mlsanityData to 14 Oct 2026

PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering

arXiv 2310.16147 ↗First posted 24 Oct 2023cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Information-seeking questions in long-form question answering (LFQA) often prove misleading due to ambiguity or false presupposition in the question. While many existing approaches handle misleading questions, they are tailored to limited questions, which are insufficient in a real-world setting with unpredictable input characteristics. In this work, we propose PreWoMe, a unified approach capable of handling any type of information-seeking question. The key idea of PreWoMe involves extracting presuppositions in the question and exploiting them as working memory to generate feedback and action about the question. Our experiment shows that PreWoMe is effective not only in tackling misleading questions but also in handling normal ones, thereby demonstrating the effectiveness of leveraging presuppositions, feedback, and action for real-world QA settings.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 21 of its 36 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

21 of 36 references.

References · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  8. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  9. 2022Measuring and Narrowing the Compositionality Gap in Language Modelscited by 1,075
  10. 2019ELI5: Long Form Question Answeringcited by 575
  11. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  12. 2020AmbigQA: Answering Ambiguous Open-domain Questionscited by 390
9 more
  1. 2022Self-critiquing models for assisting human evaluatorscited by 380
  2. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 307
  3. 2022Large Language Models with Controllable Working Memorycited by 169
  4. 2021Hurdles to Progress in Long-form Question Answeringcited by 167
  5. 2023A Critical Evaluation of Evaluations for Long-form Question Answeringcited by 111
  6. 2022CREPE: Open-Domain Question Answering with False Presuppositionscited by 72
  7. 2022(QA)2: Question Answering with Questionable Assumptionscited by 51
  8. 2021Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answeringcited by 41
  9. 2022Query Refinement Prompts for Closed-Book Long-Form Question Answeringcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024FinTextQA: A Dataset for Long-form Financial Question Answeringcited by 54
  2. 2025How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformationcited by 18
  3. 2025Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysiscited by 3
  4. 2026Don't `Well, Actually' Me Unless You Know What You're Talking About: Weak Presupposition Verification Degrades General QA Performancecited by 1