Using contradictions improves question answering systems
Not on the map. Why?
Abstract (arXiv)
This work examines the use of contradiction in natural language inference (NLI) for question answering (QA). Typically, NLI systems help answer questions by determining if a potential answer is entailed (supported) by some background context. But is it useful to also determine if an answer contradicts the context? We test this in two settings, multiple choice and extractive QA, and find that systems that incorporate contradiction can do slightly better than entailment-only systems on certain datasets. However, the best performances come from using contradiction, entailment, and QA model confidence scores together. This has implications for the deployment of QA systems in domains such as medicine and science where safety is an issue.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 51 references that are in the map. First posted on arXiv 28 Sep 2022.
Builds on
32 of 51 references.
References · 32
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
- 2022Survey of Hallucination in Natural Language Generationcited by 2,056
- 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
- 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
20 more
- 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 851
- 2019Adversarial NLI: A New Benchmark for Natural Language Understandingcited by 798
- 2017Crowdsourcing Multiple Choice Science Questionscited by 742
- 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
- 2019Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoningcited by 281
- 2019QASC: A Dataset for Question Answering via Sentence Compositioncited by 248
- 2020Selective Question Answering under Domain Shiftcited by 228
- 2019MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehensioncited by 183
- 2019DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehensioncited by 156
- 2018Transforming Question Answering Datasets Into Natural Language Inference Datasetscited by 99
- 2020I like fish, especially dolphins: Addressing Contradictions in Dialogue Modelingcited by 68
- 2021Can NLI Models Verify QA Systems' Predictions?cited by 46
- 2022Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusterscited by 44
- 2019Generating Persona Consistent Dialogues by Exploiting Natural Language Inferencecited by 33
- 2018MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledgecited by 30
- 2019MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participantscited by 20
- 2021WikiContradiction: Detecting Self-Contradiction Articles on Wikipediacited by 17
- 2019Repurposing Entailment for Multi-Hop Question Answering Taskscited by 10
- 2021What Would it Take to get Biomedical QA Systems into Practice?cited by 7
- 2020Using Natural Language Relations between Answer Choices for Machine Comprehensioncited by 1
Built on by
Not cited yet.