# Exploring Practitioner Perspectives On Training Data Attribution Explanations

arXiv: https://arxiv.org/abs/2310.20477 · HTML: https://mlsanity.com/paper/2310.20477/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 31 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Questioning the AI: Informing Design Practices for Explainable AI User Experiences](https://mlsanity.com/paper/2001.02478/) (2020)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [On the Accuracy of Influence Functions for Measuring Group Effects](https://mlsanity.com/paper/1905.13289/) (2019)
- [Training Data Influence Analysis and Estimation: A Survey](https://mlsanity.com/paper/2212.04612/) (2022)
- [Scaling Up Influence Functions](https://mlsanity.com/paper/2112.03052/) (2021)
- [FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging](https://mlsanity.com/paper/2012.15781/) (2020)
- [Understanding the Origins of Bias in Word Embeddings](https://mlsanity.com/paper/1810.03611/) (2018)
- [Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach](https://mlsanity.com/paper/2002.01092/) (2020)
- [Interactive Label Cleaning with Example-based Explanations](https://mlsanity.com/paper/2106.03922/) (2021)
- [The Who in XAI: How AI Background Shapes Perceptions of AI Explanations](https://mlsanity.com/paper/2107.13509/) (2021)
- [Combining Feature and Instance Attribution to Detect Artifacts](https://mlsanity.com/paper/2107.00323/) (2021)

## Built on by (most cited first, 3 of 3)

- [Unifying Corroborative and Contributive Attributions in Large Language Models](https://mlsanity.com/paper/2311.12233/) (2023)
- [Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond](https://mlsanity.com/paper/2410.07158/) (2024)
- [Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers](https://mlsanity.com/paper/2609.07729/) (2026)

## Abstract (arXiv)

Explainable AI (XAI) aims to provide insight into opaque model reasoning to humans and as such is an interdisciplinary field by nature. In this paper, we interviewed 10 practitioners to understand the possible usability of training data attribution (TDA) explanations and to explore the design space of such an approach. We confirmed that training data quality is often the most important factor for high model performance in practice and model developers mainly rely on their own experience to curate data. End-users expect explanations to enhance their interaction with the model and do not necessarily prioritise but are open to training data as a means of explanation. Within our participants, we found that TDA explanations are not well-known and therefore not used. We urge the community to focus on the utility of TDA techniques from the human-machine collaboration perspective and broaden the TDA evaluation to reflect common use cases in practice.