# An Information Bottleneck Characterization of the Understanding-Workload Tradeoff

arXiv: https://arxiv.org/abs/2310.07802 · HTML: https://mlsanity.com/paper/2310.07802/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 95 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Builds on (most cited first, 29 of 29)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Effect of Confidence and Explanation on Accuracy and Trust Calibration in AI-Assisted Decision Making](https://mlsanity.com/paper/2001.02114/) (2020)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Manipulating and Measuring Model Interpretability](https://mlsanity.com/paper/1802.07810/) (2018)
- [Questioning the AI: Informing Design Practices for Explainable AI User Experiences](https://mlsanity.com/paper/2001.02478/) (2020)
- [AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap](https://mlsanity.com/paper/2306.01941/) (2023)
- [Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences](https://mlsanity.com/paper/1712.00547/) (2017)
- [Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions](https://mlsanity.com/paper/1901.03729/) (2019)
- ["Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interaction](https://mlsanity.com/paper/2210.03735/) (2022)
- [The deterministic information bottleneck](https://mlsanity.com/paper/1604.00268/) (2016)
- [Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations](https://mlsanity.com/paper/1702.07826/) (2017)
- [Understanding Learned Reward Functions](https://mlsanity.com/paper/2012.05862/) (2020)
- [Explaining a black-box using Deep Variational Information Bottleneck Approach](https://mlsanity.com/paper/1902.06918/) (2019)
- [Enabling Robots to Communicate their Objectives](https://mlsanity.com/paper/1702.03465/) (2017)
- [Charting the Sociotechnical Gap in Explainable AI: A Framework to Address the Gap in XAI](https://mlsanity.com/paper/2302.00799/) (2023)
- [Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps](https://mlsanity.com/paper/2005.08874/) (2020)
- [The Utility of Explainable AI in Ad Hoc Human-Machine Teaming](https://mlsanity.com/paper/2209.03943/) (2022)
- [Selective Explanations: Leveraging Human Input to Align Explainable AI](https://mlsanity.com/paper/2301.09656/) (2023)
- [Explaining Reinforcement Learning to Mere Mortals: An Empirical Study](https://mlsanity.com/paper/1903.09708/) (2019)
- [Semantic categories of artifacts and animals reflect efficient coding](https://mlsanity.com/paper/1905.04562/) (2019)
- [Plan Explanations as Model Reconciliation -- An Empirical Study](https://mlsanity.com/paper/1802.01013/) (2018)
- [Reasoning about Counterfactuals to Improve Human Inverse Reinforcement Learning](https://mlsanity.com/paper/2203.01855/) (2022)
- [Online Explanation Generation for Human-Robot Teaming](https://mlsanity.com/paper/1903.06418/) (2019)

## Built on by (most cited first, 3 of 3)

- [Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents](https://mlsanity.com/paper/2606.05391/) (2026)
- [PaperTrail: A Claim-Evidence Interface for Grounding Provenance in LLM-based Scholarly Q&A](https://mlsanity.com/paper/2602.21045/) (2026)
- [Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Decision Making](https://mlsanity.com/paper/2511.12378/) (2025)

## Abstract (arXiv)

Recent advances in artificial intelligence (AI) have underscored the need for explainable AI (XAI) to support human understanding of AI systems. Consideration of human factors that impact explanation efficacy, such as mental workload and human understanding, is central to effective XAI design. Existing work in XAI has demonstrated a tradeoff between understanding and workload induced by different types of explanations. Explaining complex concepts through abstractions (hand-crafted groupings of related problem features) has been shown to effectively address and balance this workload-understanding tradeoff. In this work, we characterize the workload-understanding balance via the Information Bottleneck method: an information-theoretic approach which automatically generates abstractions that maximize informativeness and minimize complexity. In particular, we establish empirical connections between workload and complexity and between understanding and informativeness through human-subject experiments. This empirical link between human factors and information-theoretic concepts provides an important mathematical characterization of the workload-understanding tradeoff which enables user-tailored XAI design.