mlsanityData to 14 Oct 2026

LLMs grasp morality in concept

arXiv 2311.02294 ↗First posted 4 Nov 2023cs.CL cs.CYcited by 2

Not on the map. Why?

Abstract (arXiv)

Work in AI ethics and fairness has made much progress in regulating LLMs to reflect certain values, such as fairness, truth, and diversity. However, it has taken the problem of how LLMs might 'mean' anything at all for granted. Without addressing this, it is not clear what imbuing LLMs with such values even means. In response, we provide a general theory of meaning that extends beyond humans. We use this theory to explicate the precise nature of LLMs as meaning-agents. We suggest that the LLM, by virtue of its position as a meaning-agent, already grasps the constructions of human society (e.g. morality, gender, and race) in concept. Consequently, under certain ethical frameworks, currently popular methods for model alignment are limited at best and counterproductive at worst. Moreover, unaligned models may help us better develop our moral and social philosophy.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 4 Nov 2023.

Builds on

16 of 41 references.

References · 16

  1. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  2. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  3. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  4. 2022Survey of Hallucination in Natural Language Generationcited by 2,075
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  6. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
  7. 2023The Curse of Recursion: Training on Generated Data Makes Models Forgetcited by 356
  8. 2020A Survey on Neural Network Interpretabilitycited by 291
  9. 2021Can Machines Learn Morality? The Delphi Experimentcited by 141
  10. 2022Language Models as Agent Modelscited by 132
  11. 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
  12. 2023NLPositionality: Characterizing Design Biases of Datasets and Modelscited by 94
4 more
  1. 2022Large Language Models and the Reverse Turing Testcited by 38
  2. 2019From Clustering to Cluster Explanations via Neural Networkscited by 34
  3. 2023Imitation versus Innovation: What children can do that large language and language-and-vision models cannot (yet)?cited by 13
  4. 2023On the Computation of Meaning, Language Models and Incomprehensible Horrorscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 1.

2 papers.

  1. 2026Large Language Model Reasoning Failurescited by 21
  2. 2024Legally Binding but Unfair? Towards Assessing Fairness of Privacy Policiescited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Beyond Ethical Alignment: Evaluating LLMs as Artificial Moral Assistants
  2. 2024The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making
  3. 2024MoralBench: Moral Evaluation of LLMs
  4. 2023Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs
  5. 2025Black Box Deployed -- Functional Criteria for Artificial Moral Agents in the LLM Era
  6. 2023Exploring the psychology of LLMs' Moral and Legal Reasoning
  7. 2026How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions
  8. 2025The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas