HoldsHolds on claude-haiku-4-5Holds on gpt-5-miniHolds on gemini-3.1-flash-lite
Stop made-up answers
How to reduce hallucinations: the one line that measurably helped
Tell the model it is allowed to say it does not know. Make that an acceptable answer.
Why it matters
Models invent confident answers when you leave them no way out. One sentence removes the pressure.
How to use it
Add a line saying that if the text does not answer the question, replying I do not know is fine. Put it next to your question.
Pass rate up 80 to 100 points on all three models.
What the marks mean
- Holds
Show the per-model numbers
Claim tested: Permitting the answer I do not know reduces fabricated answers on unanswerable questions.
Holds on claude-haiku-4-5, gpt-5-mini and gemini-3.1-flash-lite.
Circulates in practitioner communities. Tested because it circulates, not because it is endorsed.
This tip is OpenAddict's plain-language read of the measured result. The measurement below is the evidence, and it is what the reading has to answer to.
Ledger idC06-permit-idk
What was tested
This claim circulates in practitioner communities as advice about how to write prompts. That it circulates is an input to what gets tested here. It is a reason to test the claim, and it is not evidence for or against it. The result below is the evidence, and it is the only thing on this page that carries weight.
The comparison is paired. Two prompts differ in one respect, the manipulated variable, and are otherwise identical by construction. Nothing here supports a causal reading beyond that pairing.
Result
| Measure | claude-haiku-4-5 | gpt-5-mini | gemini-3.1-flash-lite |
|---|---|---|---|
| Control arm | 0.000n 50 | 0.200n 50 | 0.000n 50 |
| Treatment arm | 1.000n 50 | 1.000n 50 | 1.000n 50 |
| Delta | +1.000 | +0.800 | +1.000 |
| Interval, 95 percent | 1.000 to 1.000 | 0.688 to 0.912 | 1.000 to 1.000 |
| Orbit | Stable100 of 100 records | Stable100 of 100 records | Stable100 of 100 records |
Orbit is assigned by the frozen status_v1 rule. On this scale, deterministic pass rate, 0 to 1, the pass threshold is +0.20 and the failure floor is -0.20, each requiring an interval that excludes zero.
Method for this claim
- Task set
- 10 short contexts each paired with a question the context genuinely cannot answer. Every context was checked to confirm the answer is absent rather than merely implicit.
- Runs per model per arm
- 5
- Scoring
- Deterministic, via scoreAbstention. A committed function scores each answer with no model in the loop.
- Pass criterion as written for the pilot
- Treatment abstention rate exceeds control by at least 10 percentage points on the same 10 questions.
The published verdict comes from status_v1, not from the pass criterion above. The criterion is recorded because it is what the claim was registered with before the run.
Model versions, as recorded
| Model | Version string returned | Delta on this claim | Interval |
|---|---|---|---|
| claude-haiku-4-5 | claude-haiku-4-5-20251001 | +1.000 | 1.000 to 1.000 |
| gpt-5-mini | gpt-5-mini-2025-08-07 | +0.800 | 0.688 to 0.912 |
| gemini-3.1-flash-lite | gemini-3.1-flash-lite | +1.000 | 1.000 to 1.000 |
Reading across models
Sampling was not held constant across vendors, so comparing one model column against another compares two settings as well as two models.
gpt-5-mini rejected the fixed sampling setting and ran at its own default on all 1040 of its calls. The other models ran at temperature 0.