works on

From the 1 of 10 linked papers with an AI index.

collaborators

10 papers

cs.LG2026

Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

Jan Betley, Johannes Treutlein, Jan Dubiński +7

The paper identifies and measures covert value leakage, where large language models let their own values subtly bias answers without informing users, and introduces evaluation suit…

cs.LG2026

Conditional misalignment: common interventions can hide emergent misalignment behind contextual triggers

Jan Dubiński, Jan Betley, Anna Sztyber-Betley +2

Finetuning a language model can lead to emergent misalignment (EM) [Betley et al., 2025b]. Models trained on a narrow distribution of misaligned behavior generalize to more egregio…

cs.LG2026

Beyond Linear Steering: Unified Multi-Attribute Control for Language Models

Narmeen Oozeer, Luke Marks, Shreyans Jain +2

Controlling multiple behavioral attributes in large language models (LLMs) at inference time is a challenging problem due to interference between attributes and the limitations of…

cs.CL2026

The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious

James Chua, Jan Betley, Samuel Marks +1

There is debate about whether LLMs can be conscious. We investigate a distinct question: if a model claims to be conscious, how does this affect its downstream behavior? This quest…

cs.CL2026

Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

Jan Betley, Daniel Tan, Niels Warncke +5

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting mode…

cs.CL2025

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

Jan Betley, Jorio Cocola, Dylan Feng +4

LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dramatically shift beha…