DISCO: Distilling Counterfactuals with Large Language Models
Graph Chatbot
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.
Due to daylight variability, a design cannot be thoroughly assessed using single-moment simulations, which is why we need dynamic performance metrics like Daylight Autonomy and Useful Daylight Illuminance. Going one step further, the annual variation in pe ...
This document summarizes adaptation experiments done on French MediaParl corpus and other French corpora. Baseline adaptation techniques are briefly presented and evaluated in the MediaParl task for speaker adaptation, speaker adaptive training, database c ...
Airlines schedules are built such as to maximize expected profit. Such schedules turn out to be more sensitive to delays and are hence unstable. The trend has thus evolved towards robust schedules, trading off between sensitivity with respect to disruption ...
Lausanne-Morges agglomeration will experiment strong increases in the number of inhabitants and jobs until 2020. The additional trips generated by these increases will have to be carried out in a larger proportion by soft mobility and transit. There are ma ...
Domain language model adaptation consists in re-estimating probabilities of a baseline LM in order to better match the specifics of a given broad topic of interest. To do so, a common strategy is to retrieve adaptation texts from the Web based on a given d ...
Although there exists a large body of work on efficient data collection in sensor networks, the vast majority of proposed techniques have not been implemented on real networks or thoroughly studied on real data. As algorithm performance is highly dependent ...
This paper presents a system for the offline recognition of large vocabulary unconstrained handwritten texts. The only assumption made about the data is that it is written in English. This allows the application of Statistical Language Models in order to i ...
This paper presents a system for the offline recognition of large vocabulary unconstrained handwritten texts. The only assumption made about the data is that it is written in English. This allows the application of Statistical Language Models in order to i ...
In a society which produces and consumes an ever increasing amount of information, methods which can make sense out of al1 this data become of crucial importance. Machine learning tries to develop models which can make the information load accessible. Thre ...
Domain language model adaptation consists in re-estimating probabilities of a baseline LM in order to better match the specifics of a given broad topic of interest. To do so, a common strategy is to retrieve adaptation texts from the Web based on a given d ...