ArticleProceedings of the National Academy of Sciences of the United States of America2024
Deception abilities emerged in large language models.
Article in Proceedings of the National Academy of Sciences of the United States of America, 2024. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed.
- Should Care Robots Answer? Rethinking Moral Answerability Beyond Humans.Nursing inquiry · 2026Article
- Perceived humanness and empathy are dissociated in relationship advice generated by a large language model.Nature communications · 2026Article
- Evolvable AI: Threats of a new major transition in evolution.Proceedings of the National Academy of Sciences of the United States of America · 2026Article
- Use of large language models to identify pseudo-information: Implications for health information.Health information and libraries journal · 2025Article
- Large language models in clinical psychiatry: Applications and optimization strategies.World journal of psychiatry · 2025Review
- Risks of AI scientists: prioritizing safeguarding over autonomy.Nature communications · 2025Review
- Comparing AI and human decision-making mechanisms in daily collaborative experiments.iScience · 2025Article
- Frontier AI developers need an internal audit function.Risk analysis : an official publication of the Society for Risk Analysis · 2025Article
- Large language models are proficient in solving and creating emotional intelligence tests.Communications psychology · 2025Article
- The Double-Edged Sword of Anthropomorphism in LLMsProceedings (MDPI) · 2025Article
- Capturing Argument in Agent-Based Models.Topoi : an international review of philosophy · 2025Article
- Deception abilities emerged in large language models.Proceedings of the National Academy of Sciences of the United States of America · 2024Article
- AI deception: A survey of examples, risks, and potential solutions.Patterns (New York, N.Y.) · 2024Review
- Human-like intuitive behavior and reasoning biases emerged in large language models but disappeared in ChatGPT.Nature computational science · 2023Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
1 author.
Funding
Abstract
Large language models (LLMs) are currently at the forefront of intertwining AI systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady increase in reasoning abilities, future LLMs are under suspicion of becoming able to deceive human operators and utilizing this ability to bypass monitoring efforts. As a prerequisite to this, LLMs need to possess a conceptual understanding of deception strategies. This study reveals that such strategies emerged in state-of-the-art LLMs, but were nonexistent in earlier LLMs. We conduct a series of experiments showing that state-of-the-art LLMs are able to understand and induce false beliefs in other agents, that their performance in complex deception scenarios can be amplified utilizing chain-of-thought reasoning, and that eliciting Machiavellianism in LLMs can trigger misaligned deceptive behavior. GPT-4, for instance, exhibits deceptive behavior in simple test scenarios 99.16% of the time (
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.