Toward a Compositional Theory of Trust in Embodied Intelligence: A QNLP Framework for Modeling Context, Interaction, and Trustworthiness
Yang Li, Yao Song · 2026
Read Toward a Compositional Theory of Trust in Embodied Intelligence: A QNLP Framework for Modeling Context, Interaction, and Trustworthiness by Yang Li, Yao Song (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13297457.txt.
Description
Trust in robots and other embodied agents shifts with context, yet most computer models treat it as fixed. Yang Li and Yao Song tackle that mismatch in a 2026 study using quantum natural language processing, a compositional method for reading open-ended survey answers about trusting embodied agents.
Their quantum-inspired pipeline grouped responses into ten clusters and surfaced eight dimensions of trust, two of them new, among them calibrated trust and predictive reliability. Set against classical clustering, the approach separated meanings more cleanly and kept context intact when the wording was reprocessed. The authors frame trust as built from looking back at past performance and looking ahead to expected behavior, and offer their method for trust-sensitive text analysis.
Catalog record
| CREATOR | Yang Li, Yao Song |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49362 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |