On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings

Peter A. Jansen, Kelly Smith, Dan Moreno, Huitzilin Ortiz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Building compositional explanations requires models to combine two or more facts that, together, describe why the answer to a question is correct. Typically, these “multi-hop” explanations are evaluated relative to one (or a small number of) gold explanations. In this work, we show these evaluations substantially underestimate model performance, both in terms of the relevance of included facts, as well as the completeness of model-generated explanations, because models regularly discover and produce valid explanations that are different than gold explanations. To address this, we construct a large corpus of 126k domain-expert (science teacher) relevance ratings that augment a corpus of explanations to standardized science exam questions, discovering 80k additional relevant facts not rated as gold. We build three strong models based on different methodologies (generation, ranking, and schemas), and empirically show that while expert-augmented ratings provide better estimates of explanation quality, both original (gold) and expert-augmented automatic evaluations still substantially underestimate performance by up to 36% when compared with full manual expert judgements, with different models being disproportionately affected. This poses a significant methodological challenge to accurately evaluating explanations produced by compositional reasoning models.

Original languageEnglish (US)
Title of host publicationEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages7529-7542
Number of pages14
ISBN (Electronic)9781955917094
StatePublished - 2021
Event2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021 - Virtual, Punta Cana, Dominican Republic
Duration: Nov 7 2021Nov 11 2021

Publication series

NameEMNLP 2021 - 2021 Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021
Country/TerritoryDominican Republic
CityVirtual, Punta Cana
Period11/7/2111/11/21

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Fingerprint

Dive into the research topics of 'On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings'. Together they form a unique fingerprint.

Cite this