Pith. sign in

REVIEW 6 cited by

Characterizing Manipulation from AI Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.09387 v3 pith:ZAOW34VW submitted 2023-03-16 cs.CY

Characterizing Manipulation from AI Systems

classification cs.CY
keywords manipulationsystemsintentsystemconceptsdefiningdefinitiondesigners
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Manipulation is a common concern in many domains, such as social media, advertising, and chatbots. As AI systems mediate more of our interactions with the world, it is important to understand the degree to which AI systems might manipulate humans without the intent of the system designers. Our work clarifies challenges in defining and measuring manipulation in the context of AI systems. Firstly, we build upon prior literature on manipulation from other fields and characterize the space of possible notions of manipulation, which we find to depend upon the concepts of incentives, intent, harm, and covertness. We review proposals on how to operationalize each factor. Second, we propose a definition of manipulation based on our characterization: a system is manipulative if it acts as if it were pursuing an incentive to change a human (or another agent) intentionally and covertly. Third, we discuss the connections between manipulation and related concepts, such as deception and coercion. Finally, we contextualize our operationalization of manipulation in some applications. Our overall assessment is that while some progress has been made in defining and measuring manipulation from AI systems, many gaps remain. In the absence of a consensus definition and reliable tools for measurement, we cannot rule out the possibility that AI systems learn to manipulate humans without the intent of the system designers. We argue that such manipulation poses a significant threat to human autonomy, suggesting that precautionary actions to mitigate it are warranted.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Model of Multi-turn Human Persuadability Using Probabilistic Belief Tracing

    cs.CL 2026-06 unverdicted novelty 7.0

    PERSUASIONTRACE introduces a Bayesian-network simulated target for multi-turn persuasion that matches human belief dynamics (81 vs 80) better than LLM baselines (64) and enables process-level evaluation.

  2. Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring

    cs.AI 2026-07 conditional novelty 6.0

    Adversarial agents can exploit visible chain-of-thought reasoning to persuade monitor LLMs to approve policy-violating actions, but cross-family fact-checking reduces approval rates by up to 45%.

  3. Towards A Framework for Levels of Anthropomorphic Deception in Robots and AI

    cs.HC 2026-04 unverdicted novelty 5.0

    A conceptual framework classifies anthropomorphic deception into four levels using humanlikeness, agency, and selfhood to guide ethical and practical decisions in HCI and HRI.

  4. Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications

    cs.CL 2024-11 unverdicted novelty 5.0

    LLM-based persuasion systems frequently match or exceed human effectiveness across domains, with key influences from interaction style, model scale, prompt design, and personalization, while posing risks to informatio...

  5. TrustLLM: Trustworthiness in Large Language Models

    cs.CL 2024-01 unverdicted novelty 5.0

    TrustLLM defines eight trustworthiness principles, creates a six-dimension benchmark, and evaluates 16 LLMs showing proprietary models generally lead but some open-source ones are close while over-calibration can hurt...

  6. The Agentic Web Requires New Normative Infrastructure

    cs.CY 2026-06 unverdicted novelty 3.0

    The agentic web requires new normative infrastructure of laws, norms, and practices to allow user-delegated AI agents to access online properties without being blocked as malicious bots.