From Statements to Questions: AI as Epistemic Repair Infrastructure

In plain language

The paper wanted to see if AI can turn firm claims into open questions. It tried using big text models to pull hidden ideas out of statements. It found that the AI can change a claim into a testable question and show unseen angles. In trials it made hidden assumptions clear without giving a final answer. This helps people talk better and avoid fights that start from hidden beliefs.

Restated for a non-expert reader; the original wording follows.

In the paper's words

Human conflict often begins not with a lack of speech, but with speech that has hardened into statements. Statements can conceal the assumptions that make them possible: what one side takes as perception, the other experiences as accusation. This poster proposes a practical framework for using large language models as tools of negative epistemology: not to decide who is right, but to surface what participants do not know they do not know.

The abstract, verbatim, and its opening sentence is the claim. Every line below is quoted from the text.

Numbers it reports

No sentence of this paper reports a figure with a unit or a quantity word, so none is shown.

How it is done

1. A statement-to-question protocol is introduced for extracting hidden assumptions, generating adversarial perspectives, identifying falsifiers, and deciding whether a situation calls for repair, negotiation, boundary-setting, or enforcement.

   from Abstract

2. Statement-to-question protocol.

   from Poster sections

3. State the belief: "They are acting in bad faith." Extract hidden assumptions: what evidence distinguishes bad faith from fear, incentives, confusion, or constraint?

   from S-Q protocol

What would falsify it

1. A statement-to-question protocol is introduced for extracting hidden assumptions, generating adversarial perspectives, identifying falsifiers, and deciding whether a situation calls for repair, negotiation, boundary-setting, or enforcement.

   from Abstract

2. Identify falsifiers: what observation would change my view?

   from S-Q protocol

Where the claim stops

1. LLMs can help by converting fixed statements into testable questions, generating adversarial perspectives, and making hidden assumptions visible.

   from Thesis

2. Their value is not that they provide truth, but that they expand the space of what participants know they do not know.

   from Thesis

3. Statements can conceal the assumptions that make them possible: what one side takes as perception, the other experiences as accusation.

   from Abstract

Where to read

1. Thesis59 words · 1 min
2. Abstract169 words · 1 min
3. Poster sections64 words · 1 min
4. S-Q protocol55 words · 1 min
5. Risk box32 words · 1 min
6. Artifacts13 words · 1 min
7. Status note28 words · 1 min