Calibrating Uncertainty in Generative Language Interfaces: A Behavioral Economics Framework for Engagement and Conversion
Bibliographic record
Abstract
Uncertainty in generative language interfaces (GLIs) is inevitable: overconfidence erodes trust, while excessive hedging frustrates users. This paper introduces a framework for calibrating ambiguity in GLIs, combining behavioral economics and HCI insights with entropy-based computational anchoring. The implementation of a modular prototype exposes adjustable “ambiguity knobs”, integrating normalized entropy scoring with a hedging classifier. A large-scale user study (N=2,164) across four domains-e-commerce, enterprise dashboards, education, and creative ideation-evaluates the effects of calibrated ambiguity on trust, curiosity, satisfaction, and task outcomes. Results show that moderate ambiguity consistently improves engagement and trust (e.g., a + 10.4pp conversion uplift in e-commerce, p<0.01) compared with zero-shot and static-hedge baselines. These findings demonstrate that ambiguity calibration is operationalizable, not merely descriptive, and yield actionable design strategies for AI practitioners. By uniting computational uncertainty quantification with domain-sensitive behavioral effects, this work provides a reproducible foundation for trustworthy GLI design.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.060 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.005 | 0.006 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".