4 citations · 12 across the 9 of their papers we have counts for
10 papers
Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
Sweta Karlekar, Carolina Zheng, Magnus Saebo +5
Many applications seek to optimize LLM outputs at test time by iteratively proposing, scoring, and refining candidates over a discrete output space. Existing methods use a calibrat…
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…
Extremely Greedy Equivalence Search
Achille Nazaret, David Blei
The goal of causal discovery is to learn a directed acyclic graph from data. One of the most well-known methods for this problem is Greedy Equivalence Search (GES). GES searches fo…
Can Generative AI Solve Your In-Context Learning Problem? A Martingale Perspective
Andrew Jesson, Nicolas Beltran-Velez, David Blei
This work is about estimating when a conditional generative model (CGM) can solve an in-context learning (ICL) problem. An in-context learning (ICL) problem comprises a CGM, a data…
Multi-environment Topic Models
Dominic Sobhani, Amir Feder, David Blei
Probabilistic topic models are a powerful tool for extracting latent themes from large text datasets. In many text datasets, we also observe per-document covariates (e.g., source,…
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…
Treeffuser: Probabilistic Predictions via Conditional Diffusions with Gradient-Boosted Trees
Nicolas Beltran-Velez, Alessandro Antonio Grande, Achille Nazaret +2
Probabilistic prediction aims to compute predictive distributions rather than single point predictions. These distributions enable practitioners to quantify uncertainty, compute ri…
Estimating the Hallucination Rate of Generative AI
Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu +5
This paper presents a method for estimating the hallucination rate for in-context learning (ICL) with generative AI. In ICL, a conditional generative model (CGM) is prompted with a…
Stable Differentiable Causal Discovery
Achille Nazaret, Justin Hong, Elham Azizi +1
Inferring causal relationships as directed acyclic graphs (DAGs) is an important but challenging problem. Differentiable Causal Discovery (DCD) is a promising approach to this prob…
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…