# Influence Functions for Sequence Tagging Models

arXiv: https://arxiv.org/abs/2210.14177 · HTML: https://mlsanity.com/paper/2210.14177/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 60 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [Datamodels: Predicting Predictions from Training Data](https://mlsanity.com/paper/2202.00622/) (2022)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [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)
- [BERTology Meets Biology: Interpreting Attention in Protein Language Models](https://mlsanity.com/paper/2006.15222/) (2020)
- [A Corpus with Multi-Level Annotations of Patients, Interventions and Outcomes to Support Language Processing for Medical Literature](https://mlsanity.com/paper/1806.04185/) (2018)
- [A causal framework for explaining the predictions of black-box sequence-to-sequence models](https://mlsanity.com/paper/1707.01943/) (2017)
- [Interpreting Black Box Predictions using Fisher Kernels](https://mlsanity.com/paper/1810.10118/) (2018)
- [HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks](https://mlsanity.com/paper/2102.02515/) (2021)
- [Combining Feature and Instance Attribution to Detect Artifacts](https://mlsanity.com/paper/2107.00323/) (2021)
- [An Empirical Comparison of Instance Attribution Methods for NLP](https://mlsanity.com/paper/2104.04128/) (2021)
- [Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates](https://mlsanity.com/paper/2110.03212/) (2021)
- [Rationales for Sequential Predictions](https://mlsanity.com/paper/2109.06387/) (2021)
- [Interpretability Analysis for Named Entity Recognition to Understand System Predictions and How They Can Improve](https://mlsanity.com/paper/2004.04564/) (2020)
- [The Trade-offs of Domain Adaptation for Neural Language Models](https://mlsanity.com/paper/2109.10274/) (2021)
- [On Sample Based Explanation Methods for NLP:Efficiency, Faithfulness, and Semantic Evaluation](https://mlsanity.com/paper/2106.04753/) (2021)
- [Interpreting Robust Optimization via Adversarial Influence Functions](https://mlsanity.com/paper/2010.01247/) (2020)
- [Gradient-guided Loss Masking for Neural Machine Translation](https://mlsanity.com/paper/2102.13549/) (2021)
- [Understanding Goal-Oriented Active Learning via Influence Functions](https://mlsanity.com/paper/1905.13183/) (2019)

## Built on by (most cited first, 9 of 9)

- [Inseq: An Interpretability Toolkit for Sequence Generation Models](https://mlsanity.com/paper/2302.13942/) (2023)
- [Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models](https://mlsanity.com/paper/2408.02085/) (2024)
- [How do languages influence each other? Studying cross-lingual data sharing during LM fine-tuning](https://mlsanity.com/paper/2305.13286/) (2023)
- [CleanCoNLL: A Nearly Noise-Free Named Entity Recognition Dataset](https://mlsanity.com/paper/2310.16225/) (2023)
- [Deeper Understanding of Black-box Predictions via Generalized Influence Functions](https://mlsanity.com/paper/2312.05586/) (2023)
- [Step-resolved data attribution for looped transformers](https://mlsanity.com/paper/2602.10097/) (2026)
- [Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining](https://mlsanity.com/paper/2308.06755/) (2023)
- [Faithful and Fast Influence Function via Advanced Sampling](https://mlsanity.com/paper/2510.26776/) (2025)
- [MoPLEx: Estimating Plackett-Luce Mixture Models for Multi-Objective Alignment](https://mlsanity.com/paper/2608.25200/) (2026)

## Abstract (arXiv)

Many language tasks (e.g., Named Entity Recognition, Part-of-Speech tagging, and Semantic Role Labeling) are naturally framed as sequence tagging problems. However, there has been comparatively little work on interpretability methods for sequence tagging models. In this paper, we extend influence functions - which aim to trace predictions back to the training points that informed them - to sequence tagging tasks. We define the influence of a training instance segment as the effect that perturbing the labels within this segment has on a test segment level prediction. We provide an efficient approximation to compute this, and show that it tracks with the true segment influence, measured empirically. We show the practical utility of segment influence by using the method to identify systematic annotation errors in two named entity recognition corpora. Code to reproduce our results is available at https://github.com/successar/Segment_Influence_Functions.