OpenReview
.net
OpenReview
.net
Login
OpenReview
.net
Login
Martín Soto
Joined
September 2024
Names
Martín Soto
(Preferred)
Emails
****@gmail.com
(Confirmed)
Personal Links
Google Scholar
Career & Education History
MS student
Mathematics,
Universitat de Barcelona
(ub.edu)
2022
–
2024
Advisors, Relations & Conflicts
No relations added
Expertise
No areas of expertise listed
Publications
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
Jan Betley
,
Daniel Chee Hian Tan
,
Niels Warncke
,
Anna Sztyber-Betley
,
Xuchan Bao
,
Martín Soto
,
Nathan Labenz
,
Owain Evans
ICLR 2025 FM-Wild Workshop
Readers:
Everyone
Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
Jan Betley
,
Daniel Chee Hian Tan
,
Niels Warncke
,
Anna Sztyber-Betley
,
Xuchan Bao
,
Martín Soto
,
Nathan Labenz
,
Owain Evans
ICML 2025 oral
Readers:
Everyone
Language Models Can Articulate Their Implicit Goals
Jan Betley
,
Xuchan Bao
,
Martín Soto
,
Anna Sztyber-Betley
,
James Chua
,
Owain Evans
SafeGenAi Poster
Readers:
Everyone
Tell me about yourself: LLMs are aware of their learned behaviors
Jan Betley
,
Xuchan Bao
,
Martín Soto
,
Anna Sztyber-Betley
,
James Chua
,
Owain Evans
ICLR 2025 Spotlight
Readers:
Everyone
Co-Authors
Anna Sztyber-Betley
Daniel Chee Hian Tan
James Chua
Jan Betley
Nathan Labenz
Niels Warncke
Owain Evans
Xuchan Bao