95 citations · 187 across the 11 of their papers we have counts for
12 papers
Muse Spark Safety & Preparedness Report
Cristina Menghini, Peter Ney, Hamza Kwisaba +117
Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framewo…
Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
Carolina Zheng, Nicolas Beltran-Velez, Sweta Karlekar +5
Traditional topic models are effective at uncovering latent themes in large text collections. However, due to their reliance on bag-of-words representations, they struggle to captu…
Hypothesis Testing the Circuit Hypothesis in LLMs
Claudia Shi, Nicolas Beltran-Velez, Achille Nazaret +5
Large language models (LLMs) demonstrate surprising capabilities, but we do not understand how they are implemented. One hypothesis suggests that these capabilities are primarily e…
Data Augmentations for Improved (Large) Language Model Generalization
Amir Feder, Yoav Wald, Claudia Shi +2
The reliance of text classifiers on spurious correlations can lead to poor generalization at deployment, raising concerns about their use in safety-critical domains such as healthc…
Evaluating the Moral Beliefs Encoded in LLMs
Nino Scherrer, Claudia Shi, Amir Feder +1
This paper presents a case study on the design, administration, post-processing, and evaluation of surveys on large language models (LLMs). It comprises two components: (1) A stati…
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
Stephen Casper, Xander Davies, Claudia Shi +29
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of…
An Invariant Learning Characterization of Controlled Text Generation
Carolina Zheng, Claudia Shi, Keyon Vafa +2
Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor…
On the Misspecification of Linear Assumptions in Synthetic Control
Achille Nazaret, Claudia Shi, David M. Blei
The synthetic control (SC) method is a popular approach for estimating treatment effects from observational panel data. It rests on a crucial assumption that we can write the treat…
On the Assumptions of Synthetic Control Methods
Claudia Shi, Dhanya Sridhar, Vishal Misra +1
Synthetic control (SC) methods have been widely applied to estimate the causal effect of large-scale interventions, e.g., the state-wide effect of a change in policy. The idea of s…
Conformal Sensitivity Analysis for Individual Treatment Effects
Mingzhang Yin, Claudia Shi, Yixin Wang +1
Estimating an individual treatment effect (ITE) is essential to personalized decision making. However, existing methods for estimating the ITE often rely on unconfoundedness, an as…
Invariant Representation Learning for Treatment Effect Estimation
Claudia Shi, Victor Veitch, David Blei
The defining challenge for causal inference from observational data is the presence of `confounders', covariates that affect both treatment assignment and the outcome. To address t…
Adapting Neural Networks for the Estimation of Treatment Effects
Claudia Shi, David M. Blei, Victor Veitch
This paper addresses the use of neural networks for the estimation of treatment effects from observational data. Generally, estimation proceeds in two stages. First, we fit models…