Conversation as path traversal

[-]Jon Garcia4y30

As a slight tangent, I'm interested in your thoughts on the nature of the "conversation space" being traversed. You seemed to imply that conversations can have goals, i.e. destinations that participants in the conversation can try to steer it towards. For this, I'm imagining that the interlocutors have certain mental maps (e.g., a "who", "what", "when", "where", "why", and "how", along with their relations) that they either want filled in for themselves or that they're trying to fill in for the other person.

The conversation would then involve looking for holes in each other's mental maps (regions of high uncertainty) and cooperating to fill them in. Interruptions would then entail one participant trying to shift the other person's attention to a (slightly?) different mental map that's of greater interest to them (kind of like what I'm doing with this comment?).

As a further aside, I think this is one area where large language models like GPT-3 fall short of how humans actually use language. They can simulate conversations, but they can't really participate in genuine conversation-space traversals in the sense of deliberately looking for gaps in understanding and for ways to fill those gaps.

By the way, how would your model handle other types of conversation that have purposes other than conveying or seeking information, such as witty banter, small talk, or giving/receiving orders? Would such conversations still involve traversals in the same space, or would it look qualitatively different? Would there still be goal states or just open-ended evolution?

[-]Adam Zerner4y30

The conversation would then involve looking for holes in each other's mental maps (regions of high uncertainty) and cooperating to fill them in.

Absolutely! Although I'm not sure how well this particular path traversal analogy fits that idea. I like the one I used in Debugging the student more. I think the differences between the two are subtle but there.

You seemed to imply that conversations can have goals, i.e. destinations that participants in the conversation can try to steer it towards.

Yeah, I think so. An example that comes to my mind is that recently I was texting with a friend. We were talking about how there are so many covid cases in the NBA. I said how it feels weird to me given how disproportionate it is vs the general population. My friend said stuff about how athletes travel a lot and often do risky things like going out clubbing. I said that's probably true but it doesn't seem strong enough to explain it. Then he said how they are constantly getting covid tests. That lead to a lightbulb going off in my head. "Of course! That's it!" We both felt happy with that as the explanation for the phenomenon, and using this analogy, we reached the destination.

But to address what you bring up later in your comment, I don't think conversations always do or always should have this sort of singular destination as the goal. Witty banter is a good example of that. I think that like most things, it's a spectrum. Sometimes there is a very clear and singular destination that everyone knows they are after, but that is an extreme. Other times the conversation participants know they are headed in some general direction, but aren't sure exactly where the destination. Ie. there is an element of babbling.

They can simulate conversations, but they can't really participate in genuine conversation-space traversals in the sense of deliberately looking for gaps in understanding and for ways to fill those gaps.

I actually know almost nothing about how language models like GPT-3 work, but it at least seems like it should be possible for them to do this, no?

By the way, how would your model handle other types of conversation that have purposes other than conveying or seeking information, such as witty banter, small talk, or giving/receiving orders? Would such conversations still involve traversals in the same space, or would it look qualitatively different? Would there still be goal states or just open-ended evolution?

To address this more explicitly, I think the model still fits.

In the witty banter case, the participants continue to take tangents, never pursuing one particular destination too hard. They do so because they enjoy the exploring and/or the novelty of going in new directions.
In the giving/receiving orders case, the authority figure has a lot of control over where the conversation goes. And they restrict the paths that the subordinate can take. Eg. by requiring a yes or no answer. Or often times only giving the subordinate one choice for an answer, eg. "Yes sir!".
In small talk, it is taboo to go down certain paths. Eg. this clip makes fun of the fact that moving from small talk to "medium talk" is such a big taboo. In the context of small talk, the other paths to things like medium talk ("How's your marriage?") still exist, you can still go down them, it's just that doing so is taboo.

[-]Gunnar_Zarncke4y20

Do you know the conversational game where two people get assigned different roles (like Napoleon and Marie Curie) but both only know the other person's role? The goal is to figure out who you are and steer the conversation their way. I found it in an old book and many of the games in it assume social conversations to be very collaborative and smalltalk-like. Interuption would be impolite of course so you have to be very subtle in steering the conversation.

[-]Adam Zerner4y20

I haven't heard of that game, but it's a very interesting idea! I'll have to give it a shot!

It sounds incredibly difficult though. The space of possible people you might be is very large. Plus the other person is fighting against, you, trying to figure out who they are before you can figure out who you are.

Interuption would be impolite of course so you have to be very subtle in steering the conversation.

Now that I think about it, maybe it isn't so obvious that interruption is impolite. I am thinking back to a trip I had back home. My girlfriend and mom established a routine where they would continually interrupt each other right before the other one was finished speaking. I don't like doing that, so I never really said anything when the three of us were hanging out.

Then I brought it up. I didn't have this path traversal analogy at the time, but I basically tried to say what I was saying in this blog post about how it doesn't give me a chance to have any input on where the conversation goes, and there are often times where they would steer it in one direction at times when I wasn't ready to make that turn. They said I should just interrupt then. I said how that would be rude. They said no it isn't. They both realized that they were constantly interrupting each other, but genuinely didn't find it offputting at all. Think girl talk, I guess?

This is an anecdote of course, but thinking about it now, I feel like it is a convention I have seen in others before, and isn't too uncommon.

That all is talking descriptively about whether it is impolite. Prescriptively, I think there are various situations where it shouldn't be considered impolite.

LESSWRONG
LW

LESSWRONG
LW

14

Conversation as path traversal

14

14

Interrupting

Tangents

Online