mlsanityData to 13 Oct 2026

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

arXiv 2207.00868 ↗First posted 2 Jul 2022cs.AI cs.CL cs.CYcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 25 of its 280 references that are in the map. First posted on arXiv 2 Jul 2022.

Builds on

25 of 280 references.

References · 25

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  2. 2020Language Models are Few-Shot Learnerscited by 32,320
  3. 2017Deep reinforcement learning from human preferencescited by 3,871
  4. 2016Concrete Problems in AI Safetycited by 1,614
  5. 2022LaMDA: Language Models for Dialog Applicationscited by 1,219
  6. 2019Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inferencecited by 867
  7. 2020Artificial Intelligence, Values and Alignmentcited by 443
  8. 2019What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language modelscited by 317
  9. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 294
  10. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 254
  11. 2020Experience Grounds Languagecited by 241
  12. 2021Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Littlecited by 176
13 more
  1. 2018Incomplete Contracting and AI Alignmentcited by 60
  2. 2021Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communitiescited by 40
  3. 2018Learning from Richer Human Guidance: Augmenting Comparison-Based Learning with Feature Queriescited by 16
  4. 2020Implementations in Machine Ethics: A Surveycited by 16
  5. 2021Pragmatic competence of pre-trained language models through the lens of discourse connectivescited by 16
  6. 2020Open Questions in Creating Safe Open-ended AI: Tensions Between Control and Creativitycited by 15
  7. 2021The Singleton Fallacy: Why Current Critiques of Language Models Miss the Pointcited by 12
  8. 2021Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligencecited by 10
  9. 2021Large Language Models are not Models of Natural Language: they are Corpus Modelscited by 6
  10. 2021Est-ce que vous compute? Code-switching, cultural identity, and AIcited by 6
  11. 2022Moral Dilemmas for Moral Machinescited by 6
  12. 2022Linguistic communication as (inverse) reward designcited by 6
  13. 2019Learning from Learning Machines: Optimisation, Rules, and Social Normscited by 3

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Deep Learning and Ethicscited by 0