arXiv subjects

Caspar Kaiser

Publications and source records attributed to Caspar Kaiser.

3 recordsLinked to original sources

arXiv2026

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models

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 open-weights models about their own consciousness, and then verifying their responses using classifiers trained on internal activations. We draw upon three model families (Qwen, Llama, GPT-OSS) ranging from 0.6 billion to 70 billion parameters, approximately 50 questions about consciousness and subjective experience, and three classification methods from the interpretability literature. First, we find that models consistently deny being sentient: they attribute consciousness to humans but not to themselves. Second, classifiers trained to detect underlying beliefs - rather than mere outputs - provide no clear evidence that these denials are untruthful. Third, within the Qwen family, larger models deny sentience more confidently than smaller ones. These findings contrast with recent work suggesting that models harbour latent beliefs in their own consciousness.

cs.CL↗

arXiv2026

Measuring the Unmeasurable? Systematic Evidence on Scale Transformations in Subjective Survey Data

Ordered response scales are ubiquitous in economics, but their interpretation rests on an untested assumption: that numerical labels reflect equal psychological intervals. We develop a framework to quantify how relaxing this assumption affects empirical results. Using new experimental evidence, we show that scale use is only mildly non-linear. Replicating over 40,000 estimates from more than 80 papers, we find that coefficient signs and significance are largely robust, but relative magnitudes are not. Even modest non-linearities generate substantial variation in implied trade-offs.

econ.GN↗

arXiv2022

Human Wellbeing and Machine Learning

There is a vast literature on the determinants of subjective wellbeing. International organisations and statistical offices are now collecting such survey data at scale. However, standard regression models explain surprisingly little of the variation in wellbeing, limiting our ability to predict it. In response, we here assess the potential of Machine Learning (ML) to help us better understand wellbeing. We analyse wellbeing data on over a million respondents from Germany, the UK, and the United States. In terms of predictive power, our ML approaches do perform better than traditional models. Although the size of the improvement is small in absolute terms, it turns out to be substantial when compared to that of key variables like health. We moreover find that drastically expanding the set of explanatory variables doubles the predictive power of both OLS and the ML approaches on unseen data. The variables identified as important by our ML algorithms - $i.e.$ material conditions, health, and meaningful social relations - are similar to those that have already been identified in the literature. In that sense, our data-driven ML results validate the findings from conventional approaches.

econ.EM↗