# When is it permissible for artificial intelligence to lie? A trust-based approach

arXiv: https://arxiv.org/abs/2103.05434 · HTML: https://mlsanity.com/paper/2103.05434/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 56 references that are in the map.
- First posted on arXiv 9 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Deal or No Deal? End-to-End Learning for Negotiation Dialogues](https://mlsanity.com/paper/1706.05125/) (2017)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Dissecting Contextual Word Embeddings: Architecture and Representation](https://mlsanity.com/paper/1808.08949/) (2018)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models](https://mlsanity.com/paper/1902.08858/) (2019)
- [Pretraining Methods for Dialog Context Representation Learning](https://mlsanity.com/paper/1906.00414/) (2019)
- [Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation](https://mlsanity.com/paper/1804.08069/) (2018)
- [A Survey of Available Corpora for Building Data-Driven Dialogue Systems](https://mlsanity.com/paper/1512.05742/) (2015)
- [Zero-Shot Dialog Generation with Cross-Domain Latent Actions](https://mlsanity.com/paper/1805.04803/) (2018)
- [Taking Principles Seriously: A Hybrid Approach to Value Alignment](https://mlsanity.com/paper/2012.11705/) (2020)
- [Mimetic vs Anchored Value Alignment in Artificial Intelligence](https://mlsanity.com/paper/1810.11116/) (2018)

## Built on by (most cited first, 2 of 2)

- [Towards a Roadmap on Software Engineering for Responsible AI](https://mlsanity.com/paper/2203.08594/) (2022)
- [Deceptive AI Ecosystems: The Case of ChatGPT](https://mlsanity.com/paper/2306.13671/) (2023)

## Abstract (arXiv)

Conversational Artificial Intelligence (AI) used in industry settings can be trained to closely mimic human behaviors, including lying and deception. However, lying is often a necessary part of negotiation. To address this, we develop a normative framework for when it is ethical or unethical for a conversational AI to lie to humans, based on whether there is what we call "invitation of trust" in a particular scenario. Importantly, cultural norms play an important role in determining whether there is invitation of trust across negotiation settings, and thus an AI trained in one culture may not be generalizable to others. Moreover, individuals may have different expectations regarding the invitation of trust and propensity to lie for human vs. AI negotiators, and these expectations may vary across cultures as well. Finally, we outline how a conversational chatbot can be trained to negotiate ethically by applying autoregressive models to large dialog and negotiations datasets.