GF
Guido Freire
cs.AIcs.CLcs.LG
On Valency
published · living versionsW_4d9v7zp6·v1 · currentpublished
Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment
with Ariana M. Villegas-Suarez, Sohan Venkatesh, Bartosz Cywiński
1 version
W_n6rj4p5u·v1published
Preprints & journals
2 papers in the corpus · 2026Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not2610.28539v1 · Maria Victoria Carro, Denise Alejandra Mester, Facundo Nieto et al.2026 · 0 citationsarXivon Valency
DrugBench: Evaluating AI Control Protocols for Medication Harm Mitigation2606.20663v1 · Guido Freire, Agust'in Mart'inez-Sun'e, Viviana Cotik2026 · 0 citationsarXiv
Career total: 6 works. 2 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.