activity
20242026
collaborators

6 papers

cs.LG2026

Out-of-Distribution Generalization of Risk Aversion in Language Models

Kristina Zhang, Junior Chinomso Okoroafor, Benjamin Maltbie +3

Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned. Misaligned but risk-averse AIs would tend to prefer low-risk, low-rewa…

cs.LG2026

Spurious Correlation Learning in Preference Optimization: Mechanisms, Consequences, and Mitigation via Tie Training

Christian Moya, Alex Semendinger, Guang Lin +1

Preference learning methods like Direct Preference Optimization (DPO) are known to induce reliance on spurious correlations, leading to sycophancy and length bias in today's langua…

cs.AI2026

Towards Shutdownable Agents: Generalizing Stochastic Choice in RL Agents and LLMs

Carissa Cullen, Harry Garland, Alexander Roman +3

Misaligned artificial agents might resist shutdown. One proposed solution is to train agents to lack preferences between different-length trajectories. The Discounted Reward for Sa…

cs.AI2025

Shutdownable Agents through POST-Agency

Elliott Thornley

Many fear that future artificial agents will resist shutdown. I present an idea - the POST-Agents Proposal - for ensuring that doesn't happen. I propose that we train agents to sat…

cs.LG2025

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

cs.AI2024

Towards Shutdownable Agents via Stochastic Choice

Elliott Thornley, Alexander Roman, Christos Ziakas +2

The POST-Agents Proposal (PAP) is an idea for ensuring that advanced artificial agents never resist shutdown. A key part of the PAP is using a novel `Discounted Reward for Same-Len…