# Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning

arXiv: https://arxiv.org/abs/2401.13986 · HTML: https://mlsanity.com/paper/2401.13986/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 42 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 27 of 27)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior?](https://mlsanity.com/paper/2005.01831/) (2020)
- [Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs](https://mlsanity.com/paper/2311.02262/) (2023)
- [Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations](https://mlsanity.com/paper/2307.08678/) (2023)
- [On the Relation between Sensitivity and Accuracy in In-context Learning](https://mlsanity.com/paper/2209.07661/) (2022)
- [An Evaluation of the Human-Interpretability of Explanation](https://mlsanity.com/paper/1902.00006/) (2019)
- [The Promise and Peril of Human Evaluation for Model Interpretability](https://mlsanity.com/paper/1711.07414/) (2017)
- [Benchmarking and Improving Generator-Validator Consistency of Language Models](https://mlsanity.com/paper/2310.01846/) (2023)
- [Medical Exam Question Answering with Large-scale Reading Comprehension](https://mlsanity.com/paper/1802.10279/) (2018)

## Built on by (most cited first, 26 of 26)

- [Reasoning Models Don't Always Say What They Think](https://mlsanity.com/paper/2505.05410/) (2025)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Are DeepSeek R1 And Other Reasoning Models More Faithful?](https://mlsanity.com/paper/2501.08156/) (2025)
- [Bias-Augmented Consistency Training Reduces Biased Reasoning in Chain-of-Thought](https://mlsanity.com/paper/2403.05518/) (2024)
- [Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.22777/) (2025)
- [Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering](https://mlsanity.com/paper/2409.10790/) (2024)
- [Can We Predict Alignment Before Models Finish Thinking? Towards Monitoring Misaligned Reasoning Models](https://mlsanity.com/paper/2507.12428/) (2025)
- [Counterfactual Simulation Training for Chain-of-Thought Faithfulness](https://mlsanity.com/paper/2602.20710/) (2026)
- [Crafting Interpretable Embeddings by Asking LLMs Questions](https://mlsanity.com/paper/2405.16714/) (2024)
- [Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation](https://mlsanity.com/paper/2411.06387/) (2024)
- [Reasoning-Grounded Natural Language Explanations for Language Models](https://mlsanity.com/paper/2503.11248/) (2025)
- [Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries](https://mlsanity.com/paper/2403.01002/) (2024)
- [XForecast: Evaluating Natural Language Explanations for Time Series Forecasting](https://mlsanity.com/paper/2410.14180/) (2024)
- [Aligning What LLMs Do and Say: Towards Self-Consistent Explanations](https://mlsanity.com/paper/2506.07523/) (2025)
- [A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations](https://mlsanity.com/paper/2505.19299/) (2025)
- [Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations](https://mlsanity.com/paper/2510.17256/) (2025)
- [RobustExplain: Evaluating Robustness of LLM-Based Explanation Agents for Recommendation](https://mlsanity.com/paper/2601.19120/) (2026)
- [CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts](https://mlsanity.com/paper/2510.09278/) (2025)
- [Support-Contra Asymmetry in LLM Explanations](https://mlsanity.com/paper/2510.21884/) (2025)
- [Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study](https://mlsanity.com/paper/2508.09776/) (2025)
- [Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation](https://mlsanity.com/paper/2510.14915/) (2025)
- [ProfileXAI: User-Adaptive Explainable AI](https://mlsanity.com/paper/2510.22998/) (2025)
- [Two Heads are Better than One: Distilling Large Language Model Features Into Small Models with Feature Decomposition and Mixture](https://mlsanity.com/paper/2511.07110/) (2025)
- [Automated Testing of LLM-Based Post Hoc Explainers Using Model Checking as an Oracle](https://mlsanity.com/paper/2608.30581/) (2026)
- [A Removal Based Approach to Improve LLM Faithfulness at Test-Time](https://mlsanity.com/paper/2609.04343/) (2026)

## Abstract (arXiv)

Large language models (LLMs) often generate convincing, fluent explanations. However, different from humans, they often generate inconsistent explanations on different inputs. For example, an LLM may generate the explanation "all birds can fly" when answering the question "Can sparrows fly?" but meanwhile answer "no" to the related question "Can penguins fly?". Explanations should be consistent across related examples so that they allow a human to simulate the LLM's decision process on multiple examples. We propose explanation-consistency finetuning (EC-finetuning), a method that adapts LLMs to generate more consistent natural-language explanations on related examples. EC-finetuning involves finetuning LLMs on synthetic data that is carefully constructed to contain consistent explanations. Across a variety of question-answering datasets in various domains, EC-finetuning yields a 10.0% relative explanation consistency improvement on four finetuning datasets, and generalizes to seven out-of-distribution datasets not seen during finetuning (+4.5% relative). Code is available at https://github.com/yandachen/explanation-consistency-finetuning .