mlsanityData to 14 Oct 2026

Indirect Question Answering in English, German and Bavarian: A Challenging Task for High- and Low-Resource Languages Alike

arXiv 2603.15130 ↗First posted 16 Mar 2026cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

Indirectness is a common feature of daily communication, yet is underexplored in NLP research for both low-resource as well as high-resource languages. Indirect Question Answering (IQA) aims at classifying the polarity of indirect answers. In this paper, we present two multilingual corpora for IQA of varying quality that both cover English, Standard German and Bavarian, a German dialect without standard orthography: InQA+, a small high-quality evaluation dataset with hand-annotated labels, and GenIQA, a larger training dataset, that contains artificial data generated by GPT-4o-mini. We find that IQA is a pragmatically hard task that comes with various challenges, based on several experiment variations with multilingual transformer models (mBERT, XLM-R and mDeBERTa). We suggest and employ recommendations to tackle these challenges. Our results reveal low performance, even for English, and severe overfitting. We analyse various factors that influence these results, including label ambiguity, label set and dataset size. We find that the IQA performance is poor in high- (English, German) and low-resource languages (Bavarian) and that it is beneficial to have a large amount of training data. Further, GPT-4o-mini does not possess enough pragmatic understanding to generate high-quality IQA data in any of our tested languages.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 70 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

27 of 70 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  4. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  5. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  7. 2019Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)cited by 174
  8. 2023Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluationcited by 136
  9. 2024EuroLLM: Multilingual Language Models for Europecited by 106
  10. 2019Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approachescited by 65
  11. 2024PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilitiescited by 59
  12. 2017Creating and Characterizing a Diverse Corpus of Sarcasm in Dialoguecited by 43
15 more
  1. 2021From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understandingcited by 43
  2. 2025Seq vs Seq: An Open Suite of Paired Encoders and Decoderscited by 38
  3. 2020"I'd rather just go to bed": Understanding Indirect Answerscited by 36
  4. 2016Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Losscited by 30
  5. 2024What Do Dialect Speakers Want? A Survey of Attitudes Towards Language Technology for German Dialectscited by 21
  6. 2022Experimental Standards for Deep Learning in Natural Language Processing Researchcited by 10
  7. 2024Sebastian, Basti, Wastl?! Recognizing Named Entities in Bavarian Dialectal Datacited by 8
  8. 2024MaiBaam: A Multi-Dialectal Bavarian Universal Dependency Treebankcited by 7
  9. 2024Generalizable Sarcasm Detection Is Just Around The Corner, Of Course!cited by 5
  10. 2025Improving Dialectal Slot and Intent Detection with Auxiliary Tasks: A Multi-Dialectal Bavarian Case Studycited by 3
  11. 2025They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discoursecited by 3
  12. 2014Multilingual Part-of-Speech Tagging: Two Unsupervised Approachescited by 2
  13. 2023Interpreting Indirect Answers to Yes-No Questions in Multiple Languagescited by 2
  14. 2025Standard-to-Dialect Transfer Trends Differ across Text and Speech: A Case Study on Intent and Topic Classification in German Dialectscited by 2
  15. 2025Better Language Model-Based Judging Reward Modeling through Scaling Comprehension Boundariescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026textitVersteasch du mi? Computational and Socio-Linguistic Perspectives on GenAI, LLMs, and Non-Standard Languagecited by 0