Speech anonymization has focused on the acoustic signal, leaving open how much speaker information the transcribed words themselves retain. In this work, we study pairwise speaker and demographic-attribute verification from transcribed speech. We introduce SPARC (Spoken Profile Authorship Recognition Corpus), a benchma...
Efthymios Tsaprazlis, Bo-Wen Yi, Tian-Tian Feng et al.· 0 citations
This work benchmarks 41 open-weight LLMs across six behavioral economics games and shows that game-derived cooperative profiles robustly predict downstream performance in AI-for-Science tasks, indicating that cooperative disposition is a distinct, measurable property of LLMs not reducible to general ability.
Shivani Kumar, A. Bharathwaj, David Jurgens· arXiv.org· 1 citation
HARISSA fine-tunes the model so that both states predict correctness, then makes both decisions with one policy that cascades through the ways of answering from cheapest to most expensive, skipping a way the prefill state predicts will fail and deferring the query when the answer it stops with is predicted wrong.
Kenan Alkiek, Moontae Lee, David Jurgens et al.· 0 citations
A controlled multilingual evaluation across six geographically, culturally, and linguistically diverse languages reveals a central disconnect in multilingual moral reasoning: language changes models'moral judgments and the training evidence associated with their reasoning, but does not correspondingly localize the mora...
