Change the rating scale, change the AI verdict
Across political, sentiment and toxicity tasks, changing one scale feature shifted about one in five category assignments. The unreviewed audit warns against treating LLM scores as stable measurements.
The short version
3 key points
- 1.The experiment crossed two formats, four scale lengths, two signs, three tasks, two prompting strategies and five models.
- 2.Changing a single scale-design feature moved normalised scores by about 0.10 and switched the assigned category for roughly 18% to 20% of texts.
- 3.Toxicity classifications were most sensitive, and adding a written rubric did not remove the instability.
A scoring choice moved roughly one verdict in five
Language models did not give stable text scores when researchers changed only the ruler used to ask the question. In an unreviewed experiment, switching between continuous and ordinal scales changed the assigned low, middle or high category for 18.8% of texts. Changing the number of points changed 18.2%, while moving between signed and unsigned scales changed 20.3%. Average normalised-score shifts were about a tenth of the full scale. For a moderation team or social-science project, that is large enough to alter which posts, parties or people appear extreme.
The design crossed two formats, four lengths—3, 5, 11 and 21 points—and signed versus unsigned numbering. Researchers repeated those conditions for political leaning, movie-review sentiment and toxicity, under zero-shot and rubric prompts, using five proprietary and open models. The English-language datasets contained 1,700 media-bias texts, 5,000 movie reviews and 5,000 toxicity examples. This is a systematic sensitivity test, not a claim that every model decision is wrong.[1]
Toxicity was especially vulnerable to the ruler
Toxicity produced the biggest category changes: between 29% and 40% depending on which scale feature moved. On continuous scales, changing the sign altered 24.4% of categories, compared with 16.3% on ordinal scales. The paper suggests one reason is conceptual. Political leaning and sentiment run between two opposing poles, while toxicity is a one-directional construct from absence to greater presence. A signed scale may tempt a model to treat zero as the boundary for harmlessness even when the verbal labels imply something else.
More points reduced the numerical effect of switching formats, but did not make the resulting categories more stable: 18.2% to 20.1% still changed at every scale length. A written rubric also failed to reduce sensitivity relative to a zero-shot instruction. Extra reasoning helped a little for three open models, but the improvements were small and inconsistent. The audit therefore challenges a familiar comfort: a detailed prompt can make a measurement look disciplined while leaving the result dependent on arbitrary scale design.[1]
The distinction that matters
Three scale edits, three routes to a different category
Each comparison changed one prompt feature while holding the task, text and other scale features fixed.
Format
Continuous ↔ ordinal
18.8% switched category
Range
3, 5, 11 or 21 points
18.2% switched
Sign
Signed ↔ unsigned
20.3% switched
This is a robustness warning, not a universal error rate
The study compares each model with itself under minimally different prompts; it does not show that the new category is less accurate than the old one. Human labels were used for descriptive comparison, not as a complete causal explanation of why scores moved. Only three tasks, three English datasets and five current models were tested. Political categories were heavily concentrated in the middle, sentiment was more polarised, and toxicity had its own class distribution, so part of the difference may come from those datasets rather than the underlying concept alone.
No funding or competing-interest statement appears in the accessible preprint. Before an institution uses LLM scores to flag abuse, measure ideology, rank applicants or compare populations, it should report the exact scale wording and rerun the analysis with plausible alternatives. Decisions that change under a defensible relabelling need human review or a more stable measurement method. Confidence would rise with preregistered replication across languages, domains, model versions and human-designed scales, plus tests of downstream decisions rather than scores alone. The finding is not that numeric prompts are useless; it is that their apparent precision can conceal a fragile choice of ruler.[1]
Evidence check
Unreviewed preprint; three English-language datasets and constructs; five model versions; no evidence that one scale is universally correct or that every downstream decision changes.
Reporting basis: Source analysis. Original source date: 15 October 2026.
Explore the full source and evidence record
What this means for people
- A person or post could be placed in a different risk, sentiment or political category because an analyst changed the numbering rather than the underlying text.
Global context
The models are used internationally, but the experiment's English datasets do not establish how translated labels, culturally specific toxicity or local political spectra behave.
What the evidence does not yet show
- Unreviewed preprint; three English-language datasets and constructs; five model versions; no evidence that one scale is universally correct or that every downstream decision changes.
What to watch next
- Independent multilingual replication, stable results across model updates, preregistered scale choices and audits of real moderation or policy decisions.
Living evidence record
Impact record IAI-0WBQVC6
Evidence stage
Studied
Confidence
Supported
Reporting basis
Source analysis
Independent or research support
Present
Record status
Monitoring
Last checked
17 October 2026
Source trail
1 direct source across 1 source type.
People impact
Documented in this record.
Uncertainty
Limits and next checks are explicit.
Stages describe the evidence available—not whether a technology is good or bad. See the public method.
Single-source reporting disclosure
This record analyses one direct source. It can establish what arXiv published or reported, but it is not independent corroboration of every performance claim or predicted outcome. The confidence label will change only when broader evidence is added.
Evidence trail
Sources used for this report
Links checked 17 October 2026
Research question, topics and regions
How format, range and sign of a rating scale change LLM-based scores for political leaning, sentiment and toxicity
Topics: Content moderation · Political analysis · Measurement · LLM evaluation · Research methods
Regions: Global · Asia
This report is labelled source analysis. We summarise and analyse source material in our own words; company statements remain attributed claims until independently supported. Translated summaries preserve the meaning of the original source and link back to it. Read our editorial standards.
Watch the background, then check the evidence
The Royal Society
AI-generated illustration · not a video frame
YouTube loads only when you choose. Press play in the player to start. If playback is unavailable, use “Watch on YouTube” below.
Healthcare, culture & human impact · Background explainer
Published 2026-07-01 · 44 min 28 sec
Is this the AI future we want? | The Royal Society
A Royal Society discussion with Madhumita Murgia and biomedical engineer Alison Noble on AI’s potential in healthcare, science and culture, recorded at the 30 June 2026 event.
Evidence check: A discussion of opportunities and risks, including future possibilities. It is not evidence that every application described is available or clinically proven.
Source checked 14 October 2026. Check available captions on the publisher’s video page.
The Impact Brief · Free
Keep following the stories that matter to you.
Get our weekday briefing on what changed and why it matters. Choose your topics below.
Continue the story
There’s more to this story
Society & Media
Do AI explanations help people know when to trust a system?
A South Korean survey found that people who perceived an AI system as clearer also reported more understanding, trust and reliance. It did not test whether they actually understood the system or trusted it appropriately.
8 min · 1 source
Society & Media
Did a chatbot empower tourism communities? The study never tested one
A peer-reviewed experiment found that Kimi.ai could tailor advice to six community-tourism roles. But all 36 participants were students acting out those roles, sessions lasted minutes, and the paper reports no real decision, income, cultural or environmental outcome.
8 min · 2 sources
Society & Media
Can image-aware AI catch fake news before it spreads?
A new peer-reviewed model improved two fixed benchmark tests by combining article text, images and an AI-generated image description. It did not verify claims or face a live, changing news stream.
7 min · 2 sources
Reader commentary
What does this mean where you are?
Tell us what you have seen at work, in your community or in everyday life. A question is welcome too. No account is needed; we review notes before publishing them.
Explore commentary across the portal →Published reader notes
0No published reader notes yet. You can start the evidence-led discussion above.
Prefer a private correction or response? Contact the newsroom.