Confidence Can Be Used to Discriminate Between Accurate and Inaccurate Lie Decisions
Bibliographic record
Abstract
There is a long-standing belief that confidence is not useful at discriminating between accurate and inaccurate deception decisions. Historically, this position made sense because people showed little ability to discriminate lie-tellers from truth-tellers. But, it is now widely accepted that, under certain conditions, people can discriminate between lie-tellers and truth-tellers. Nevertheless, belief that confidence does not discriminate between accurate and inaccurate responses persists. This belief is somewhat paradoxical because, to the extent that people can discriminate between lie-tellers and truth-tellers, signal detection theory naturally predicts a positive relationship between confidence and accuracy. In line with our signal-detection-based predictions, we show that, among decisions about whether someone is lying, those made with high confidence are more accurate than those made with low confidence. This important relationship has gone unnoticed in past work because of a reliance on inappropriate measures. Past research examining the confidence-accuracy relationship in deception research relied on correlating average confidence with proportion of correctly identified lies. These correlations provide information on whether more confident judges tend to be more accurate but remain silent on the arguably more important question of whether higher confidence decisions are more accurate than lower confidence decisions. We show that confidence-accuracy characteristic analyses are uniquely suited to measuring the confidence-accuracy relationship in deception research.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.002 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.003 |
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; both teacher heads agree on what is shown here.
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".