Search Results for author:
Found 14 papers, 6 papers with code
Auditing language models for hidden objectives
First, we conduct a blind auditing game where four teams, unaware of the model's hidden objective or training, investigate it for concerning behaviors and their causes.
Factorio Learning Environment
Large Language Models (LLMs) are rapidly saturating existing benchmarks, necessitating new open-ended evaluations.
Multi-Agent Risks from Advanced AI
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity.
Alignment faking in large language models
Explaining this gap, in almost all cases where the model complies with a harmful query from a free user, we observe explicit alignment-faking reasoning, with the model stating it is strategically answering harmful queries in training to preserve its preferred harmlessness behavior out of training.
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them.
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities; however, they still struggle to perform well in complex, dynamic environments.
Language Models Learn to Mislead Humans via RLHF
On a question-answering task (QuALITY) and programming task (APPS), RLHF makes LMs better at convincing our subjects but not at completing the task correctly.
Debating with More Persuasive LLMs Leads to More Truthful Answers
In anticipation of this, we ask: can weaker models assess the correctness of stronger models?
Scaling Opponent Shaping to High Dimensional Games
In multi-agent settings with mixed incentives, methods developed for zero-sum games have been shown to lead to detrimental outcomes.
Leading the Pack: N-player Opponent Shaping
We evaluate on over 4 different environments, varying the number of players from 3 to 5, and demonstrate that model-based OS methods converge to equilibrium with better global welfare than naive learning.
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research.
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Open-ended learning methods that automatically generate a curriculum of increasingly challenging tasks serve as a promising avenue toward generally capable reinforcement learning agents.
The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs
We present our findings as the starting point for further research into evaluating how LLMs interpret language in context and to drive the development of more pragmatic and useful models of human discourse.
Considering Race a Problem of Transfer Learning
We take the novel approach of considering race as a boundary for transfer learning in both the task (facial classification) and the domain (synthesis over distinct datasets).
