# Evaluating the Values of Sources in Transfer Learning

arXiv: https://arxiv.org/abs/2104.12567 · HTML: https://mlsanity.com/paper/2104.12567/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 54 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [Linguistic Knowledge and Transferability of Contextual Representations](https://mlsanity.com/paper/1903.08855/) (2019)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [Exploring and Predicting Transferability across NLP Tasks](https://mlsanity.com/paper/2005.00770/) (2020)
- [Neuron Shapley: Discovering the Responsible Neurons](https://mlsanity.com/paper/2002.09815/) (2020)
- [On the Tractability of SHAP Explanations](https://mlsanity.com/paper/2009.08634/) (2020)
- [Adversarial Multi-task Learning for Text Classification](https://mlsanity.com/paper/1704.05742/) (2017)
- [Learning to select data for transfer learning with Bayesian Optimization](https://mlsanity.com/paper/1707.05246/) (2017)
- [Data Valuation for Medical Imaging Using Shapley Value: Application on A Large-scale Chest X-ray Dataset](https://mlsanity.com/paper/2010.08006/) (2020)
- [Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing](https://mlsanity.com/paper/1909.01482/) (2019)
- [Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?](https://mlsanity.com/paper/1911.07128/) (2019)
- [Interpretable feature subset selection: A Shapley value based approach](https://mlsanity.com/paper/2001.03956/) (2020)

## Built on by (most cited first, 11 of 11)

- [A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations](https://mlsanity.com/paper/2407.04069/) (2024)
- [Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks](https://mlsanity.com/paper/2311.00288/) (2023)
- [CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification](https://mlsanity.com/paper/2211.06800/) (2022)
- [CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging](https://mlsanity.com/paper/2502.05664/) (2025)
- [Why Does Zero-Shot Cross-Lingual Generation Fail? An Explanation and a Solution](https://mlsanity.com/paper/2305.17325/) (2023)
- [Data Selection for Fine-tuning Large Language Models Using Transferred Shapley Values](https://mlsanity.com/paper/2306.10165/) (2023)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies](https://mlsanity.com/paper/2204.08952/) (2022)
- [Efficient Shapley Values Estimation by Amortization for Text Classification](https://mlsanity.com/paper/2305.19998/) (2023)
- [Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning](https://mlsanity.com/paper/2509.13624/) (2025)
- [Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.07185/) (2024)

## Abstract (arXiv)

Transfer learning that adapts a model trained on data-rich sources to low-resource targets has been widely applied in natural language processing (NLP). However, when training a transfer model over multiple sources, not every source is equally useful for the target. To better transfer a model, it is essential to understand the values of the sources. In this paper, we develop SEAL-Shap, an efficient source valuation framework for quantifying the usefulness of the sources (e.g., domains/languages) in transfer learning based on the Shapley value method. Experiments and comprehensive analyses on both cross-domain and cross-lingual transfers demonstrate that our framework is not only effective in choosing useful transfer sources but also the source values match the intuitive source-target similarity.