mlsanityData to 13 Oct 2026

Truth Machines: Synthesizing Veracity in AI Language Models

arXiv 2301.12066 ↗First posted 28 Jan 2023cs.CY cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

As AI technologies are rolled out into healthcare, academia, human resources, law, and a multitude of other domains, they become de-facto arbiters of truth. But truth is highly contested, with many different definitions and approaches. This article discusses the struggle for truth in AI systems and the general responses to date. It then investigates the production of truth in InstructGPT, a large language model, highlighting how data harvesting, model architectures, and social feedback mechanisms weave together disparate understandings of veracity. It conceptualizes this performance as an operationalization of truth, where distinct, often conflicting claims are smoothly synthesized and confidently presented into truth-statements. We argue that these same logics and inconsistencies play out in Instruct's successor, ChatGPT, reiterating truth as a non-trivial problem. We suggest that enriching sociality and thickening "reality" are two promising vectors for enhancing the truth-evaluating capacities of future language models. We conclude, however, by stepping back to consider AI truth-telling as a social practice: what kind of "truth" do we as listeners desire?

Key facts. Cited by 8 papers in the map (data through 13 Oct 2026). Builds on 16 of its 105 references that are in the map. First posted on arXiv 28 Jan 2023.

Builds on

16 of 105 references.

References · 16

  1. 2020Language Models are Few-Shot Learnerscited by 32,320
  2. 2022Training language models to follow instructions with human feedbackcited by 15,856
  3. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,691
  4. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,949
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,650
  6. 2020Learning to summarize from human feedbackcited by 2,575
  7. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,376
  8. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,041
  9. 2022Discovering Latent Knowledge in Language Models Without Supervisioncited by 750
  10. 2017Generative Adversarial Networks: An Overviewcited by 589
  11. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 473
  12. 2020Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claimscited by 165
4 more
  1. 2021Truthful AI: Developing and governing AI that does not liecited by 111
  2. 2020Data, Power and Bias in Artificial Intelligencecited by 7
  3. 2022Automating Ambiguity: Challenges and Pitfalls of Artificial Intelligencecited by 7
  4. 2022Deceptive AI Systems That Give Explanations Are Just as Convincing as Honest AI Systems in Human-Machine Decision Makingcited by 5

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 1; 2026: 2.

8 papers.

  1. 2024Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundationscited by 19
  2. 2024Automating Thematic Analysis: How LLMs Analyse Controversial Topicscited by 10
  3. 2023Generative AI: Implications and Applications for Educationcited by 8
  4. 2026Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignmentcited by 2
  5. 2023The Application of Affective Measures in Text-based Emotion Aware Recommender Systemscited by 1
  6. 2023The Problem of Alignmentcited by 1
  7. 2025Advances in Large Language Models for Medicinecited by 1
  8. 2026Generative Confidants: How do People Experience Trust in Emotional Support from Generative AI?cited by 0