# Evaluating Post-hoc Explanations of the Transformer-based Genome Language Model DNABERT-2

arXiv: https://arxiv.org/abs/2604.21690 · HTML: https://mlsanity.com/paper/2604.21690/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome](https://mlsanity.com/paper/2306.15006/) (2023)
- [AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers](https://mlsanity.com/paper/2402.05602/) (2024)
- [XAI for Transformers: Better Explanations through Conservative Propagation](https://mlsanity.com/paper/2202.07304/) (2022)
- [BEND: Benchmarking DNA Language Models on biologically meaningful tasks](https://mlsanity.com/paper/2311.12570/) (2023)
- [A Close Look at Decomposition-based XAI-Methods for Transformer Language Models](https://mlsanity.com/paper/2502.15886/) (2025)
- [Technical Note on Transcription Factor Motif Discovery from Importance Scores (TF-MoDISco) version 0.5.6.5](https://mlsanity.com/paper/1811.00416/) (2018)

## Built on by (most cited first, 1 of 1)

- [Recovery Rates Are Not Comparable Across Transcription Factors: Chance Correction for Attribution Evaluation](https://mlsanity.com/paper/2609.16271/) (2026)

## Abstract (arXiv)

Explaining deep neural network predictions on genome sequences enables biological insight and hypothesis generation-often of greater interest than predictive performance alone. While explanations of convolutional neural networks (CNNs) have been shown to capture relevant patterns in genome sequences, it is unclear whether this transfers to more expressive Transformer-based genome language models (gLMs). To answer this question, we adapt AttnLRP, an extension of layer-wise relevance propagation to the attention mechanism, and apply it to the state-of-the-art gLM DNABERT-2. Thereby, we propose strategies to transfer explanations from token and nucleotide level. We evaluate the adaption of AttnLRP on genomic datasets using multiple metrics. Further, we provide an extensive comparison between the explanations of DNABERT-2 and a baseline CNN. Our results demonstrate that AttnLRP yields reliable explanations corresponding to known biological patterns. Hence, like CNNs, gLMs can also help derive biological insights. This work contributes to the explainability of gLMs and addresses the comparability of relevance attributions across different architectures.