CoChat

Can NLI Models Verify QA Systems’ Predictions?

Open access
Chen, Jifan, Choi, Eunsol, Durrett, Greg · 2021 · Findings of the Association for Computational Linguistics: EMNLP 2021
Cited by 47

The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.

Abstract

To build robust question answering systems, we need the ability to verify whether answers to questions are truly correct, not just "good enough" in the context of imperfect QA datasets.We explore the use of natural language inference (NLI) as a way to achieve this goal, as NLI inherently requires the premise (document context) to contain all necessary information to support the hypothesis (proposed answer to the question).We leverage large pretrained models and recent prior datasets to construct powerful question conversion and decontextualization modules, which can reformulate QA instances as premise-hypothesis pairs with very high reliability.Then, by combining standard NLI datasets with NLI examples automatically derived from QA training data, we can train NLI models to evaluate QA systems' proposed answers.We show that our approach improves the confidence estimation of a QA model across different domains.Careful manual analysis over the predictions of our NLI model shows that it can further identify cases where the QA model produces the right answer for the wrong reason, i.e., when the answer sentence does not address all aspects of the question.Context: The first season of the fantasy comedy television series The Good Place, created by Michael Schur, aired … The series focuses on Eleanor Shellstrop (Kristen Bell) , a woman who wakes up in the afterlife and is introduced by Michael (Ted Danson) to a Heaven-like utopia he designed … Question: Who plays the bad guy in the Good Place?Answer: Ted Danson Premise: The series The Good Place focuses on Eleanor Shellstrop (Kristen Bell) , a woman who wakes up in the afterlife and is introduced by Michael (Ted Danson) to a Heaven-like utopia he designed.Hypothesis: Ted Danson plays the bad guy in The Good Place.Decontextualization of the answer sentence Question conversion to a declarative statement NLI ModelAnswer is correct, but information about Michael being the bad guy is missing in the premiseNot entailed, answer rejected

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.18653/v1/2021.findings-emnlp.324

Cites

20 of 20 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 20 references

Cited by

See all 47

Metadata

Authors
Chen, J., Choi, E., & Durrett, G.
Venue
Findings of the Association for Computational Linguistics: EMNLP 2021
Published
2021
Pages
3841-3854
OpenAlex
W3213356154
Cited by
47
References
20
FWCI
4.57
Type
conference paper
Language
en
Open access
gold

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Can NLI Models Verify QA Systems’ Predictions? https://app.cochat.ai/papers/10.18653/v1/2021.findings-emnlp.324
The paper
Chen, J., Choi, E., & Durrett, G. (2021). Can NLI Models Verify QA Systems’ Predictions? Findings of the Association for Computational Linguistics: EMNLP 2021. https://doi.org/10.18653/v1/2021.findings-emnlp.324

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.