Searcharxiv⌕ Search

arXiv subjects

Andreas Göldi

Publications and source records attributed to Andreas Göldi.

2 recordsLinked to original sources

Optimized but Unowned: How AI-Authored Goals Undermine the Motivation They Are Meant to Drive

As AI tools become embedded in productivity and self-improvement contexts, a pressing question emerges: what happens when AI does the goal-setting for us? In a preregistered experiment (N = 470), we compared self-authored goals against LLM-authored goals derived from a personal reflection. LLM-generated goals scored higher on SMART criteria (|d| = 2.26), yet participants in the LLM condition reported lower psychological ownership (|d| = 1.38), commitment (|d| = 1.19), and perceived importance (|d| = 1.13). At two-week follow-up, 72.8% of self-authored participants had acted on two or more of their goals, compared to 46.6% in the LLM condition. Psychological ownership, not goal quality, mediated every downstream motivational outcome. Individuals low in trait self-efficacy, those most likely to seek AI assistance, experienced the steepest ownership erosion. These findings reveal a quality-motivation dissociation in AI-assisted goal-setting and identify authorship preservation as a design priority for AI tools deployed in identity-relevant, behavior-dependent tasks.

cs.HC↗

Insert-expansions for Tool-enabled Conversational Agents

This paper delves into an advanced implementation of Chain-of-Thought-Prompting in Large Language Models, focusing on the use of tools (or "plug-ins") within the explicit reasoning paths generated by this prompting method. We find that tool-enabled conversational agents often become sidetracked, as additional context from tools like search engines or calculators diverts from original user intents. To address this, we explore a concept wherein the user becomes the tool, providing necessary details and refining their requests. Through Conversation Analysis, we characterize this interaction as insert-expansion - an intermediary conversation designed to facilitate the preferred response. We explore possibilities arising from this 'user-as-a-tool' approach in two empirical studies using direct comparison, and find benefits in the recommendation domain.

cs.HC↗