# An Empirical Comparison of Instance Attribution Methods for NLP

arXiv: https://arxiv.org/abs/2104.04128 · HTML: https://mlsanity.com/paper/2104.04128/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [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)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Explaining Explanations: An Overview of Interpretability of Machine Learning](https://mlsanity.com/paper/1806.00069/) (2018)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [Representer Point Selection for Explaining Deep Neural Networks](https://mlsanity.com/paper/1811.09720/) (2018)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [Input Similarity from the Neural Network Perspective](https://mlsanity.com/paper/2102.05262/) (2021)
- [RelatIF: Identifying Explanatory Training Examples via Relative Influence](https://mlsanity.com/paper/2003.11630/) (2020)
- [Explaining and Improving Model Behavior with k Nearest Neighbor Representations](https://mlsanity.com/paper/2010.09030/) (2020)
- [Investigating Robustness and Interpretability of Link Prediction via Adversarial Modifications](https://mlsanity.com/paper/1905.00563/) (2019)

## Built on by (most cited first, 30 of 35)

- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization](https://mlsanity.com/paper/2109.02934/) (2021)
- [A Review on Language Models as Knowledge Bases](https://mlsanity.com/paper/2204.06031/) (2022)
- [Foundation Models and Fair Use](https://mlsanity.com/paper/2303.15715/) (2023)
- [Combining Feature and Instance Attribution to Detect Artifacts](https://mlsanity.com/paper/2107.00323/) (2021)
- [The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail](https://mlsanity.com/paper/2110.08300/) (2021)
- [ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writing](https://mlsanity.com/paper/2305.09770/) (2023)
- [Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates](https://mlsanity.com/paper/2110.03212/) (2021)
- [Data-Efficient Finetuning Using Cross-Task Nearest Neighbors](https://mlsanity.com/paper/2212.00196/) (2022)
- [Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting](https://mlsanity.com/paper/2212.06803/) (2022)
- [Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods](https://mlsanity.com/paper/2111.03120/) (2021)
- [Helpful or Harmful Data? Fine-tuning-free Shapley Attribution for Explaining Language Model Predictions](https://mlsanity.com/paper/2406.04606/) (2024)
- [Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes](https://mlsanity.com/paper/2403.17691/) (2024)
- [Influence Functions for Sequence Tagging Models](https://mlsanity.com/paper/2210.14177/) (2022)
- [Revealing the Parametric Knowledge of Language Models: A Unified Framework for Attribution Methods](https://mlsanity.com/paper/2404.18655/) (2024)
- [A Survey on Symbolic Knowledge Distillation of Large Language Models](https://mlsanity.com/paper/2408.10210/) (2024)
- [Detecting and Filtering Unsafe Training Data via Data Attribution with Denoised Representation](https://mlsanity.com/paper/2502.11411/) (2025)
- [Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration](https://mlsanity.com/paper/2410.01285/) (2024)
- [Sparse, Efficient and Explainable Data Attribution with DualXDA](https://mlsanity.com/paper/2402.12118/) (2024)
- [Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models](https://mlsanity.com/paper/2403.12809/) (2024)
- [Short-circuiting Shortcuts: Mechanistic Investigation of Shortcuts in Text Classification](https://mlsanity.com/paper/2505.06032/) (2025)
- [Planted in Pretraining, Swayed by Finetuning: A Case Study on the Origins of Cognitive Biases in LLMs](https://mlsanity.com/paper/2507.07186/) (2025)
- [DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models](https://mlsanity.com/paper/2507.09424/) (2025)
- [Large Language Model Sourcing: A Survey](https://mlsanity.com/paper/2510.10161/) (2025)
- [Interactively Providing Explanations for Transformer Language Models](https://mlsanity.com/paper/2110.02058/) (2021)
- [Towards Using Data-Influence Methods to Detect Noisy Samples in Source Code Corpora](https://mlsanity.com/paper/2205.13022/) (2022)
- [QADYNAMICS: Training Dynamics-Driven Synthetic QA Diagnostic for Zero-Shot Commonsense Question Answering](https://mlsanity.com/paper/2310.11303/) (2023)
- [Relabeling Minimal Training Subset to Flip a Prediction](https://mlsanity.com/paper/2305.12809/) (2023)
- [Class based Influence Functions for Error Detection](https://mlsanity.com/paper/2305.01384/) (2023)
- [PINNfluence: Interpreting PINNs through Influence Functions](https://mlsanity.com/paper/2409.08958/) (2024)

## Abstract (arXiv)

Widespread adoption of deep models has motivated a pressing need for approaches to interpret network outputs and to facilitate model debugging. Instance attribution methods constitute one means of accomplishing these goals by retrieving training instances that (may have) led to a particular prediction. Influence functions (IF; Koh and Liang 2017) provide machinery for doing this by quantifying the effect that perturbing individual train instances would have on a specific test prediction. However, even approximating the IF is computationally expensive, to the degree that may be prohibitive in many cases. Might simpler approaches (e.g., retrieving train examples most similar to a given test point) perform comparably? In this work, we evaluate the degree to which different potential instance attribution agree with respect to the importance of training samples. We find that simple retrieval methods yield training instances that differ from those identified via gradient-based methods (such as IFs), but that nonetheless exhibit desirable characteristics similar to more complex attribution methods. Code for all methods and experiments in this paper is available at: https://github.com/successar/instance_attributions_NLP.