# Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates

arXiv: https://arxiv.org/abs/2110.03212 · HTML: https://mlsanity.com/paper/2110.03212/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 51 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 30 of 43)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Learning the Difference that Makes a Difference with Counterfactually-Augmented Data](https://mlsanity.com/paper/1909.12434/) (2019)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [Mitigating Gender Bias in Natural Language Processing: Literature Review](https://mlsanity.com/paper/1906.08976/) (2019)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems](https://mlsanity.com/paper/1805.04508/) (2018)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Representer Point Selection for Explaining Deep Neural Networks](https://mlsanity.com/paper/1811.09720/) (2018)
- [Adversarial Removal of Demographic Attributes from Text Data](https://mlsanity.com/paper/1808.06640/) (2018)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [Breaking NLI Systems with Sentences that Require Simple Lexical Inferences](https://mlsanity.com/paper/1805.02266/) (2018)
- [Controllable Invariance through Adversarial Feature Learning](https://mlsanity.com/paper/1705.11122/) (2017)

## Built on by (most cited first, 27 of 27)

- [WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation](https://mlsanity.com/paper/2201.05955/) (2022)
- [Shortcut Learning of Large Language Models in Natural Language Understanding](https://mlsanity.com/paper/2208.11857/) (2022)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs](https://mlsanity.com/paper/2303.08114/) (2023)
- [Scalable Influence and Fact Tracing for Large Language Model Pretraining](https://mlsanity.com/paper/2410.17413/) (2024)
- [Probing Classifiers are Unreliable for Concept Removal and Detection](https://mlsanity.com/paper/2207.04153/) (2022)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [First is Better Than Last for Language Data Influence](https://mlsanity.com/paper/2202.11844/) (2022)
- [ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data](https://mlsanity.com/paper/2205.12600/) (2022)
- [Towards Tracing Factual Knowledge in Language Models Back to the Training Data](https://mlsanity.com/paper/2205.11482/) (2022)
- [Unlearning Traces the Influential Training Data of Language Models](https://mlsanity.com/paper/2401.15241/) (2024)
- [Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions](https://mlsanity.com/paper/2406.04606/) (2024)
- [In-Context Learning Demonstration Selection via Influence Analysis](https://mlsanity.com/paper/2402.11750/) (2024)
- [How Many and Which Training Points Would Need to be Removed to Flip this Prediction?](https://mlsanity.com/paper/2302.02169/) (2023)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Influence Functions for Sequence Tagging Models](https://mlsanity.com/paper/2210.14177/) (2022)
- [Speaker Information Can Guide Models to Better Inductive Biases: A Case Study On Predicting Code-Switching](https://mlsanity.com/paper/2203.08979/) (2022)
- [Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models](https://mlsanity.com/paper/2310.00840/) (2023)
- [Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training](https://mlsanity.com/paper/2312.17591/) (2023)
- [A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective](https://mlsanity.com/paper/2411.00360/) (2024)
- [Learning to Ignore Adversarial Attacks](https://mlsanity.com/paper/2205.11551/) (2022)
- [Understanding Text Classification Data and Models Using Aggregated Input Salience](https://mlsanity.com/paper/2211.05485/) (2022)
- [Detecting Instruction Fine-tuning Attacks using Influence Function](https://mlsanity.com/paper/2504.09026/) (2025)
- [CoBA: Counterbias Text Augmentation for Mitigating Various Spurious Correlations via Semantic Triples](https://mlsanity.com/paper/2508.21083/) (2025)
- [DataDignity: Training Data Attribution for Large Language Models](https://mlsanity.com/paper/2605.05687/) (2026)
- [eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts](https://mlsanity.com/paper/2605.06368/) (2026)

## Abstract (arXiv)

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the spurious correlations, but the research was primarily used in human-computer interaction scenarios. It still remains underexplored whether or how such model interpretations can be used to automatically "unlearn" confounding features. In this work, we propose influence tuning--a procedure that leverages model interpretations to update the model parameters towards a plausible interpretation (rather than an interpretation that relies on spurious patterns in the data) in addition to learning to predict the task labels. We show that in a controlled setup, influence tuning can help deconfounding the model from spurious patterns in data, significantly outperforming baseline methods that use adversarial training.