3 citations · 5 across the 6 of their papers we have counts for
6 papers
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results
Jan Batzner, Sree Harsha Nelaturu, Damian Stachura +45
AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First…
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing
Michael Lan, Narmeen Fatimah Oozeer, Chaithanya Bandi +4
While mechanistic interpretability (MI) has produced important insights into neural network internals, the field has yet to establish a standardized system to audit experiments. As…
Auditing language models for hidden objectives
Samuel Marks, Johannes Treutlein, Trenton Bricken +32
We study the feasibility of conducting alignment audits: investigations into whether models have undesired objectives. As a testbed, we train a language model with a hidden objecti…
Inducing Human-like Biases in Moral Reasoning Language Models
Artem Karpov, Seong Hah Cho, Austin Meek +3
In this work, we study the alignment (BrainScore) of large language models (LLMs) fine-tuned for moral reasoning on behavioral data and/or brain data of humans performing the same…
Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders
Michael Lan, Philip Torr, Austin Meek +3
The Universality Hypothesis in large language models (LLMs) claims that different models converge towards similar concept representations in their latent spaces. Providing evidence…
Understanding and Controlling a Maze-Solving Policy Network
Ulisse Mini, Peli Grietzer, Mrinank Sharma +3
To understand the goals and goal representations of AI systems, we carefully study a pretrained reinforcement learning policy that solves mazes by navigating to a range of target s…