My confusion with this paper is that nowhere in the paper or the many media posts about this paper do the authors show the confounding of this stochasticity on fact-checking -- how do we know that the inconsistency came from hallucination and not stochasticity? Without this causal analysis, I am not sure if their result has any technical footing whatsoever -- curious to know if anyone here has read this paper or has expertise/experience in the area of hallucination checks and can shed light on my confusion here
My confusion with this paper is that nowhere in the paper or the many media posts about this paper do the authors show the confounding of this stochasticity on fact-checking -- how do we know that the inconsistency came from hallucination and not stochasticity? Without this causal analysis, I am not sure if their result has any technical footing whatsoever -- curious to know if anyone here has read this paper or has expertise/experience in the area of hallucination checks and can shed light on my confusion here