# Truth Machines: Synthesizing Veracity in AI Language Models

arXiv: https://arxiv.org/abs/2301.12066 · HTML: https://mlsanity.com/paper/2301.12066/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 105 references that are in the map.
- First posted on arXiv 28 Jan 2023.

## Builds on (most cited first, 16 of 16)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Generative Adversarial Networks: An Overview](https://mlsanity.com/paper/1710.07035/) (2017)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims](https://mlsanity.com/paper/2004.07213/) (2020)
- [Truthful AI: Developing and governing AI that does not lie](https://mlsanity.com/paper/2110.06674/) (2021)
- [Data, Power and Bias in Artificial Intelligence](https://mlsanity.com/paper/2008.07341/) (2020)
- [Automating Ambiguity: Challenges and Pitfalls of Artificial Intelligence](https://mlsanity.com/paper/2206.04179/) (2022)
- [Deceptive AI Systems That Give Explanations Are Just as Convincing as Honest AI Systems in Human-Machine Decision Making](https://mlsanity.com/paper/2210.08960/) (2022)

## Built on by (most cited first, 8 of 8)

- [Are Large Language Models Moral Hypocrites? A Study Based on Moral Foundations](https://mlsanity.com/paper/2405.11100/) (2024)
- [Automating Thematic Analysis: How LLMs Analyse Controversial Topics](https://mlsanity.com/paper/2405.06919/) (2024)
- [Generative AI: Implications and Applications for Education](https://mlsanity.com/paper/2305.07605/) (2023)
- [Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment](https://mlsanity.com/paper/2604.25136/) (2026)
- [The Application of Affective Measures in Text-based Emotion Aware Recommender Systems](https://mlsanity.com/paper/2305.04796/) (2023)
- [The Problem of Alignment](https://mlsanity.com/paper/2401.00210/) (2023)
- [Advances in Large Language Models for Medicine](https://mlsanity.com/paper/2509.18690/) (2025)
- [Generative Confidants: How do People Experience Trust in Emotional Support from Generative AI?](https://mlsanity.com/paper/2601.16656/) (2026)

## 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?