output
20212025
most citedEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

25 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions

5 papers

cs.CL2025★ 25 cited

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…

stat.ML2023★ 3 cited

Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks

Keiichi Tamai, Tsuyoshi Okubo, Truong Vinh Truong Duy +2

We demonstrate that conventional artificial deep neural networks operating near the phase boundary of the signal propagation dynamics, also known as the edge of chaos, exhibit univ…

quant-ph2022

Quantum Neural Networks for a Supply Chain Logistics Application

Randall Correll, Sean J. Weinberg, Fabio Sanches +2

Problem instances of a size suitable for practical applications are not likely to be addressed during the noisy intermediate-scale quantum (NISQ) period with (almost) pure quantum…

cs.LG2022★ 1 cited

Reinforcement Learning for Multi-Truck Vehicle Routing Problems

Joshua Levin, Randall Correll, Takanori Ide +3

Deep reinforcement learning (RL) has been shown to be effective in producing approximate solutions to some vehicle routing problems (VRPs), especially when using policies generated…

quant-ph2021★ 18 cited

Short Quantum Circuits in Reinforcement Learning Policies for the Vehicle Routing Problem

Fabio Sanches, Sean Weinberg, Takanori Ide +1

Quantum computing and machine learning have potential for symbiosis. However, in addition to the hardware limitations from current devices, there are still basic issues that must b…