# Diversify and Disambiguate: Learning From Underspecified Data

Source: [Diversify and Disambiguate: Learning From Underspecified Data](<https://www.sota2.com/research/paper/68fa6e981e209131cea40f77>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:01:51.507Z

Authors: Yoonho Lee, Huaxiu Yao, Chelsea Finn

Published: 2022-02-07T18:59:06.000Z

## Abstract

Many datasets are underspecified: there exist multiple equally viable solutions to a given task. Underspecification can be problematic for methods that learn a single hypothesis because different functions that achieve low training loss can focus on different predictive features and thus produce widely varying predictions on out-of-distribution data. We propose DivDis, a simple two-stage framework that first learns a diverse collection of hypotheses for a task by leveraging unlabeled data from the test distribution. We then disambiguate by selecting one of the discovered hypotheses using minimal additional supervision, in the form of additional labels or inspection of function visualization. We demonstrate the ability of DivDis to find hypotheses that use robust features in image classification and natural language processing problems with underspecification.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2202.03418>)

[PDF](<https://arxiv.org/pdf/2202.03418.pdf>)