# On Measuring Faithfulness or Self-consistency of Natural Language Explanations

arXiv: https://arxiv.org/abs/2311.07466 · HTML: https://mlsanity.com/paper/2311.07466/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 57 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning](https://mlsanity.com/paper/2205.09712/) (2022)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Question Decomposition Improves the Faithfulness of Model-Generated Reasoning](https://mlsanity.com/paper/2307.11768/) (2023)
- [Stay on topic with Classifier-Free Guidance](https://mlsanity.com/paper/2306.17806/) (2023)
- [Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations](https://mlsanity.com/paper/2310.11207/) (2023)
- [Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals](https://mlsanity.com/paper/2310.00603/) (2023)
- [Gender Artifacts in Visual Datasets](https://mlsanity.com/paper/2206.09191/) (2022)
- [In-Context Explainers: Harnessing LLMs for Explaining Black Box Models](https://mlsanity.com/paper/2310.05797/) (2023)

## Built on by (most cited first, 30 of 73)

- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation](https://mlsanity.com/paper/2503.11926/) (2025)
- [Chain-of-Thought Reasoning In The Wild Is Not Always Faithful](https://mlsanity.com/paper/2503.08679/) (2025)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps](https://mlsanity.com/paper/2502.14829/) (2025)
- [Reasoning Robustness of LLMs to Adversarial Typographical Errors](https://mlsanity.com/paper/2411.05345/) (2024)
- [The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Models](https://mlsanity.com/paper/2404.03189/) (2024)
- [Chain-of-Thought Unfaithfulness as Disguised Accuracy](https://mlsanity.com/paper/2402.14897/) (2024)
- [Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?](https://mlsanity.com/paper/2404.18624/) (2024)
- [Dissociation of Faithful and Unfaithful Reasoning in LLMs](https://mlsanity.com/paper/2405.15092/) (2024)
- [Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness](https://mlsanity.com/paper/2405.18915/) (2024)
- [LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations](https://mlsanity.com/paper/2509.09396/) (2025)
- [Consistency in Language Models: Current Landscape, Challenges, and Future Directions](https://mlsanity.com/paper/2505.00268/) (2025)
- [A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior](https://mlsanity.com/paper/2602.02639/) (2026)
- [A Causal Lens for Evaluating Faithfulness Metrics](https://mlsanity.com/paper/2502.18848/) (2025)
- [A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models](https://mlsanity.com/paper/2505.23945/) (2025)
- [Multi-Level Explanations for Generative Language Models](https://mlsanity.com/paper/2403.14459/) (2024)
- [RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models](https://mlsanity.com/paper/2602.17053/) (2026)
- [Self-Critique and Refinement for Faithful Natural Language Explanations](https://mlsanity.com/paper/2505.22823/) (2025)
- [Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step](https://mlsanity.com/paper/2406.16144/) (2024)
- [GraphNarrator: Generating Textual Explanations for Graph Neural Networks](https://mlsanity.com/paper/2410.15268/) (2024)
- [Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs](https://mlsanity.com/paper/2511.08409/) (2025)
- [Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations](https://mlsanity.com/paper/2502.12530/) (2025)
- [Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It](https://mlsanity.com/paper/2507.13328/) (2025)
- [From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models](https://mlsanity.com/paper/2509.23676/) (2025)
- [Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation](https://mlsanity.com/paper/2510.13272/) (2025)
- [Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures](https://mlsanity.com/paper/2603.16475/) (2026)
- [Inference to the Best Explanation in Large Language Models](https://mlsanity.com/paper/2402.10767/) (2024)
- [Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations](https://mlsanity.com/paper/2601.00282/) (2026)
- [Aligning What LLMs Do and Say: Towards Self-Consistent Explanations](https://mlsanity.com/paper/2506.07523/) (2025)

## Abstract (arXiv)

Large language models (LLMs) can explain their predictions through post-hoc or Chain-of-Thought (CoT) explanations. But an LLM could make up reasonably sounding explanations that are unfaithful to its underlying reasoning. Recent work has designed tests that aim to judge the faithfulness of post-hoc or CoT explanations. In this work we argue that these faithfulness tests do not measure faithfulness to the models' inner workings -- but rather their self-consistency at output level. Our contributions are three-fold: i) We clarify the status of faithfulness tests in view of model explainability, characterising them as self-consistency tests instead. This assessment we underline by ii) constructing a Comparative Consistency Bank for self-consistency tests that for the first time compares existing tests on a common suite of 11 open LLMs and 5 tasks -- including iii) our new self-consistency measure CC-SHAP. CC-SHAP is a fine-grained measure (not a test) of LLM self-consistency. It compares how a model's input contributes to the predicted answer and to generating the explanation. Our fine-grained CC-SHAP metric allows us iii) to compare LLM behaviour when making predictions and to analyse the effect of other consistency tests at a deeper level, which takes us one step further towards measuring faithfulness by bringing us closer to the internals of the model than strictly surface output-oriented tests. Our code is available at urlhttps://github.com/Heidelberg-NLP/CC-SHAP