# The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial

arXiv: https://arxiv.org/abs/2207.00868 · HTML: https://mlsanity.com/paper/2207.00868/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 280 references that are in the map.
- First posted on arXiv 2 Jul 2022.

## Builds on (most cited first, 25 of 25)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](https://mlsanity.com/paper/1906.01820/) (2019)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)
- [Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little](https://mlsanity.com/paper/2104.06644/) (2021)
- [Incomplete Contracting and AI Alignment](https://mlsanity.com/paper/1804.04268/) (2018)
- [Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities](https://mlsanity.com/paper/2102.04257/) (2021)
- [Pragmatic competence of pre-trained language models through the lens of discourse connectives](https://mlsanity.com/paper/2109.12951/) (2021)
- [Learning from Richer Human Guidance: Augmenting Comparison-Based Learning with Feature Queries](https://mlsanity.com/paper/1802.01604/) (2018)
- [Implementations in Machine Ethics: A Survey](https://mlsanity.com/paper/2001.07573/) (2020)
- [Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativity](https://mlsanity.com/paper/2006.07495/) (2020)
- [The Singleton Fallacy: Why Current Critiques of Language Models Miss the Point](https://mlsanity.com/paper/2102.04310/) (2021)
- [Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence](https://mlsanity.com/paper/2103.00752/) (2021)
- [Large Language Models are not Models of Natural Language: they are Corpus Models](https://mlsanity.com/paper/2112.07055/) (2021)
- [Est-ce que vous compute? Code-switching, cultural identity, and AI](https://mlsanity.com/paper/2112.08256/) (2021)
- [Moral Dilemmas for Moral Machines](https://mlsanity.com/paper/2203.06152/) (2022)
- [Linguistic communication as (inverse) reward design](https://mlsanity.com/paper/2204.05091/) (2022)
- [Learning from Learning Machines: Optimisation, Rules, and Social Norms](https://mlsanity.com/paper/2001.00006/) (2019)

## Built on by (most cited first, 1 of 1)

- [Deep Learning and Ethics](https://mlsanity.com/paper/2305.15239/) (2023)

## Abstract (arXiv)

The value-alignment problem for artificial intelligence (AI) asks how we can ensure that the 'values' (i.e., objective functions) of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic communication (natural language) is a necessary condition for robust value alignment. I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems; or, more loftily, designing robustly beneficial or ethical artificial agents.