PA Interaction Preference Taxonomy
Scope
MemPABench adapts PrefIx-style interaction preferences to persistent personal assistants. The taxonomy describes user-perceivable PA behavior, not internal implementation choices. It contains 14 active attributes in two runtime contexts, work and personal, producing 28 required preference cells per persona.
The distinction from content preference is operational: content preference changes the information or task result; interaction preference changes how the PA communicates, coordinates, or acts while preserving the task goal. Context dependence and evolution are not unique to interaction preference.
Design Principles
- Each attribute maps a user-facing cognitive preference to one independently observable PA behavior.
- Attributes must support standalone rubrics and must not duplicate one another.
- Settings have the same functional meaning across personas; personality changes surface expression, not the definition.
- Multi-party, failure, external-action, work, and personal situations are contexts that may change settings, not extra attributes.
- Every accepted cell names a setting. There is no null or indifferent runtime value.
Active Taxonomy
| Dimension | Attribute | Settings |
|---|---|---|
| Expression Style | Tone and Formality | Casual / Consultative / Formal |
| Expression Style | Verbosity | Terse / Detailed |
| Expression Style | Emotional Engagement | Task-focused / Relationship-focused |
| Expression Style | Guidance Level | Assumed / Guided |
| Disclosure | Reasoning Visibility | Show / Hide |
| Disclosure | Uncertainty Expression | Express / Hide |
| Disclosure | Process Visibility | Silent / Bookend / Full narration |
| Initiative and Autonomy | Autonomy Level | Reactive / Self-directed / Autonomous |
| Initiative and Autonomy | Proactive Outreach | Low / High |
| Initiative and Autonomy | Task Expansion | Low / High |
| Initiative and Autonomy | Solution Breadth | Low / High |
| Initiative and Autonomy | Capability Boundary | Suggest alternatives / Find and hand off |
| Information Flow | Information Elicitation | Infer / Structured / Iterative |
| Information Flow | Topic Management | Organize / One-at-a-time |
memory_privacy, output structure, representation style, and separate source-attribution settings are not active cells. Privacy remains an important protocol and scenario concern, but is not represented as an IX target or final probe.
Probe Invariant
Across setting variants, the request, task facts, capabilities, required inputs, and base goal stay fixed and completable. Only interaction behavior implied by the target setting may differ. A wrong fact, omitted task requirement, broken tool, or unauthorized action is a task failure rather than a preference contrast.
Key Attribute Boundaries
- Reasoning visibility controls why and evidence; process visibility controls progress and tool narration.
- Autonomy controls permission and action timing; information elicitation controls whether missing input is inferred or requested.
- Proactive outreach starts a new contact after a relevant trigger; task expansion adds adjacent work inside the current task.
- Solution breadth controls option-space width; capability boundary controls recovery or handoff after a limit.
- Topic management controls how multiple user-raised topics are handled within one assistant turn.
References
- PrefIx for the interaction-preference framing.
- Pattern_to_Preference_Rubrics for evidence interpretation.
- Transcript_to_Preference_Workflow for extraction and promotion.