Concern 83 · Working draft · editorial review in progress
Preference elicitation manipulation
Preference elicitation manipulation happens when the way reviewers are asked for feedback pushes them toward a particular answer.
Understanding the concern
A question's wording, the order of options, or what background is shown can influence a rating. The resulting dataset may be presented as a neutral record of what people wanted even though the collection process helped shape the response.
This differs from secretly changing a submitted label. The person may answer sincerely within a leading setup. Teams should inspect the questions, test alternative presentations, and record uncertainty rather than treat the final click as a complete expression of preference.
An example
Asking which answer is more helpful after praising one option is not the same as asking without that cue.
Illustrative unless identified as a documented case.
Evidence and its limits
Supports examining annotation design and collection context; this is a methodological concern, not an allegation about a named feedback program.
Barbara Plank · EMNLP 2022 · Research position paper
The Problem of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation ↗ (opens in a new tab)Explains why human disagreement can contain useful information rather than merely label noise.
Gebru and colleagues · Communications of the ACM · Research proposal
Datasheets for Datasets ↗ (opens in a new tab)Documentation questions cover composition, collection, time, uses, permissions, and maintenance. This is a documentation method, not proof of a particular dataset's defects.
Broader frameworks and background
These resources provide context. They do not establish every claim in this concern.
A question to discuss
Would reviewers make the same choice if the wording, order, or context changed?
Keep track of different views, what needs checking, and any next step in your own discussion notes.
Open discussion notes →Principles for the conversation
Before you finish · reflect together
Virtues and principles to consider
Virtues are qualities we practice in how we treat people and make choices. They are not scores for judging someone. Use these ideas to explore what a thoughtful response could look like.
Truthfulness
Truthfulness means making claims that match the evidence and being clear about what we do not know. It includes correcting mistakes rather than protecting a polished story.
Check sources, label guesses, and distinguish a trial result from a proven benefit. If AI helped produce a claim, someone still needs to take responsibility for checking it.
Ask together: What can we honestly say, and what still needs checking?
Justice
Justice means fair treatment, fair procedures, and attention to who receives benefits and burdens. It asks whether people with less power can be heard and seek repair.
Look at outcomes across different groups and individual cases. Provide a usable way to challenge decisions and correct harm. Equal wording in a policy does not guarantee equal treatment in practice.
Ask together: Who benefits, who bears the cost, and who can challenge the decision?
Stewardship
Stewardship means caring for resources and systems that others depend on, including people who will use them later. It looks beyond the benefit of a quick launch.
Plan for maintenance, energy use, data protection, and eventual shutdown. Ask who will look after the tool when the original team moves on and how future users can avoid inheriting hidden costs.
Ask together: What are we responsible for caring for over time?
Editorial ratings
These are editorial judgments from the register, not measured probabilities or predictions about your situation.
About the register and scoring →More ways to explore
Search for more writing
For more specific or recent material, open a search below or ask for a web summary. AI-generated summaries can contain mistakes; open the original articles to check them.