Believing Anthropomorphism: Examining the Role of Anthropomorphic Cues on Trust in Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909197403160576 |
|---|---|
| author | Cohn, Michelle Pushkarna, Mahima Olanubi, Gbolahan O. Moran, Joseph M. Padgett, Daniel Mengesha, Zion Heldreth, Courtney |
| author_facet | Cohn, Michelle Pushkarna, Mahima Olanubi, Gbolahan O. Moran, Joseph M. Padgett, Daniel Mengesha, Zion Heldreth, Courtney |
| contents | People now regularly interface with Large Language Models (LLMs) via speech and text (e.g., Bard) interfaces. However, little is known about the relationship between how users anthropomorphize an LLM system (i.e., ascribe human-like characteristics to a system) and how they trust the information the system provides. Participants (n=2,165; ranging in age from 18-90 from the United States) completed an online experiment, where they interacted with a pseudo-LLM that varied in modality (text only, speech + text) and grammatical person ("I" vs. "the system") in its responses. Results showed that the "speech + text" condition led to higher anthropomorphism of the system overall, as well as higher ratings of accuracy of the information the system provides. Additionally, the first-person pronoun ("I") led to higher information accuracy and reduced risk ratings, but only in one context. We discuss these findings for their implications for the design of responsible, human-generative AI experiences. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06079 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Believing Anthropomorphism: Examining the Role of Anthropomorphic Cues on Trust in Large Language Models Cohn, Michelle Pushkarna, Mahima Olanubi, Gbolahan O. Moran, Joseph M. Padgett, Daniel Mengesha, Zion Heldreth, Courtney Human-Computer Interaction People now regularly interface with Large Language Models (LLMs) via speech and text (e.g., Bard) interfaces. However, little is known about the relationship between how users anthropomorphize an LLM system (i.e., ascribe human-like characteristics to a system) and how they trust the information the system provides. Participants (n=2,165; ranging in age from 18-90 from the United States) completed an online experiment, where they interacted with a pseudo-LLM that varied in modality (text only, speech + text) and grammatical person ("I" vs. "the system") in its responses. Results showed that the "speech + text" condition led to higher anthropomorphism of the system overall, as well as higher ratings of accuracy of the information the system provides. Additionally, the first-person pronoun ("I") led to higher information accuracy and reduced risk ratings, but only in one context. We discuss these findings for their implications for the design of responsible, human-generative AI experiences. |
| title | Believing Anthropomorphism: Examining the Role of Anthropomorphic Cues on Trust in Large Language Models |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2405.06079 |