DISCO: Distilling Counterfactuals with Large Language Models

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Despite the widespread use of self-tracking technologies for promoting personal wellbeing, there is limited research on the monitoring of intimate data, particularly urine. To shed light on the design possibilities within this unexplored domain we designed ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Numerous conductor designs for pulsed magnets based on High Temperature Superconductors (HTS), featuring stacks of tapes are currently being proposed. A major contribution to the AC losses is expected to be given by hysteresis losses. Several numerical mod ...

We formalize the problem of prompt compression for large language models (LLMs) and present a framework to unify token-level prompt compression methods which create hard prompts for black-box models. We derive the distortion-rate function for this setup as ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

Masonry aggregates, which emerged as layouts of cities and villages became denser, make up historical centres all over the world. In these aggregates, neighbouring structures may share structural walls that are joined at the interfaces by mortar or interlo ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

A range of behavioral and contextual factors, including eating and drinking behavior, mood, social context, and other daily activities, can significantly impact an individual's quality of life and overall well-being. Therefore, inferring everyday life aspe ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

The 70 kDa heat shock protein (Hsp70) chaperones control protein homeostasis in all ATP-containing cellular compartments. J-domain proteins (JDPs) coevolved with Hsp70s to trigger ATP hydrolysis and catalytically upload various substrate polypeptides in ne ...

Generative language models (LMs) have become omnipresent across data science. For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted. LM performance has consistently be ...

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ...

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

This paper proposes a data-driven control design method for nonlinear systems that builds upon the Koopman operator framework. In particular, the Koopman operator is used to lift the nonlinear dynamics to a higher-dimensional space where the so-called obse ...

Dynamic downscaling of atmospheric forcing data to the hectometer resolution has shown increases in accuracy for landsurface models, but at great computational cost. Here we present a validation of a novel intermediate complexity atmospheric model, HICAR, ...

DISCO: Distilling Counterfactuals with Large Language Models

Chat with Graph Search

Designing for Intimate Wellbeing: Aidee, a Qualitative Approach To Urine Home Monitoring

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Validation and Application of Hysteresis Loss Model for HTS Stacks and Conductors for Fusion Applications

Fundamental Limits of Prompt Compression: A Rate- Distortion Framework for Black-Box Language Models

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Seismic Testing of Adjacent Interacting Masonry Structures – Analysis of a Blind Prediction

Random matrix methods for high-dimensional machine learning models

Generalization and Personalization of Machine Learning for Multimodal Mobile Sensing in Everyday Life

Robust NAS under adversarial training: benchmark, theory, and beyond

Autorepression of yeast Hsp70 cochaperones by intramolecular interactions involving their J-domains

Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling

Augmenting large language models with chemistry tools

Extensions of Peer Prediction Incentive Mechanisms

Data-Driven Control Synthesis using Koopman Operator: A Robust Approach

Intermediate complexity atmospheric modeling in complex terrain: is it right?