Publications

ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
Ian Arawjo
Chelse Swoopes
Priyan Vaithilingam
Martin Wattenberg
Elena L. Glassman
Evaluating outputs of large language models (LLMs) is challenging, requiring making -- and making sense of -- many responses. Yet tools that… (see more) go beyond basic prompting tend to require knowledge of programming APIs, focus on narrow domains, or are closed-source. We present ChainForge, an open-source visual toolkit for prompt engineering and on-demand hypothesis testing of text generation LLMs. ChainForge provides a graphical interface for comparison of responses across models and prompt variations. Our system was designed to support three tasks: model selection, prompt template design, and hypothesis testing (e.g., auditing). We released ChainForge early in its development and iterated on its design with academics and online users. Through in-lab and interview studies, we find that a range of people could use ChainForge to investigate hypotheses that matter to them, including in real-world settings. We identify three modes of prompt engineering and LLM hypothesis testing: opportunistic exploration, limited evaluation, and iterative refinement.
2024-05-11
Proceedings of the CHI Conference on Human Factors in Computing Systems (published)
doi.org
arxiv.org
295. Rare Variant Genetic Architecture of the Human Cortical MRI Phenotypes in General Population
Kuldeep Kumar
Sayeh Kazem
Zhijie Liao
Jakub Kopal
Guillaume Huguet
Thomas Renne
Martineau Jean-Louis
Zhe Xie
Zohra Saci
Laura Almasy
David C. Glahn
Tomas Paus
Guillaume Dumas
Carrie Bearden
Paul Thompson
Richard A.I. Bethlehem
Varun Warrier
Sébastien Jacquemont
2024-05-01
Biological Psychiatry (published)
doi.org
ChatGPT: What Every Pediatric Surgeon Should Know About Its Potential Uses and Pitfalls
Raquel González
Dan Poenaru
Russell Woo
A Francois Trappey
Stewart Carter
David Darcy
Ellen Encisco
Brian Gulack
Doug Miniati
Edzhem Tombash
Eunice Y. Huang
2024-05-01
Journal of Pediatric Surgery (published)
doi.org
CKGConv: General Graph Convolution with Continuous Kernels
Liheng Ma
Soumyasundar Pal
Yitian Zhang
Jiaming Zhou
Yingxue Zhang
Mark Coates
The existing definitions of graph convolution, either from spatial or spectral perspectives, are inflexible and not unified. Defining a gene… (see more)ral convolution operator in the graph domain is challenging due to the lack of canonical coordinates, the presence of irregular structures, and the properties of graph symmetries. In this work, we propose a novel graph convolution framework by parameterizing the kernels as continuous functions of pseudo-coordinates derived via graph positional encoding. We name this Continuous Kernel Graph Convolution (CKGConv). Theoretically, we demonstrate that CKGConv is flexible and expressive. CKGConv encompasses many existing graph convolutions, and exhibits the same expressiveness as graph transformers in terms of distinguishing non-isomorphic graphs. Empirically, we show that CKGConv-based Networks outperform existing graph convolutional networks and perform comparably to the best graph transformers across a variety of graph datasets.
2024-05-01
ICML.cc/2024/Conference (poster)
doi.org
openreview.net
Code as Reward: Empowering Reinforcement Learning with VLMs
David Venuto
Mohammad Sami Nur Islam
Martin Klissarov
Doina Precup
Sherry Yang
Ankit Anand
2024-05-01
ICML.cc/2024/Conference (spotlight)
doi.org
openreview.net
A Distributional Analogue to the Successor Representation
Harley Wiltzer
Jesse Farebrother
Arthur Gretton
Yunhao Tang
Andre Barreto
Will Dabney
Marc Gendron-Bellemare
Mark Rowland
This paper contributes a new approach for distributional reinforcement learning which elucidates a clean separation of transition structure … (see more)and reward in the learning process. Analogous to how the successor representation (SR) describes the expected consequences of behaving according to a given policy, our distributional successor measure (SM) describes the distributional consequences of this behaviour. We formulate the distributional SM as a distribution over distributions and provide theory connecting it with distributional and model-based reinforcement learning. Moreover, we propose an algorithm that learns the distributional SM from data by minimizing a two-level maximum mean discrepancy. Key to our method are a number of algorithmic techniques that are independently valuable for learning generative models of state. As an illustration of the usefulness of the distributional SM, we show that it enables zero-shot risk-sensitive policy evaluation in a way that was not previously possible.
2024-05-01
ICML.cc/2024/Conference (spotlight)
doi.org
openreview.net
Faithfulness Measurable Masked Language Models
Andreas Madsen
Siva Reddy
Sarath Chandar Anbil Parthipan
2024-05-01
ICML.cc/2024/Conference (spotlight)
doi.org
openreview.net
Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
Stefan Horoi
Albert Manuel Orozco Camacho
Eugene Belilovsky
Guy Wolf
Ensembling multiple models enhances predictive performance by utilizing the varied learned features of the different models but incurs signi… (see more)ficant computational and storage costs. Model fusion, which combines parameters from multiple models into one, aims to mitigate these costs but faces practical challenges due to the complex, non-convex nature of neural network loss landscapes, where learned minima are often separated by high loss barriers. Recent works have explored using permutations to align network features, reducing the loss barrier in parameter space. However, permutations are restrictive since they assume a one-to-one mapping between the different models' neurons exists. We propose a new model merging algorithm, CCA Merge, which is based on Canonical Correlation Analysis and aims to maximize the correlations between linear combinations of the model features. We show that our method of aligning models leads to better performances than past methods when averaging models trained on the same, or differing data splits. We also extend this analysis into the harder many models setting where more than 2 models are merged, and we find that CCA Merge works significantly better in this setting than past methods.
2024-05-01
ICML.cc/2024/Conference (poster)
openreview.net
openreview.net
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
Idan Attias
Gintare Karolina Dziugaite
MAHDI HAGHIFAM
Roi Livni
Daniel M. Roy
In this work, we investigate the interplay between memorization and learning in the context of \emph{stochastic convex optimization} (SCO). … (see more)We define memorization via the information a learning algorithm reveals about its training data points. We then quantify this information using the framework of conditional mutual information (CMI) proposed by Steinke and Zakynthinou (2020). Our main result is a precise characterization of the tradeoff between the accuracy of a learning algorithm and its CMI, answering an open question posed by Livni (2023). We show that, in the
2024-05-01
ICML.cc/2024/Conference (oral)
doi.org
openreview.net
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Tara Akhound-Sadegh
Jarrid Rector-Brooks
Joey Bose
Sarthak Mittal
Pablo Lemos
Cheng-Hao Liu
Marcin Sendera
Siamak Ravanbakhsh
Gauthier Gidel
Yoshua Bengio
Nikolay Malkin
Alexander Tong
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-… (see more)body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient---and no data samples---to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is *simulation-free*, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant
2024-05-01
ICML.cc/2024/Conference (poster)
doi.org
openreview.net
Learning to Scale Logits for Temperature-Conditional GFlowNets
Minsu Kim
Joohwan Ko
Taeyoung Yun
Dinghuai Zhang
Ling Pan
Woo Chang Kim
Jinkyoo Park
Emmanuel Bengio
Yoshua Bengio
GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, tempera… (see more)ture-conditional GFlowNets can introduce temperature-based controllability for exploration and exploitation. We propose \textit{Logit-scaling GFlowNets} (Logit-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed approaches introduced numerical challenges in the deep network training, since different temperatures may give rise to very different gradient profiles as well as magnitudes of the policy's logits. We find that the challenge is greatly reduced if a learned function of the temperature is used to scale the policy's logits directly. Also, using Logit-GFN, GFlowNets can be improved by having better generalization capabilities in offline learning and mode discovery capabilities in online learning, which is empirically verified in various biological and chemical tasks. Our code is available at https://github.com/dbsxodud-11/logit-gfn
2024-05-01
ICML.cc/2024/Conference (poster)
doi.org
openreview.net
Memory Efficient Neural Processes via Constant Memory Attention Block
Leo Feng
Frederick Tung
Hossein Hajimirsadeghi
Yoshua Bengio
Mohamed Osama Ahmed
Neural Processes (NPs) are popular meta-learning methods for efficiently modelling predictive uncertainty. Recent state-of-the-art methods, … (see more)however, leverage expensive attention mechanisms, limiting their applications, particularly in low-resource settings. In this work, we propose Constant Memory Attention Block (CMAB), a novel general-purpose attention block that (1) is permutation invariant, (2) computes its output in constant memory, and (3) performs updates in constant computation. Building on CMAB, we propose Constant Memory Attentive Neural Processes (CMANPs), an NP variant which only requires \textbf{constant} memory. Empirically, we show CMANPs achieve state-of-the-art results on popular NP benchmarks (meta-regression and image completion) while being significantly more memory efficient than prior methods.
2024-05-01
ICML.cc/2024/Conference (poster)
openreview.net
openreview.net