Experimental Economics· 2026Q1
The impact of LLM-based recommendations on decisions under uncertainty
- 0citations
- Q1SCImago
- 2026year
Short summary
LLM-based recommendations compressed valuation distributions for lotteries, reducing extreme valuations without changing mean valuations.
AI-generated from the title and abstract; the full text is not read.
Key points
- LLM recommendations compressed the distribution of lottery valuations.
- Extreme valuations were reduced by LLM recommendations.
- Mean valuations were not significantly changed by LLM recommendations.
- LLMs reduced risk, complexity, and ambiguity aversion intensity.
AI-generated from the title and abstract; the full text is not read.
Abstract
Abstract We study how large language model (LLM) based recommendations affect evaluations of uncertainty. We elicit certainty equivalents for (i) lotteries that share the same reduced-form winning probability but vary in cognitive demands because they are compound, and (ii) an Ellsberg-style ambiguous lottery. Across all lottery types, valuations from participants who receive LLM-based recommendations before each valuation exhibit second-order stochastic dominance relative to valuations from participants who do not. Hence, LLM-based recommendations leave mean valuations unchanged but compress the distribution, reducing the incidence of extreme valuations. Consistent with this pattern, LLM-based recommendations reduce the intensity of risk, complexity, and ambiguity aversion, while leaving the fraction of participants classified as averse unchanged.
The authors' abstract, as published at the source. Experimental Economics, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
General Decision SciencesDecision Sciences