Communities

Writing
Writing
Codidact Meta
Codidact Meta
The Great Outdoors
The Great Outdoors
Photography & Video
Photography & Video
Scientific Speculation
Scientific Speculation
Cooking
Cooking
Electrical Engineering
Electrical Engineering
Judaism
Judaism
Languages & Linguistics
Languages & Linguistics
Software Development
Software Development
Mathematics
Mathematics
Christianity
Christianity
Code Golf
Code Golf
Music
Music
Physics
Physics
Linux Systems
Linux Systems
Power Users
Power Users
Tabletop RPGs
Tabletop RPGs
Community Proposals
Community Proposals
tag:snake search within a tag
answers:0 unanswered questions
user:xxxx search by author id
score:0.5 posts with 0.5+ score
"snake oil" exact phrase
votes:4 posts with 4+ votes
created:<1w created < 1 week ago
post_type:xxxx type of post
Search help
Notifications
Mark all as read See all your notifications »
Q&A

Comments on What underlying principle is at play for how objective or subjective a natural language instruction is?

Parent

What underlying principle is at play for how objective or subjective a natural language instruction is?

+2
−0

I am interested in exploring a series of prompts for a large language model which move from instructions which have a clear-cut "correct result", such as the instruction to capitalize every letter "S" in some sentence, to questions which may have a few acceptable results, to questions which are more open-ended and subjective.

I would like to think of some analytical framework which makes it clear exactly what is changing, presumably semantically, as we shift along that gradient. I can't see it clearly in my mind at the moment.

My guess is it could be modeled using information theory, and I can expand on how.

History
Why does this post require attention from curators or moderators?
You might want to add some details to your flag.
Why should this post be closed?

0 comment threads

Post
+2
−0

The question alludes to at least three correlated, but quite distinct dimensions.

  • Objectivity/subjectivity
  • Room for model's creativity (information theoretical)
  • Crispness of the boundary between "correct" and "incorrect" productions.

To define them, introduce an additional agent, perhaps a human, acting as a referee. The referee observes of the interaction between the prompt and the model's production and eventually marks the model's performance with a percentage of "correctness": 0 for an incorrect production, 100 for a correct production.

Crispness of correctness - Crisp (black-and-white) prompts will mostly solicit productions scored 0 or 100. Fuzzy (gray area) prompts will mostly solicit productions scored somewhere in between. There's no single most popular measure of fuzziness, but you could pick one from literature or invent your own.

Room for creativity - For a crisp prompt, define this as the logarithm of the number of 100% correct productions for a given prompt. For a fuzzy prompt, you might need something like weighted entropy and/or a "minimum correctness cut-off threshold".

Objectivity/subjectivity seems to relate to a population of referees. An objective prompt will solicit correlated marks from different referees, whereas for a subjective prompt, it's conceivable that different referees will prefer different productions. Ultimately, you can measure that correlation. But the concept is population-dependent.

It's not unusual to see one of those dimensions used as a proxy for another. If the competitors are people and not language models, and you need a very high degree of objectivity, it often helps if all the prompts are crisp and the room for creativity is zero - that is, if each prompt has exactly one correct production. Such limitations don't deliver any objectivity in themselves, but they make it easier to evaluate objectivity using a population of assessors.

I'm afraid that none of those three dimensions are of primarily linguistic nature, or at least I cannot quite see the connection (and a better answer might be able to point one out).

History
Why does this post require attention from curators or moderators?
You might want to add some details to your flag.

1 comment thread

Crispness (3 comments)
Crispness
Michael‭ wrote 9 months ago

Is crispness necessarily bimodal or does any fully discrete success criteria work? (Or does it not matter because "Capitalize all of letter 'S' or all of letter 'D'" is effectively a single test on boolean logic?)

Jirka Hanika‭ wrote 9 months ago

I had bimodal crispness in mind, but you could probably find a way to define crispness to be more like discreteness, thus ending up with yet another dimension. The original post uses the term "clear-cut" which could perhaps mean either; the degree of bimodality is easier to define than the degree of discreteness, though, especially when working with finite data sets.

I borrowed the term "crisp" from the field fuzzy logic, where it is used as the antonym for "fuzzy". Fuzzy logic studies the concept of "partial truth", and so any value other than 100% truth or full falsity counts as fuzzy, even if the particular value has a lot of gravitational force of its own in a given application. In that field, a predicate is crisp if it is bimodal, and it is fuzzy if it ever yields any "in-between" values.

My answer wasn't attempting to exhaust the space of potential dimensions that could be studied. I was just pointing out that the OP already touches on several ones.

Michael‭ wrote 9 months ago

Thanks for explaining!