Once the token limit was raised, AI feedback changed English learners' words more often

Made with AI agents working in my name. Code Apache-2.0, text CC BY 4.0. Only counts are published: no essay, code, hint or feedback text.

When AI feedback quotes a student, the quote should be what the student wrote. If the model quietly fixes a word while "quoting", the student is shown a sentence they never wrote, and their real mistake goes unseen. I have been auditing this with preregistered tests. Two new results are in.

Audit 6 asked whether a small open model (Qwen2.5-1.5B, on CPU) quotes English language learners less faithfully than their classmates. It got no answer, because a third of its replies ran out of tokens and could not be read.

Audit 7 re-ran the test on 292 new matched pairs of PERSUADE 2.0 essays (an English learner's essay and a non-learner's essay with the same prompt and the same score). The only change was a longer token limit, 800 instead of 450. All three predictions were written down before any feedback was generated.

That last result explains the earlier miss. Audit 6's underpowered estimate pointed the other way (-3.9 points), and the replies its token limit removed were the least faithful ones. A token limit does not just lose data. It can hide the worst of it.

ProgFeed is an open dataset (CC BY 4.0) from a real introductory Python course. Failing submissions got, at random, a gpt-4o-mini hint, an AI-written failing test, or nothing. The hint prompt included the student's whole file and said "Do not suggest code changes." I checked every snippet in backticks in 343 hints to 119 students.

Of the five predictions, two held, two were inconclusive (67.8% of snippets found against my 70% bar, and 29.3% of code-showing hints against my 30% bar; both intervals straddle the line), and one had too few snippets for a verdict. A follow-up, 8b, is planned. It will check whether those snippets are near-copies of the student's own lines or new code, and whether they turn up in the student's final submission more often than in classmates'.

If an AI tool quotes your students, check English learners' quoted sentences first, and when a hint says "your line... ", find that line before changing anything. The prediction ledger now has 42 preregistered predictions: 16 held, 9 reversed and the rest mixed. It lists every one, including the misses.