# Can LLMs Faithfully Explain Themselves in Low-Resource Languages? A Case Study on Emotion Detection in Persian

arXiv: https://arxiv.org/abs/2511.19719 · HTML: https://mlsanity.com/paper/2511.19719/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 24 Nov 2025.

## Builds on (most cited first, 15 of 15)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [Relying on the Unreliable: The Impact of Language Models' Reluctance to Express Uncertainty](https://mlsanity.com/paper/2401.06730/) (2024)
- [Are self-explanations from Large Language Models faithful?](https://mlsanity.com/paper/2401.07927/) (2024)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Investigating the influence of noise and distractors on the interpretation of neural networks](https://mlsanity.com/paper/1611.07270/) (2016)
- [TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation](https://mlsanity.com/paper/2407.10114/) (2024)
- [Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification](https://mlsanity.com/paper/2105.02657/) (2021)
- [ArmanEmo: A Persian Dataset for Text-based Emotion Detection](https://mlsanity.com/paper/2207.11808/) (2022)
- [The Effect of Model Size on LLM Post-hoc Explainability via LIME](https://mlsanity.com/paper/2405.05348/) (2024)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used to generate self-explanations alongside their predictions, a practice that raises concerns about the faithfulness of these explanations, especially in low-resource languages. This study evaluates the faithfulness of LLM-generated explanations in the context of emotion classification in Persian, a low-resource language, by comparing the influential words identified by the model against those identified by human annotators. We assess faithfulness using confidence scores derived from token-level log-probabilities. Two prompting strategies, differing in the order of explanation and prediction (Predict-then-Explain and Explain-then-Predict), are tested for their impact on explanation faithfulness. Our results reveal that while LLMs achieve strong classification performance, their generated explanations often diverge from faithful reasoning, showing greater agreement with each other than with human judgments. These results highlight the limitations of current explanation methods and metrics, emphasizing the need for more robust approaches to ensure LLM reliability in multilingual and low-resource contexts.