mlsanityData to 14 Oct 2026

Discrepancy Detection at the Data Level: Toward Consistent Multilingual Question Answering

arXiv 2510.11928 ↗First posted 13 Oct 2025cs.CL cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

Multilingual question answering (QA) systems must ensure factual consistency across languages, especially for objective queries such as What is jaundice?, while also accounting for cultural variation in subjective responses. We propose MIND, a user-in-the-loop fact-checking pipeline to detect factual and cultural discrepancies in multilingual QA knowledge bases. MIND highlights divergent answers to culturally sensitive questions (e.g., Who assists in childbirth?) that vary by region and context. We evaluate MIND on a bilingual QA system in the maternal and infant health domain and release a dataset of bilingual questions annotated for factual and cultural inconsistencies. We further test MIND on datasets from other domains to assess generalization. In all cases, MIND reliably identifies inconsistencies, supporting the development of more culturally aware and factually consistent QA systems.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 81 references that are in the map. First posted on arXiv 13 Oct 2025.

Builds on

24 of 81 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  3. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  4. 2020Selective Question Answering under Domain Shiftcited by 238
  5. 2022Challenges and Strategies in Cross-Cultural NLPcited by 218
  6. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 144
  7. 2023AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Webcited by 144
  8. 2023Complex Claim Verification with Evidence Retrieved in the Wildcited by 110
  9. 2021Decontextualization: Making Sentences Stand-Alonecited by 102
  10. 2019Answering Complex Open-domain Questions Through Iterative Query Generationcited by 60
  11. 2023Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrongcited by 51
  12. 2021Fool Me Twice: Entailment from Wikipedia Gamificationcited by 50
12 more
  1. 2021Can NLI Models Verify QA Systems' Predictions?cited by 46
  2. 2022Stretching Sentence-pair NLI Models to Reason over Long Documents and Clusterscited by 44
  3. 2023Language Models Hallucinate, but May Excel at Fact Verificationcited by 37
  4. 2022Varifocal Question Generation for Fact-checkingcited by 27
  5. 2021WikiContradiction: Detecting Self-Contradiction Articles on Wikipediacited by 17
  6. 2024Improving Tool Retrieval by Leveraging Large Language Models for Query Generationcited by 11
  7. 2019Repurposing Entailment for Multi-Hop Question Answering Taskscited by 10
  8. 2024FACTOID: FACtual enTailment fOr hallucInation Detectioncited by 10
  9. 2025AskQE: Question Answering as Automatic Evaluation for Machine Translationcited by 7
  10. 2024Enhancing Robustness of Retrieval-Augmented Language Models with In-Context Learningcited by 6
  11. 2024QuestGen: Effectiveness of Question Generation Methods for Fact-Checking Applicationscited by 2
  12. 2020Efficient Clustering from Distributions over Topicscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Perspectives on Cross-Lingual Consistency in LLMs for Medical Questionscited by 0
  2. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0