activity
20212024
most citedCollective Constitutional AI: Aligning a Language Model with Public Input

73 citations · 134 across the 11 of their papers we have counts for

collaborators

11 papers

cs.CY20248 cited

Clio: Privacy-Preserving Insights into Real-World AI Use

Alex Tamkin, Miles McCain, Kunal Handa +18

How are AI assistants being used in the real world? While model providers in theory have a window into this impact via their users' data, both privacy concerns and practical challe…

cs.AI20249 cited

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Carson Denison, Monte MacDiarmid, Fazl Barez +11

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming c…

cs.AI202473 cited

Collective Constitutional AI: Aligning a Language Model with Public Input

Saffron Huang, Divya Siddarth, Liane Lovitt +4

There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collect…

cs.CL2024

Bayesian Preference Elicitation with Language Models

Kunal Handa, Yarin Gal, Ellie Pavlick +4

Aligning AI systems to users' interests requires understanding and incorporating humans' complex values and preferences. Recently, language models (LMs) have been used to gather in…

cs.LG20237 cited

Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data

Wai Tong Chung, Bassem Akoush, Pushan Sharma +9

Analysis of compressible turbulent flows is essential for applications related to propulsion, energy generation, and the environment. Here, we present BLASTNet 2.0, a 2.2 TB networ…

cs.LG20232 cited

Codebook Features: Sparse and Discrete Interpretability for Neural Networks

Alex Tamkin, Mohammad Taufeeque, Noah D. Goodman

Understanding neural networks is challenging in part because of the dense, continuous nature of their hidden states. We explore whether we can train neural networks to have hidden…