# MaNtLE: Model-agnostic Natural Language Explainer

arXiv: https://arxiv.org/abs/2305.12995 · HTML: https://mlsanity.com/paper/2305.12995/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 38 references that are in the map.
- First posted on arXiv 22 May 2023.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [Instruction Induction: From Few Examples to Natural Language Task Descriptions](https://mlsanity.com/paper/2205.10782/) (2022)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Rethinking Explainability as a Dialogue: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01875/) (2022)
- [Fixing Model Bugs with Natural Language Patches](https://mlsanity.com/paper/2211.03318/) (2022)
- [CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations](https://mlsanity.com/paper/2204.07142/) (2022)
- [LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning](https://mlsanity.com/paper/2212.09104/) (2022)

## Built on by (most cited first, 4 of 4)

- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [FaithLM: Towards Faithful Explanations for Large Language Models](https://mlsanity.com/paper/2402.04678/) (2024)
- [Learnable Game-theoretic Policy Optimization for Data-centric Self-explanation Rationalization](https://mlsanity.com/paper/2510.13393/) (2025)
- [Agentic-imodels: Evolving agentic interpretability tools via autoresearch](https://mlsanity.com/paper/2605.03808/) (2026)

## Abstract (arXiv)

Understanding the internal reasoning behind the predictions of machine learning systems is increasingly vital, given their rising adoption and acceptance. While previous approaches, such as LIME, generate algorithmic explanations by attributing importance to input features for individual examples, recent research indicates that practitioners prefer examining language explanations that explain sub-groups of examples. In this paper, we introduce MaNtLE, a model-agnostic natural language explainer that analyzes multiple classifier predictions and generates faithful natural language explanations of classifier rationale for structured classification tasks. MaNtLE uses multi-task training on thousands of synthetic classification tasks to generate faithful explanations. Simulated user studies indicate that, on average, MaNtLE-generated explanations are at least 11% more faithful compared to LIME and Anchors explanations across three tasks. Human evaluations demonstrate that users can better predict model behavior using explanations from MaNtLE compared to other techniques