# Properties and Challenges of LLM-Generated Explanations

arXiv: https://arxiv.org/abs/2402.10532 · HTML: https://mlsanity.com/paper/2402.10532/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 66 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Builds on (most cited first, 30 of 30)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Multimodal Explanations: Justifying Decisions and Pointing to the Evidence](https://mlsanity.com/paper/1802.08129/) (2018)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [Measuring Association Between Labels and Free-Text Rationales](https://mlsanity.com/paper/2010.12762/) (2020)
- [WT5?! Training Text-to-Text Models to Explain their Predictions](https://mlsanity.com/paper/2004.14546/) (2020)
- [Explaining Explanations in AI](https://mlsanity.com/paper/1811.01439/) (2018)
- [Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing](https://mlsanity.com/paper/2102.12060/) (2021)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Few-Shot Self-Rationalization with Natural Language Prompts](https://mlsanity.com/paper/2111.08284/) (2021)
- [Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions](https://mlsanity.com/paper/1901.03729/) (2019)
- [Aligning Faithful Interpretations with their Social Attribution](https://mlsanity.com/paper/2006.01067/) (2020)
- [How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation](https://mlsanity.com/paper/1802.00682/) (2018)
- [Towards Explainable NLP: A Generative Explanation Framework for Text Classification](https://mlsanity.com/paper/1811.00196/) (2018)
- [Explanation-Based Human Debugging of NLP Models: A Survey](https://mlsanity.com/paper/2104.15135/) (2021)
- [The Promise and Peril of Human Evaluation for Model Interpretability](https://mlsanity.com/paper/1711.07414/) (2017)
- [On the Diversity and Limits of Human Explanations](https://mlsanity.com/paper/2106.11988/) (2021)
- [LIREx: Augmenting Language Inference with Relevant Explanation](https://mlsanity.com/paper/2012.09157/) (2020)

## Built on by (most cited first, 24 of 24)

- [Content Moderation by LLM: From Accuracy to Legitimacy](https://mlsanity.com/paper/2409.03219/) (2024)
- [LLM-Generated Black-box Explanations Can Be Adversarially Helpful](https://mlsanity.com/paper/2405.06800/) (2024)
- [DeepSeek vs. ChatGPT vs. Claude: A Comparative Study for Scientific Computing and Scientific Machine Learning Tasks](https://mlsanity.com/paper/2502.17764/) (2025)
- [Epistemological Fault Lines Between Human and Artificial Intelligence](https://mlsanity.com/paper/2512.19466/) (2025)
- [A Rose by Any Other Name: LLM-Generated Explanations Are Good Proxies for Human Explanations to Collect Label Distributions on NLI](https://mlsanity.com/paper/2412.13942/) (2024)
- [Counterfactual Simulatability of LLM Explanations for Generation Tasks](https://mlsanity.com/paper/2505.21740/) (2025)
- [Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces](https://mlsanity.com/paper/2510.22922/) (2025)
- [SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations](https://mlsanity.com/paper/2511.09804/) (2025)
- [SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection](https://mlsanity.com/paper/2408.12748/) (2024)
- [Gazelle: An Instruction Dataset for Arabic Writing Assistance](https://mlsanity.com/paper/2410.18163/) (2024)
- [No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Size](https://mlsanity.com/paper/2408.01444/) (2024)
- [Prompt Inject Detection with Generative Explanation as an Investigative Tool](https://mlsanity.com/paper/2502.11006/) (2025)
- [Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing](https://mlsanity.com/paper/2503.05280/) (2025)
- [Show Me How: Benefits and Challenges of Agent-Augmented Counterfactual Explanations for Non-Expert Users](https://mlsanity.com/paper/2504.13897/) (2025)
- [Investigating Co-Constructive Behavior of Large Language Models in Explanation Dialogues](https://mlsanity.com/paper/2504.18483/) (2025)
- [A Systematic Comparison between Extractive Self-Explanations and Human Rationales in Text Classification](https://mlsanity.com/paper/2410.03296/) (2024)
- [Self-Rationalization in the Wild: A Large Scale Out-of-Distribution Evaluation on NLI-related tasks](https://mlsanity.com/paper/2502.04797/) (2025)
- [Semiotic logical hexagon theory for LLM logical reasoning](https://mlsanity.com/paper/2607.21933/) (2026)
- [Exploiting Latent Linearity in LLMs Improves Explainable Molecular Representation Learning](https://mlsanity.com/paper/2410.08829/) (2024)
- [SNAPE-PM: Building and Utilizing Dynamic Partner Models for Adaptive Explanation Generation](https://mlsanity.com/paper/2505.13053/) (2025)
- [Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models](https://mlsanity.com/paper/2508.04427/) (2025)
- [Beyond Technocratic XAI: The Who, What & How in Explanation Design](https://mlsanity.com/paper/2508.09231/) (2025)
- [EVADE: LLM-Based Explanation Generation and Validation for Error Detection in NLI](https://mlsanity.com/paper/2511.08949/) (2025)
- [From Plausible to Actionable: A Position on LLM Self-Explanations](https://mlsanity.com/paper/2607.15957/) (2026)

## Abstract (arXiv)

The self-rationalising capabilities of large language models (LLMs) have been explored in restricted settings, using task/specific data sets. However, current LLMs do not (only) rely on specifically annotated data; nonetheless, they frequently explain their outputs. The properties of the generated explanations are influenced by the pre-training corpus and by the target data used for instruction fine-tuning. As the pre-training corpus includes a large amount of human-written explanations "in the wild", we hypothesise that LLMs adopt common properties of human explanations. By analysing the outputs for a multi-domain instruction fine-tuning data set, we find that generated explanations show selectivity and contain illustrative elements, but less frequently are subjective or misleading. We discuss reasons and consequences of the properties' presence or absence. In particular, we outline positive and negative implications depending on the goals and user groups of the self-rationalising system.