---
title: "Linguistics to LLMs: Teaching with and about Chatbots (2026)"
description: "They describe how they rebuilt a three-week dialogue unit within a mandatory, German-taught AI course for Business… 12 references."
authors: ["Ulrike Pado", "Barbara Pampel"]
year: 2026
venue: "Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026)"
source: "https://aclanthology.org/2026.teachingnlp-1.4/"
doi: "10.18653/v1/2026.teachingnlp-1.4"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/pado-2026-linguistics-llms-teaching-about-chatbots/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pado-2026-linguistics-llms-teaching-about-chatbots/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/35/) / Linguistics to LLMs: Teaching with and about Chatbots

# Linguistics to LLMs: Teaching with and about Chatbots

**Authors:** [Ulrike Pado](https://md.research.elamur.ai/free/en/authors/ulrike-pado/) and Barbara Pampel · **Year:** 2026 · **Venue:** [Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026)](https://md.research.elamur.ai/free/en/venues/teachingnlp/) ([Workshop on Teaching Natural Language Processing 2026](https://md.research.elamur.ai/free/en/venues/teachingnlp/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.teachingnlp-1.4/) · [PDF](https://aclanthology.org/2026.teachingnlp-1.4.pdf) · [DOI 10.18653/v1/2026.teachingnlp-1.4](https://doi.org/10.18653/v1/2026.teachingnlp-1.4) · [OpenAlex](https://openalex.org/W7140102160)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
LLM-based methods are rapidly displacing older NLP techniques, so existing courses must be revised. The authors use this as a chance to add a chatbot as a learning aid. They describe how they rebuilt a three-week dialogue unit within a mandatory, German-taught AI course for Business Informatics bachelor students at Hochschule für Technik Stuttgart. The unit previously covered rule-based digital assistants. It now treats LLM-based chatbots and covers:
- human dialogue theory (adjacency pairs, Gricean Maxims)
- neural networks and the Transformer
- embeddings
- energy consumption and bias

They also deployed a tutorbot built with Retrieval-Augmented Generation (RAG) in Flowise on open-source LLMs. It is restricted to the course materials and also serves as a case study analysed in class. Questionnaires before and after instruction showed that students felt more confident about the technical basics. They also judged LLMs more realistically, attributing less objectivity and intelligence to them while recognising their human-like conversational behaviour. The paper offers a practical template for instructors making similar curriculum changes.

## Key points
- Setting: a 14-week mandatory AI class in the second year of a seven-semester Business Informatics program, taught with the Computer-based Learning (CBL) approach (self-paced videos, self-tests, exercises during in-person sessions).
- The tutorbot "SKIT" uses RAG over the class slides. Its system prompt forbids answering beyond the retrieved context and supplies a fixed fallback reply when the slides contain no relevant information.
- The authors' earlier work found the bot answered as intended in 95% of 328 user-bot interactions.
- Usage: 280 interactions occurred during the LLM/chatbot weeks, and roughly 110 more were spread over the rest of the course, peaking before formative tests. Use was anonymous, and no student opted out of research analysis.
- Stated limitations: the small number of students and classes limits generalisability, and fast-moving tools may quickly date the findings.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Konstanz](https://md.research.elamur.ai/free/en/universities/university-of-konstanz/) — University, Konstanz, Germany · 17 works · 232 citations
- [Stuttgart Technical University of Applied Sciences](https://md.research.elamur.ai/free/en/universities/stuttgart-technical-university-of-applied-sciences/) — University, Stuttgart, Germany · 2 works · 1 citation

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,437 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,320 works · [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 624 works

## Cite

Cite as: Ulrike Pado and Barbara Pampel. 2026. Linguistics to LLMs: Teaching with and about Chatbots. Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{pado2026linguistics,
  title = {{Linguistics to LLMs: Teaching with and about Chatbots}},
  author = {Ulrike Pado and Barbara Pampel},
  booktitle = {Proceedings of the Seventh Workshop on Teaching Natural Language Processing (TeachNLP 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.teachingnlp-1.4},
  url = {https://doi.org/10.18653/v1/2026.teachingnlp-1.4}
}
```

- [← previous Linguistically-Informed Evaluation of LLMs on Acceptability Judgments in a Forced-Choice Paradigm](https://md.research.elamur.ai/free/en/papers/liu-2026-linguistically-informed-evaluation-llms-acceptability/)
- [next → LingVarBench: Benchmarking LLMs on Entity Recognitions and Linguistic Verbalization Patterns in Phone-Call Transcripts](https://md.research.elamur.ai/free/en/papers/mohammadi-2026-lingvarbench-benchmarking-llms-entity-recognitions/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/35/)

## References

12 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jonathan Mayer. 2024. Untersuchung von Schüler:innenvorstellungen zu künstlicher Intelligenz. Master’s thesis, University of Konstanz. [find](https://scholar.google.com/scholar?q=Jonathan+Mayer%2E+2024%2E+Untersuchung+von+Sch%C3%BCler%3Ainnenvorstellungen+zu+k%C3%BCnstlicher+Intelligenz%2E+Master%E2%80%99s+thesis%2C+University+of+Konstanz%2E)
2. Muhammad Abbas, Farooq Ahmed Jam, and Tariq Iqbal Khan. 2024. Is it harmful or helpful? Examining the causes and consequences of generative AI usage among university students. International Journal of Educational Technology in Higher Education, 21(10). [find](https://scholar.google.com/scholar?q=Muhammad+Abbas%2C+Farooq+Ahmed+Jam%2C+and+Tariq+Iqbal+Khan%2E+2024%2E+Is+it+harmful+or+helpful%3F+Examining+the+causes+and+consequences+of+generative+AI+usage+among+university+students%2E+International+Journal+of)
3. Joshua Maynez, Shashi Narayan, Bernd Bohnet, and Ryan McDonald. 2020. [On faithfulness and factuality in abstractive summarization](https://md.research.elamur.ai/free/en/papers/maynez-2020-faithfulness-factuality-abstractive-summarization/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1906–1919, Online. Association for Computational Linguistics.
4. Daniel H Chang, Michael Pin-Chuan Lin, Shiva Hajian, and Quincy Q Wang. 2023. Educational design principles of using AI chatbot that supports self-regulated learning in education: Goal setting, feedback, and personalization. Sustainability, 15(17):12921. [find](https://scholar.google.com/scholar?q=Daniel+H+Chang%2C+Michael+Pin%2DChuan+Lin%2C+Shiva+Hajian%2C+and+Quincy+Q+Wang%2E+2023%2E+Educational+design+principles+of+using+AI+chatbot+that+supports+self%2Dregulated+learning+in+education%3A+Goal+setting%2C+feedba)
5. Ali Doosthosseini, Jonathan Decker, Hendrik Nolte, and Julian Kunkel. 2025. SAIA: A Seamless Slurm-Native Solution for HPC-Based Services. [find](https://scholar.google.com/scholar?q=Ali+Doosthosseini%2C+Jonathan+Decker%2C+Hendrik+Nolte%2C+and+Julian+Kunkel%2E+2025%2E+SAIA%3A+A+Seamless+Slurm%2DNative+Solution+for+HPC%2DBased+Services%2E)
6. Barbara Pampel, Simon Martin, and Ulrike Padó. 2025. Regaining Control: Enabling Educators to Build Specialized AI Chat Bots with Retrieval Augmented Generation. In Proceedings of the 17th International Conference on Computer Supported Education - Volume 2: CSEDU, pages 371–378. INSTICC, SciTePress. [find](https://scholar.google.com/scholar?q=Barbara+Pampel%2C+Simon+Martin%2C+and+Ulrike+Pad%C3%B3%2E+2025%2E+Regaining+Control%3A+Enabling+Educators+to+Build+Specialized+AI+Chat+Bots+with+Retrieval+Augmented+Generation%2E+In+Proceedings+of+the+17th+Internation)
7. Wenqi Fan, Yujuan Ding, Liangbo Ning, Shijie Wang, Hengyun Li, Dawei Yin, Tat-Seng Chua, and Qing Li. 2024. [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://md.research.elamur.ai/free/en/papers/fan-2024-survey-rag-meeting-llms-towards/). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’24, Barbara Pampe…
8. Fábio Perez and Ian Ribeiro. 2022. [Ignore Previous Prompt: Attack Techniques For Language Models](https://md.research.elamur.ai/free/en/papers/perez-2022-ignore-previous-prompt-attack-techniques/). In Proceedings of the Workshop on Machine Learning Safety at NeurIPs.
9. Kurt Shuster, Spencer Poff, Moya Chen, Douwe Kiela, and Jason Weston. 2021. [Retrieval augmentation reduces hallucination in conversation](https://md.research.elamur.ai/free/en/papers/shuster-2021-retrieval-augmentation-reduces-hallucination-conversation/). In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3784–3803, Punta Cana, Dominican Republic. Association for Computational Linguisti…
10. Thomas Süße and Maria Kobert. 2023. Generative AI at School-Insights from a study about German students’ self-reported usage, the role of students’ action-guiding characteristics, perceived learning success and the consideration of contextual factors. Zenodo. [find](https://scholar.google.com/scholar?q=Thomas+S%C3%BC%C3%9Fe+and+Maria+Kobert%2E+2023%2E+Generative+AI+at+School%2DInsights+from+a+study+about+German+students%E2%80%99+self%2Dreported+usage%2C+the+role+of+students%E2%80%99+action%2Dguiding+characteristics%2C+perceived+learning+s)
11. Jakub Swacha and Michał Gracel. 2025. Retrieval-augmented generation (RAG) chatbots for education: A survey of applications. Applied Sciences, 15(8):4234. [find](https://scholar.google.com/scholar?q=Jakub+Swacha+and+Micha%C5%82+Gracel%2E+2025%2E+Retrieval%2Daugmented+generation+%28RAG%29+chatbots+for+education%3A+A+survey+of+applications%2E+Applied+Sciences%2C+15%288%29%3A4234%2E)
12. Jiahao Yu, Yuhang Wu, Dong Shu, Mingyu Jin, and Xinyu Xing. 2023. Assessing prompt injection risks in 200+ custom GPTs. arXiv preprint arXiv:2311.11538. — [arXiv:2311.11538](https://arxiv.org/abs/2311.11538) [find](https://scholar.google.com/scholar?q=Jiahao+Yu%2C+Yuhang+Wu%2C+Dong+Shu%2C+Mingyu+Jin%2C+and+Xinyu+Xing%2E+2023%2E+Assessing+prompt+injection+risks+in+200%2B+custom+GPTs%2E+arXiv+preprint+arXiv%3A2311%2E11538%2E+%E2%80%94+%5BarXiv%3A2311%2E11538%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2311)

*Updated 1 November 2026*