We have 3 of 3 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Order-dependent activation statistics are often interpreted as evidence of interaction, but that interpretation can be confounded by where interventions enter the network. We introduce a no-fit site-asymmetry audit. For a twice-differentiable readout, the open-path order-swap decomposes into a canonical additive respon...
ModaLens, a paired image-swap audit, measures how report availability changes image sensitivity and limits conclusions about visual correctness; the direction replicates in two further model lineages.
It is asked whether committees of language-model agents deliberating on a shared workspace can be gamed by shortcuts, cues a benchmark rewards but a clinician would ignore, and what games a committee is social plausibility.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
