# Reasoning-Grounded Natural Language Explanations for Language Models

arXiv: https://arxiv.org/abs/2503.11248 · HTML: https://mlsanity.com/paper/2503.11248/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [BAE: BERT-based Adversarial Examples for Text Classification](https://mlsanity.com/paper/2004.01970/) (2020)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [Polyjuice: Generating Counterfactuals for Explaining, Evaluating, and Improving Models](https://mlsanity.com/paper/2101.00288/) (2021)
- [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://mlsanity.com/paper/2004.14786/) (2020)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Sequential Integrated Gradients: a simple but effective method for explaining language models](https://mlsanity.com/paper/2305.15853/) (2023)
- [Discretized Integrated Gradients for Explaining Language Models](https://mlsanity.com/paper/2108.13654/) (2021)
- [exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models](https://mlsanity.com/paper/1910.05276/) (2019)
- [Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning](https://mlsanity.com/paper/2401.13986/) (2024)

## Built on by (most cited first, 5 of 5)

- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Model-Agnostic Policy Explanations with Large Language Models](https://mlsanity.com/paper/2504.05625/) (2025)
- [TRUE: A Trustworthy Unified Explanation Framework for Large Language Model Reasoning](https://mlsanity.com/paper/2602.18905/) (2026)
- [Grokipedia vs Wikipedia: An LLM-Based Audit of Political Neutrality along Ideologies](https://mlsanity.com/paper/2607.15146/) (2026)
- [Integrating Feature Understandability into Feature Selection for Human-Centred Tabular Explanations](https://mlsanity.com/paper/2610.16627/) (2026)

## Abstract (arXiv)

We propose a large language model explainability technique for obtaining faithful natural language explanations by grounding the explanations in a reasoning process. When converted to a sequence of tokens, the outputs of the reasoning process can become part of the model context and later be decoded to natural language as the model produces either the final answer or the explanation. To improve the faithfulness of the explanations, we propose to use a joint predict-explain approach, in which the answers and explanations are inferred directly from the reasoning sequence, without the explanations being dependent on the answers and vice versa. We demonstrate the plausibility of the proposed technique by achieving a high alignment between answers and explanations in several problem domains, observing that language models often simply copy the partial decisions from the reasoning sequence into the final answers or explanations. Furthermore, we show that the proposed use of reasoning can also improve the quality of the answers.