Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Language Models Act on Hidden Valence
Cameron Berg, Caspar Kaiser
Language models describe some internal states as good and others as bad. But whether models have a stake in them is an open question. Simply asking models is unlikely to be informa…
cs.CL2026
No Reliable Evidence of Self-Reported Sentience in Small Large Language Models
Caspar Kaiser, Sean Enderby
Whether language models possess sentience has no empirical answer. But whether they believe themselves to be sentient can, in principle, be tested. We do so by querying several ope…