A starting point for discussion
The idea
The researchers give the AI models instructions and examples based on participants’ details and recorded choices. They include both orders of each proposal pair because a model’s choice may change depending on which proposal appears first. They use LoRA, a method that changes some of a model’s parameter values, to adapt about 12% of them while keeping the rest fixed.
Place in the reasoning
AI assessment · Connected to reasoning
Describes including both orderings of proposal pairs to address order sensitivity; this does not show that presentation effects were eliminated.
Different prediction checks reveal different limits
The design is relevant to reliability under presentation changes but does not itself demonstrate order invariance.
What this means and why it matters
What this means
The researchers adapt AI models for this task using examples of participants’ choices. They change about 12% of the model parameters, the settings inside an AI system that affect its responses, and leave the rest fixed.
Why it matters
These are study methods, not proof that the effect of option order was removed or that the method works equally well with other data.
Conditions & assumptions
Source coverage: Full readable text of the retrieved 37-page research draft, a research draft shared before formal publication, including references and appendices. Figures are not independently interpreted. The method gives the AI model instructions and examples using participant information and choices. Reversing proposal order is intended to address the possibility that the model’s choice changes depending on which option appears first. LoRA adapts a model by changing some of its parameter values without changing them all.
Questions this connects to
AI-suggested relationships. Authors have not necessarily responded to one another.
Related claims & perspectives
AI-suggested relationships. Authors have not necessarily responded to one another.