# Selectively Providing Reliance Calibration Cues With Reliance Prediction

arXiv: https://arxiv.org/abs/2302.09995 · HTML: https://mlsanity.com/paper/2302.09995/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 40 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 8 of 8)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Trust-Aware Decision Making for Human-Robot Collaboration: Model Learning and Planning](https://mlsanity.com/paper/1801.04099/) (2018)
- [Trust and Reliance in XAI -- Distinguishing Between Attitudinal and Behavioral Measures](https://mlsanity.com/paper/2203.12318/) (2022)
- [Unified Questioner Transformer for Descriptive Question Generation in Goal-Oriented Visual Dialogue](https://mlsanity.com/paper/2106.15550/) (2021)

## Built on by (most cited first, 1 of 1)

- [User Decision Guidance with Selective Explanation Presentation from Explainable-AI](https://mlsanity.com/paper/2402.18016/) (2024)

## Abstract (arXiv)

For effective collaboration between humans and intelligent agents that employ machine learning for decision-making, humans must understand what agents can and cannot do to avoid over/under-reliance. A solution to this problem is adjusting human reliance through communication using reliance calibration cues (RCCs) to help humans assess agents' capabilities. Previous studies typically attempted to calibrate reliance by continuously presenting RCCs, and when an agent should provide RCCs remains an open question. To answer this, we propose Pred-RC, a method for selectively providing RCCs. Pred-RC uses a cognitive reliance model to predict whether a human will assign a task to an agent. By comparing the prediction results for both cases with and without an RCC, Pred-RC evaluates the influence of the RCC on human reliance. We tested Pred-RC in a human-AI collaboration task and found that it can successfully calibrate human reliance with a reduced number of RCCs.