# Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning

arXiv: https://arxiv.org/abs/1903.03877 · HTML: https://mlsanity.com/paper/1903.03877/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2019.

## Built on by (most cited first, 15 of 15)

- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Large Language Models Assume People are More Rational than We Really are](https://mlsanity.com/paper/2406.17055/) (2024)
- [Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning](https://mlsanity.com/paper/2402.17930/) (2024)
- [TASRA: a Taxonomy and Analysis of Societal-Scale Risks from AI](https://mlsanity.com/paper/2306.06924/) (2023)
- [How to talk so AI will learn: Instructions, descriptions, and autonomy](https://mlsanity.com/paper/2206.07870/) (2022)
- [Choice Set Misspecification in Reward Inference](https://mlsanity.com/paper/2101.07691/) (2021)
- [Active Reward Learning from Multiple Teachers](https://mlsanity.com/paper/2303.00894/) (2023)
- [Toward In-Context Teaching: Adapting Examples to Students' Misconceptions](https://mlsanity.com/paper/2405.04495/) (2024)
- [Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values](https://mlsanity.com/paper/2502.00313/) (2025)
- [Active teacher selection for reward learning](https://mlsanity.com/paper/2310.15288/) (2023)
- [Linguistic communication as (inverse) reward design](https://mlsanity.com/paper/2204.05091/) (2022)
- [Representational Alignment Supports Effective Machine Teaching](https://mlsanity.com/paper/2406.04302/) (2024)
- [Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments](https://mlsanity.com/paper/2206.04546/) (2022)
- [The Role of Higher-Order Cognitive Models in Active Learning](https://mlsanity.com/paper/2401.04397/) (2024)
- [Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response](https://mlsanity.com/paper/2607.27508/) (2026)

## Abstract (arXiv)

It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people have an interest in the robot performing well, and will thus behave pedagogically, choosing actions that are informative to the robot. In turn, robots benefit from interpreting the behavior by accounting for this pedagogy. In this work, we focus on misspecification: we argue that robots might not know whether people are being pedagogic or literal and that it is important to ask which assumption is safer to make. We cast objective learning into the more general form of a common-payoff game between the robot and human, and prove that in any such game literal interpretation is more robust to misspecification. Experiments with human data support our theoretical results and point to the sensitivity of the pedagogic assumption.