To Ask or Not to Ask: Learning to Require Human Feedback
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911200254623744 |
|---|---|
| author | Pugnana, Andrea De Toni, Giovanni Barbera, Cesare Pellungrini, Roberto Lepri, Bruno Passerini, Andrea |
| author_facet | Pugnana, Andrea De Toni, Giovanni Barbera, Cesare Pellungrini, Roberto Lepri, Bruno Passerini, Andrea |
| contents | Developing decision-support systems that complement human performance in classification tasks remains an open challenge. A popular approach, Learning to Defer (LtD), allows a Machine Learning (ML) model to pass difficult cases to a human expert. However, LtD treats humans and ML models as mutually exclusive decision-makers, restricting the expert contribution to mere predictions. To address this limitation, we propose Learning to Ask (LtA), a new framework that handles both when and how to incorporate expert input in an ML model. LtA is based on a two-part architecture: a standard ML model and an enriched model trained with additional expert human feedback, with a formally optimal strategy for selecting when to query the enriched model. We provide two practical implementations of LtA: a sequential approach, which trains the models in stages, and a joint approach, which optimises them simultaneously. For the latter, we design surrogate losses with realisable-consistency guarantees. Our experiments with synthetic and real expert data demonstrate that LtA provides a more flexible and powerful foundation for effective human-AI collaboration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_08314 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | To Ask or Not to Ask: Learning to Require Human Feedback Pugnana, Andrea De Toni, Giovanni Barbera, Cesare Pellungrini, Roberto Lepri, Bruno Passerini, Andrea Machine Learning Human-Computer Interaction Developing decision-support systems that complement human performance in classification tasks remains an open challenge. A popular approach, Learning to Defer (LtD), allows a Machine Learning (ML) model to pass difficult cases to a human expert. However, LtD treats humans and ML models as mutually exclusive decision-makers, restricting the expert contribution to mere predictions. To address this limitation, we propose Learning to Ask (LtA), a new framework that handles both when and how to incorporate expert input in an ML model. LtA is based on a two-part architecture: a standard ML model and an enriched model trained with additional expert human feedback, with a formally optimal strategy for selecting when to query the enriched model. We provide two practical implementations of LtA: a sequential approach, which trains the models in stages, and a joint approach, which optimises them simultaneously. For the latter, we design surrogate losses with realisable-consistency guarantees. Our experiments with synthetic and real expert data demonstrate that LtA provides a more flexible and powerful foundation for effective human-AI collaboration. |
| title | To Ask or Not to Ask: Learning to Require Human Feedback |
| topic | Machine Learning Human-Computer Interaction |
| url | https://arxiv.org/abs/2510.08314 |