Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance

arXiv:2607.05113v2 Announce Type: replace Abstract: Imagine two users interact with the same LLM. One has been told it is the cutting-edge flagship model; the other, an older, weaker model. They walk away with markedly different ratings of its usefulness and intelligence, yet they used the same model. In a controlled study, 162 participants each used one of six LLMs from two families across three collaborative tasks, after first viewing a landing page that matched, overstated, or understated their model's true capability. This pre-interaction framing shifted user opinions and interaction behavior while task performance did not. Oversold users rated the model more favorably and used more directive prompting, while Undersold users wrote longer, more collaborative prompts. The quality of what users and the model produced together depended only on the model's true capability, not on what users were told. Participants' change in model impressions after use, measured across two impression measures, was not predicted by task performance ($\beta = -0.01$ and $0.11$, both n.s.), but by whether the model met users' expectations ($\beta = 0.47$ and $0.50$, both $p < .001$) and how confident they felt working with it ($\beta = 0.47$ and $0.36$, both $p < .001$). After interaction, users are still rating the pitch, not the product: user-elicited LLM evaluations, including the preference data driving public leaderboards, measure expectation management at least as much as the model itself.

Abstract:Imagine two users interact with the same LLM. One has been told it is the cutting-edge flagship model; the other, an older, weaker model. They walk away with markedly different ratings of its usefulness and intelligence, yet they used the same model. In a controlled study, 162 participants each used one of six LLMs from two families across three collaborative tasks, after first viewing a landing page that matched, overstated, or understated their model's true capability. This pre-interaction framing shifted user opinions and interaction behavior while task performance did not. Oversold users rated the model more favorably and used more directive prompting, while Undersold users wrote longer, more collaborative prompts. The quality of what users and the model produced together depended only on the model's true capability, not on what users were told. Participants' change in model impressions after use, measured across two impression measures, was not predicted by task performance ($\beta = -0.01$ and $0.11$, both n.s.), but by whether the model met users' expectations ($\beta = 0.47$ and $0.50$, both $p < .001$) and how confident they felt working with it ($\beta = 0.47$ and $0.36$, both $p < .001$). After interaction, users are still rating the pitch, not the product: user-elicited LLM evaluations, including the preference data driving public leaderboards, measure expectation management at least as much as the model itself.

Computation and Language (cs.CL); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC)

arXiv:2607.05113 [cs.CL]

(or arXiv:2607.05113v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.05113 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Rating the Pitch, Not the Product: User Evaluations of LLMs Reflect Expectations More Than Performance

Related coverage