Skip to content
Sprint projectNov 15, 2026Paris, France

Epistemic Bridges: Do Language Models Reach the Connections People Make?

Sofia Gallego

Submitted to AI x Epistemics Research Sprint. Sprint projects are early-stage work by participants, not Apart Research publications.

Read the report

Report: Epistemic Bridges: Do Language Models Reach the Connections People Make?

Code (opens in new tab)More on mapideas.org (opens in new tab)
Share

Epistemic Bridges asks how much of the space of connections that people make AI models reach. In the web game Bridges, players link two words with no evident connection, in any form. The same pairs went to 15 open models from 2019 to 2025, with reasoning personas, creative conditions and different temperatures. The players' answers draw a map of ideas, and each model is placed on it by recall and precision, with no model judging any answer. Measured as written, chat models seem to reach almost none of the map. Most of that gap is one shared assistant voice. With the voice removed from every answer in the same way, the newer chat models still reach less of the map than people (recall 47% to 59%, against 81%), and no model comes near people on both counts. Only answering as an ordinary person drawn at random widens the ideas on every model, and a reasoning persona held by such a life widens them too. As more people think with AI, measuring diversity needs the voice and the ideas apart, and keeping ideas diverse may need models with more perspective as well as better reasoning.

Reviews

Judging this Sprint?

Review “Epistemic Bridges: Do Language Models Reach the Connections People Make?”

Your public critique appears on the project page without your name. Reviews of strong projects are shared with funders, as you choose below.

Not shown on the project page.

Shown on the project page, without your name.

Only the Apart team reads this, and funders if you agree below.

Decline to score

Only when the quality of the writing makes the work impossible to follow. Say why in your private critique; the project page shows only that a judge declined, not why.

How much would this matter for the field if it worked? How innovative is it? For scores of 4-5: is this actually new to the field, or replicating recent work?

Scoring guide
  1. 1Negligible. No clear problem addressed, or no meaningful novelty.
  2. 2Limited. Addresses a real problem but with a generic or well-trodden approach. Incremental at best.
  3. 3Moderate. Clear problem with a reasonable approach; some novelty in framing or method beyond routine application of existing tools.
  4. 4Significant. Important problem with an original approach, or identifies a neglected problem area. A valuable contribution others could build on.
  5. 5Exceptional. Tackles a critical problem with a genuinely novel approach, or opens a new research direction. Clear theory of change. You'd be excited to share this with researchers in the area.

How sound are methodology, implementation, and findings?

Scoring guide
  1. 1Seriously flawed. Methodology broken, results uninterpretable, or implementation doesn't work.
  2. 2Weak. Approach has significant gaps: missing validation, flawed experimental design, or incomplete implementation.
  3. 3Competent. Technically solid given the short duration. Methodology makes sense, results are interpretable, limitations acknowledged, work builds toward clear conclusions.
  4. 4Strong. Thorough methodology with convincing validation. Results clearly support conclusions. Immediately useful for future work.
  5. 5Exceptional. Ambitious scope executed rigorously. Surprising findings, novel methods, or unusually robust validation.

How clearly are work, findings, and impact potential communicated?

Scoring guide
  1. 1Incomprehensible. Cannot determine what the project is actually claiming or doing.
  2. 2Hard to follow. Key information buried, missing, or diluted by excessive length. Significant effort to extract main points.
  3. 3Clear enough. Can understand the problem, approach, and results without undue effort. Core content clearly present: problem, method, findings, limitations.
  4. 4Well presented. Easy to follow, well-structured, appropriate level of detail. Target audience would get it quickly.
  5. 5Exceptionally clear. A pleasure to read. Complex ideas made accessible. Could serve as a model for how to present this type of work.
No infohazards
Sharing your name *

When we share a strong project with funders, your name, scores and public critique go with it, confidentially; this choice is only about whether your name is public. If you think this project deserves funding, please also endorse it: that carries the most weight.

Share my private critique with funders *

See our Privacy Policy.

No public critique yet.

Cite this project

@misc{gallego2026epistemic,
  title = {{Epistemic Bridges: Do Language Models Reach the Connections People Make?}},
  author = {Sofia Gallego},
  year = {2026},
  month = nov,
  note = {Submitted to AI x Epistemics Research Sprint, an Apart Research Sprint},
  howpublished = {\url{https://apartresearch.com/sprints/projects/epistemic-bridges-do-language-models-reach-the-connections-people-make-y0xuxrgxw8}},
  url = {https://apartresearch.com/sprints/projects/epistemic-bridges-do-language-models-reach-the-connections-people-make-y0xuxrgxw8}
}
Browse all projects