Lune

ACL Findings2023

Open-World Factually Consistent Question Generation

Himanshu Maheshwari, Sumit Shekhar, Apoorv Saxena, Niyati Chhaya

Abstract

Question generation methods based on pretrained language models often suffer from factual inconsistencies and incorrect entities and are not answerable from the input paragraph. Domain shift -where the test data is from a different domain than the training data -further exacerbates the problem of hallucination. This is a critical issue for any natural language application doing question generation. In this work, we propose an effective data processing technique based on de-lexicalization for consistent question generation across domains. Unlike existing approaches for remedying hallucination, the proposed approach does not filter training data and is generic across question-generation models. Experimental results across six benchmark datasets show that our model is robust to domain shift and produces entity-level factually consistent questions without significant impact on traditional metrics.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Generative Language Models for Paragraph-Level Question Generation cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
  • Read before Generate! Faithful Long Form Question Answering with Machine Reading cites A Controllable Model of Grounded Response Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. An Audit on the Perspectives and Challenges of Hallucinations in NLPPranav Narayanan Venkit, Tatiana Chakravorti, Vipul Gupta, Heidi Biggs et al.EMNLP 2024 · 8 citations
  2. K-HALU: Multiple Answer Korean Hallucination Benchmark for Large Language ModelsJaehyung Seo, Heuiseok LimICLR 2025

Builds on10

  1. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
  2. Reinforcement Learning Based Graph-to-Sequence Model for Natural Question GenerationYu Chen, Lingfei Wu, Mohammed J. ZakiICLR 2020 · 167 citations
  3. A Controllable Model of Grounded Response GenerationZeqiu Wu, Michel Galley, Chris Brockett, Yizhe Zhang et al.AAAI 2021 · 89 citations
  4. Read before Generate! Faithful Long Form Question Answering with Machine ReadingDan Su, Xiaoguang Li, Jindi Zhang, Lifeng Shang et al.ACL Findings 2022 · 37 citations
  5. Generative Language Models for Paragraph-Level Question GenerationAsahi Ushio, Fernando Alva-Manchego, José Camacho-ColladosEMNLP 2022 · 30 citations

Related papers

  1. HalluClean: A Unified Framework to Combat Hallucinations in LLMsYaxin Zhao, Yu ZhangAAAI 2026
  2. FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text TrainingXinxin You, Qixin Sun, Chenwei Yan, Xiao Zhang et al.NeurIPS 2025
  3. PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the BeginningLangming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang et al.ACL Findings 2026
  4. How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM HallucinationSaad Obaid ul Islam, Anne Lauscher, Goran GlavasEMNLP 2025
  5. Knowledge Verification to Nip Hallucination in the BudFanqi Wan, Xinting Huang, Leyang Cui, Xiaojun Quan et al.EMNLP 2024 · 8 citations
Dusk over the sea between two cliffs drawn in fine vertical lines