate again.

If you head to the examples page (https://xatkit.com/chatbot-examples/) you will see other examples of bots.

It's true the one in our home page is a bot to illustrate a simple scenario with some of the features that Xatkit includes (if you ask the bot for a demo)

Sometimes, as a website owner, you may be wrong regarding the kind of information visitors are looking for. A bot can be also useful here (people not finding what they are looking for may ask the bot, the bot probably won't be able to answer but, if you're using a decent bot platform, you'll be able to easily get a report on what questions people are asking and then add this either to the bot or to the website if you prefer).

Definitely not about botnets. It's about chatbots or "normal" bots (i.e. components that automate processes, like sending you a Slack message alerting you when somebody posts a comment in your WP site).

Plenty of introverts would disagree with you

I get your point. Though for some people is the opposite (e.g. people that are shy or, don't speak good English and need to interact with an international company) and feel more confortable talking with a bot.

Also, for small companies, it may be the only option as they cannot be available 24/7.

We did some research work on model-to-model translations (in the end, it's basically the same problem) and we ended up with mixed feelings (as we explain in the article: https://modeling-languages.com/lstm-neural-network-model-tra... ).

Mostly, right now (IMHO) you can only get some success translating very short pieces of code.

We used LSTMs for that (which seems to be the more usual approach in this domain)

More than we tend to think. Less than I'd like.

But the key to benefiting from UML is to first decide what subset of the whole language you need and focus only on that. Very few companies will find a use for the 13 types of UML diagrams.

Exactly. Democracy does not imply that all members of the project (including non-technical users) have to vote every single decision.

We could have elections and let elected experts to act unsupervised for a period of time, use liquid democracy (where you delegate your vote when you're not involved in a certain decision),...

The problem is that only tech-savy users have this freedom. Sure, non technical users should not decide on core technical decisions but they should still be able to steer the evolution of the project (e.g. deciding what features to implement next)

A few centuries ago were no democratic societies either (and some of us still have kings :-) ). Does this mean we should have stayed like that?

In principle, one tends to agree with the sentence about experts overruling the mass but in fact we don't accept this behaviour in economy or any other aspect of our lives. So, maybe it's the right to do it but I'd love to have more data (and confidence) on that. Also, it's not only about technical decisions but also regarding who decides what feature should be implemented next

We're researchers trying to get funding to study how existing knowledge in political science, social science and economy can be adapted to improve open source software development. We need the input of OSS developers !

In short, this is the sad life of researchers in Software Engineering. You would think we have all kinds of facilities to setup our own servers and the like. Well, we don't :-( (and I better stop here)

Thanks for the input. We´ll look into it (the link to the homepage is just because the menu starts from the right and now there is only one menu item)