pith. sign in

arxiv: 2606.12418 · v1 · pith:BBBS7R7Vnew · submitted 2026-05-08 · 💻 cs.CY · cs.AI

Divination by Prompt: LLM-Mediated Xuanxue on Chinese Social Media

Chuang Li , Lixuan Wang , Yuqi Chen , Ze Hong This is my paper

Pith reviewed 2026-06-30 23:30 UTC · model grok-4.3

classification 💻 cs.CY cs.AI
keywords LLM divinationXuanxueprompt engineeringconfirmation biasdivinatory authorityXiaohongshumixed methodsanthropology of technology
0
0 comments X

The pith

LLM divination on Chinese social media keeps traditional guidance functions but shifts authority to user prompt refinement and scalable verification.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper studies how people on Xiaohongshu use large language models for divination on personal matters like relationships, jobs, and exams. It shows users reach these tools through viral trends or sudden uncertainty, then collaborate by refining prompts to shape the output. Perceived accuracy often rests on how well the reading matches the user's life story or past events, which aligns with known biases. Professional diviners reject the practice for missing spiritual elements, while users mix scientific and metaphysical explanations. The work claims this preserves divination's core role in handling uncertainty yet changes how authority forms through repeatability and co-production.

Core claim

LLM-mediated divination in Xuanxue preserves core functions of traditional practice while introducing scalability, repeatability, and prompt-driven co-production that reshape how divinatory authority is constructed and evaluated.

What carries the argument

collaborative prompt refinement, in which users iteratively edit inputs to co-produce readings and thereby become active participants in constructing the divinatory output.

If this is right

  • Users treat LLM outputs as repeatable and testable, leading to practices like multiple trials and cross-model checks.
  • Authority shifts toward prompt engineering skill rather than inherited or spiritual expertise.
  • Professional diviners respond by emphasizing ontological differences to maintain boundaries.
  • Participants reconcile AI results with both empirical testing and metaphysical beliefs.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This pattern may extend to other cultural practices where AI becomes a co-author of interpretive knowledge.
  • Repeated use could alter how people experience uncertainty by making divination instantly available and revisable.
  • Economic effects on traditional diviners would depend on whether users see LLM versions as substitutes or supplements.

Load-bearing premise

The 23,000 posts and 32 interviews capture typical user practices and that stated reasons for believing the readings truly stem from biographical fit and confirmation bias.

What would settle it

A controlled study that tracks the same users across repeated LLM readings and traditional diviner sessions to test whether verification behaviors and authority judgments differ systematically from the patterns reported here.

read the original abstract

The rapid proliferation of large language models (LLMs) has produced a striking cultural practice: using conversational AI for divination. This paper offers one of the first systematic studies of LLM-mediated divination in the context of Xuanxue, an internet-native umbrella term for mystical and spiritual practices on Chinese social media. Using a mixed-methods design, we analyze 23000+ posts and comments from Xiaohongshu and conduct 32 semi-structured interviews with users and professional diviners. Users primarily consult LLMs about pragmatic concerns - romantic relationships, careers, exams, and in-game gacha draws - via two intersecting pathways: trend-driven curiosity enabled by viral visibility and zero-cost access, and event-driven anxiety under conditions of uncertainty. A defining feature is collaborative prompt refinement, which turns users into active prompt engineers. Among commenters expressing a clear stance, perceived efficacy skews positive, with "accuracy" often justified through biographical fit and retrospective confirmation, consistent with Barnum and confirmation bias. Users also develop verification practices such as repeated trials and cross-model comparison. Professional diviners, by contrast, portray LLMs as lacking the "spiritual power" required for genuine divination, reflecting both ontological commitments and economic boundary-work. We also show how participants navigate tensions between scientific and metaphysical frames when interpreting AI-generated readings. Situating these findings in anthropological and cognitive-evolutionary theories of divination, we argue that LLM divination preserves core functions of traditional practice while introducing scalability, repeatability, and prompt-driven co-production that reshape how divinatory authority is constructed and evaluated.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper presents a mixed-methods study of LLM-mediated divination (Xuanxue) on Chinese social media. Drawing on 23,000+ Xiaohongshu posts/comments and 32 semi-structured interviews with users and professional diviners, it identifies pragmatic consultation pathways (trend-driven curiosity and event-driven anxiety), collaborative prompt refinement by users, positive efficacy perceptions justified via biographical fit and retrospective confirmation (aligned with Barnum and confirmation bias), verification practices like repeated trials, and professional diviners' rejection of LLMs for lacking spiritual power. The central argument is that LLM divination preserves core functions of traditional practice while introducing scalability, repeatability, and prompt-driven co-production that reshape divinatory authority.

Significance. If the empirical claims hold after addressing sampling and validation issues, the work would be a valuable early systematic contribution to the anthropology of AI and divination practices. It explicitly credits the large post volume and interview data, situates findings in established cognitive-evolutionary and anthropological theories, and offers falsifiable observations about user behaviors and authority shifts that could be tested in follow-up studies.

major comments (2)
  1. [Methods] Methods section (data collection description): The 23,000+ posts are drawn exclusively from Xiaohongshu, a platform whose norms favor trend-driven and visually performative content. This creates a selection bias toward users already inclined to share novel or positive experiences, which is load-bearing for the claim that observed practices establish both continuity with traditional Xuanxue functions and the reshaping of authority via prompt co-production.
  2. [Results] Results section (efficacy attributions): Perceived efficacy is coded as biographical fit or retrospective confirmation without supplementary validation methods such as longitudinal tracking of prediction accuracy or comparison against non-LLM controls. This renders the mapping onto Barnum/confirmation-bias mechanisms post-hoc interpretation rather than tested inference, weakening the preservation-of-core-functions argument.
minor comments (2)
  1. [Methods] Methods section: Additional details on coding procedures for posts/comments, exclusion criteria, and inter-rater reliability would strengthen the mixed-methods design and allow assessment of interpretive consistency.
  2. [Introduction] Abstract and introduction: The term 'Xuanxue' is used as an umbrella without a dedicated definition or historical grounding paragraph; a brief clarification would aid readers unfamiliar with the Chinese social media context.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback. We address each major comment below and indicate planned revisions to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Methods] Methods section (data collection description): The 23,000+ posts are drawn exclusively from Xiaohongshu, a platform whose norms favor trend-driven and visually performative content. This creates a selection bias toward users already inclined to share novel or positive experiences, which is load-bearing for the claim that observed practices establish both continuity with traditional Xuanxue functions and the reshaping of authority via prompt co-production.

    Authors: We agree that sampling exclusively from Xiaohongshu introduces platform-specific selection bias, as its norms emphasize visual and trend-driven sharing that may overrepresent users inclined toward novel or positive experiences. Xiaohongshu was selected as the primary site of LLM-mediated Xuanxue proliferation on Chinese social media. We will add an expanded limitations subsection that explicitly discusses these biases and their implications for generalizability. We will also clarify how the 32 interviews provide triangulation by including users who may not post publicly. These changes qualify the scope of our claims without altering the core observations on prompt co-production and authority shifts, which remain grounded in the data from this key platform. revision: partial

  2. Referee: [Results] Results section (efficacy attributions): Perceived efficacy is coded as biographical fit or retrospective confirmation without supplementary validation methods such as longitudinal tracking of prediction accuracy or comparison against non-LLM controls. This renders the mapping onto Barnum/confirmation-bias mechanisms post-hoc interpretation rather than tested inference, weakening the preservation-of-core-functions argument.

    Authors: The efficacy analysis relies on thematic coding of posts and interviews, which is standard for qualitative exploration of cultural practices and does not claim experimental validation of mechanisms. We will revise the results and discussion sections to more explicitly frame the Barnum and confirmation-bias alignment as interpretive rather than tested inference, and we will add a limitations note acknowledging the absence of longitudinal tracking or non-LLM controls. The preservation-of-core-functions argument is supported by observed continuities in pragmatic consultation pathways and user behaviors, not by claims of predictive accuracy; the revisions will make this distinction clearer. revision: partial

Circularity Check

0 steps flagged

Empirical study with no derivations, fitted parameters, or self-referential reductions

full rationale

The paper is a mixed-methods empirical analysis of 23,000+ Xiaohongshu posts and 32 interviews, with findings interpreted against existing anthropological and cognitive-evolutionary theories of divination. No equations, parameter-fitting steps, predictions derived from fitted inputs, or load-bearing self-citations appear in the text; the central claim that LLM divination preserves core functions while adding scalability rests on direct observation and external theoretical framing rather than any reduction to the study's own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The paper relies on standard domain assumptions from anthropology and cognitive psychology about the functions of divination and mechanisms of belief formation, without introducing new free parameters or postulated entities.

axioms (2)
  • domain assumption Divination serves pragmatic functions under conditions of uncertainty
    Invoked when arguing that LLM divination preserves core functions of traditional practice.
  • domain assumption Perceived accuracy in divination is often explained by confirmation bias and biographical fit
    Used to interpret user justifications for LLM efficacy.

pith-pipeline@v0.9.1-grok · 5811 in / 1306 out tokens · 32057 ms · 2026-06-30T23:30:18.296834+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

7 extracted references · 7 canonical work pages

  1. [1]

    Boyer, P. (2020). Why divination? Evolved psychology and strategic interaction in the production of truth. Current Anthropology, 61(1), 100–123. https://doi.org/10.1086/706879 Bruce, S. (2011). Secularization: In defence of an unfashionable theory. Oxford University Press. Bruun, O. (2003). Fengshui in China: Geomantic divination between state orthodoxy a...

    work page doi:10.1086/706879 2020

  2. [2]

    Crissman, L. W. (1967). The segmentary structure of urban overseas Chinese communities. Man, 2(2), 185–204. Cyberspace Administration of China. (2023, July 13). Interim measures for the management of generative artificial intelligence services (Order No. 15). https://www.cac.gov.cn/2023- 07/13/c_1690898327029107.htm Davies, H. (2024). From I-Ching to AI: ...

    work page doi:10.1016/j.socscimed.2017.01.033 1967

  3. [3]

    Frazer, J. G. (1890). The Golden Bough: A Study in Comparative Religion, Volume 2 (V ol. 2). Macmillan. Fu, H., Li, Y ., & Lee, F. L. (2023). Techno-cultural domestication of online tarot reading in contemporary China. Media, Culture & Society, 45(1), 74–91. Garry, M., Chan, W. M., Foster, J., & Henkel, L. A. (2024). Large language models (LLMs) and the i...

    work page doi:10.48550/arxiv.2409.13686 2023

  4. [4]

    traditional culture

    Hong, Z. (2025a). Divination: A Cognitive Perspective. Cambridge University Press. Hong, Z. (2025b). When Rituals Fail: Rationalization, Bayesianism, and Predictive Processing. Evolutionary Anthropology: Issues, News, and Reviews, 34(4), e70020. Hong, Z., & Chen, Y . (2026). The Rhetoric of Disenchantment: Ghost Belief and Secular Critique in Early Twenti...

    work page doi:10.1080/2153599x.2024.2363761 2026

  5. [5]

    Mu, Y . (2024). Research on the Dissemination Effect of AIGC-generated Content on New Media Platforms: A Case Study of Xiaohongshu. Media Studies, 1(2), 1–5. Nadel, S. F. (Siegfried F. (1954). Nupe Religion. Routledge & Paul. https://ehrafworldcultures.yale.edu/document?id=ff52-002 Navigli, R., Conia, S., & Ross, B. (2023). Biases in large language models...

    work page arXiv 2024

  6. [6]

    Park, G. K. (1963). Divination and its social contexts. The Journal of the Royal Anthropological Institute of Great Britain and Ireland, 93(2), 195–209. Qian, G. (2025). 2025「活跃用户」研究报告（小红书平台）. QIAN-GUA.Com. https://www.qian-gua.com/information/detail/3149 Raphals, L. A. (2013). Divination and prediction in early China and ancient Greece. Cambridge Univers...

    work page doi:10.1163/15685276-12341345 1963

  7. [7]

    https://doi.org/10.3390/rel15040435 Turner, V . (1975). Revelation and divination in Ndembu ritual. Cornell University Press. Turner, V . W. (1968). The drums of affliction: A study of religious processes among the Ndembu of Zambia. Clarendon Press. Tylor, E. B. (1871). Primitive culture: Researches into the development of mythology, philosophy, religion,...

    work page doi:10.3390/rel15040435 1975