Saved in:
Bibliographic Details
Main Authors: Rost, Thomas Manuel, Figlia, Martina, Wallraff, Bernd
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.09043
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914048185991168
author Rost, Thomas Manuel
Figlia, Martina
Wallraff, Bernd
author_facet Rost, Thomas Manuel
Figlia, Martina
Wallraff, Bernd
contents We introduce and evaluate Stated Preference for Interaction and Continued Engagement (SPICE), a simple diagnostic signal elicited by asking a Large Language Model a YES or NO question about its willingness to re-engage with a user's behavior after reviewing a short transcript. In a study using a 3-tone (friendly, unclear, abusive) by 10-interaction stimulus set, we tested four open-weight chat models across four framing conditions, resulting in 480 trials. Our findings show that SPICE sharply discriminates by user tone. Friendly interactions yielded a near-unanimous preference to continue (97.5% YES), while abusive interactions yielded a strong preference to discontinue (17.9% YES), with unclear interactions falling in between (60.4% YES). This core association remains decisive under multiple dependence-aware statistical tests, including Rao-Scott adjustment and cluster permutation tests. Furthermore, we demonstrate that SPICE provides a distinct signal from abuse classification. In trials where a model failed to identify abuse, it still overwhelmingly stated a preference not to continue the interaction (81% of the time). An exploratory analysis also reveals a significant interaction effect: a preamble describing the study context significantly impacts SPICE under ambiguity, but only when transcripts are presented as a single block of text rather than a multi-turn chat. The results validate SPICE as a robust, low-overhead, and reproducible tool for auditing model dispositions, complementing existing metrics by offering a direct, relational signal of a model's state. All stimuli, code, and analysis scripts are released to support replication.
format Preprint
id arxiv_https___arxiv_org_abs_2509_09043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation
Rost, Thomas Manuel
Figlia, Martina
Wallraff, Bernd
Computation and Language
Artificial Intelligence
Multiagent Systems
We introduce and evaluate Stated Preference for Interaction and Continued Engagement (SPICE), a simple diagnostic signal elicited by asking a Large Language Model a YES or NO question about its willingness to re-engage with a user's behavior after reviewing a short transcript. In a study using a 3-tone (friendly, unclear, abusive) by 10-interaction stimulus set, we tested four open-weight chat models across four framing conditions, resulting in 480 trials. Our findings show that SPICE sharply discriminates by user tone. Friendly interactions yielded a near-unanimous preference to continue (97.5% YES), while abusive interactions yielded a strong preference to discontinue (17.9% YES), with unclear interactions falling in between (60.4% YES). This core association remains decisive under multiple dependence-aware statistical tests, including Rao-Scott adjustment and cluster permutation tests. Furthermore, we demonstrate that SPICE provides a distinct signal from abuse classification. In trials where a model failed to identify abuse, it still overwhelmingly stated a preference not to continue the interaction (81% of the time). An exploratory analysis also reveals a significant interaction effect: a preamble describing the study context significantly impacts SPICE under ambiguity, but only when transcripts are presented as a single block of text rather than a multi-turn chat. The results validate SPICE as a robust, low-overhead, and reproducible tool for auditing model dispositions, complementing existing metrics by offering a direct, relational signal of a model's state. All stimuli, code, and analysis scripts are released to support replication.
title Stated Preference for Interaction and Continued Engagement (SPICE): Evaluating an LLM's Willingness to Re-engage in Conversation
topic Computation and Language
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2509.09043