---
title: "LLMs of Catan — paper by Martinenghi et al. (2024)"
description: "They vary prompt design, including example-based versus definition-based task framing and the order… 58 references, cited by 4 papers here."
authors: ["Andrea Martinenghi", "Gregor Donabauer", "Simona Amenta", "Sathya Bursic", "Mathyas Giudici", "Udo Kruschwitz", "Franca Garzotto", "Dimitri Ognibene"]
year: 2024
venue: "Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024"
source: "https://aclanthology.org/2024.games-1.12/"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/martinenghi-2024-llms-catan-exploring-pragmatic-capabilities/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/martinenghi-2024-llms-catan-exploring-pragmatic-capabilities/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/13/) / LLMs of Catan: Exploring Pragmatic Capabilities of Generative Chatbots Through Prediction and Classification of Dialogue Acts in Boardgames' Multi-party Dialogues

# LLMs of Catan: Exploring Pragmatic Capabilities of Generative Chatbots Through Prediction and Classification of Dialogue Acts in Boardgames' Multi-party Dialogues

**Authors:** Andrea Martinenghi, Gregor Donabauer, Simona Amenta, Sathya Bursic, Mathyas Giudici, [Udo Kruschwitz](https://md.research.elamur.ai/free/en/authors/udo-kruschwitz/), Franca Garzotto and Dimitri Ognibene · **Year:** 2024 · **Venue:** Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024 · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2024.games-1.12/) · [PDF](https://aclanthology.org/2024.games-1.12.pdf) · [OpenAlex](https://openalex.org/W7131801413)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [4](https://md.research.elamur.ai/free/en/papers/martinenghi-2024-llms-catan-exploring-pragmatic-capabilities/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks how well general-purpose generative chatbots, mainly ChatGPT, understand the pragmatics of group conversation. It focuses on dialogue acts (DAs) in multi-party chat, where systems must also track who is speaking, turn-taking and parallel threads. Since most chatbots are tuned on two-party exchanges, the multi-party setting also tests whether their dialogue skills transfer. The authors use STAC, a corpus of player chats from online Settlers of Catan games. They run zero-shot and few-shot prompting for two tasks: labelling the DA of an utterance and forecasting the DA of the next turn. They vary prompt design, including example-based versus definition-based task framing and the order in which information appears. They also try adding statistics on typical DA sequences, and they ask the model to predict the next utterance's wording together with its act. For some DA types, ChatGPT performs on par with baselines trained from scratch, but it also shows biases and clear limits. The work matters for building chatbots that join group conversations cheaply, without full training or fine-tuning. Code and detailed results are released.

## Key points
- Data: STAC, built on the Settlers corpus of Catan chats. Settlers was the first multi-party dataset annotated for discourse parsing and was the only one until Molweni appeared.
- Two tasks are studied in zero- and few-shot regimes: classifying the current DA and predicting the upcoming one.
- Prompt factors tested:
  - framing the task through examples versus formal descriptions,
  - the order of information in the prompt,
  - adding DA-sequence statistics,
  - jointly generating the next utterance's text and its DA.
- Main result: ChatGPT keeps pace with from-scratch baselines on certain DA types, but it exhibits label biases and other weaknesses.
- Theoretical grounding: speech act theory (Austin, Searle, Grice, Strawson), including Bach & Harnish's four illocutionary classes (constatives, directives, commissives, acknowledgments). Code is at github.com/DimNeuroLab/llmGrounding.

## Interesting ideas
- Define a labelling task mainly through worked examples rather than abstract category definitions, and treat example order as an experimental variable, because LLM output shifts with presentation order.
- Treat dialogue acts as a sequence: predict the next act and inject prior statistics about which acts usually follow which.
- Have the model produce the next utterance and its act together, then check whether the generated wording actually fits the stated act.
- Use game chat logs, where the game engine records events alongside messages, to tie utterances to concrete extra-linguistic context and players' strategic goals.
- Report results per dialogue-act type against a from-scratch baseline instead of a single aggregate score, so that strengths and biases toward specific labels become visible.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): When an LLM teacher tier produces silver speech-act labels, compare example-based and definition-based prompts and shuffle example order as a control. Labels that change under shuffling should be flagged as unreliable.
- **I2** (frames): The speech-act component in prag could combine its per-utterance decision with a transition prior over preceding acts. The explanation could then cite both the cue and the dialogue context.
- **I3** (back): After generating text from a meaning graph with an intended speech act, run the generated sentence back through the act classifier. A mismatch signals a generation error.
- **I4** (world): Game-like corpora with logged state changes could serve as test beds for aligning described events and holdings, such as trades of resources, with the world model built from the text.
- **I5** (learn): Evaluate the speech-act and frame components per class against a trained baseline, which exposes systematic label preferences that a global accuracy figure would hide.

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

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (3): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 654 works · [💬 Speech act theory](https://md.research.elamur.ai/free/en/topics/speech-act-theory/) · 229 works

## Cite

Cite as: Andrea Martinenghi, Gregor Donabauer, Simona Amenta, Sathya Bursic, Mathyas Giudici, Udo Kruschwitz, Franca Garzotto and Dimitri Ognibene. 2024. LLMs of Catan: Exploring Pragmatic Capabilities of Generative Chatbots Through Prediction and Classification of Dialogue Acts in Boardgames' Multi-party Dialogues. Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024.

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

```bibtex
@inproceedings{martinenghi2024llms,
  title = {{LLMs of Catan: Exploring Pragmatic Capabilities of Generative Chatbots Through Prediction and Classification of Dialogue Acts in Boardgames' Multi-party Dialogues}},
  author = {Andrea Martinenghi, Gregor Donabauer, Simona Amenta, Sathya Bursic, Mathyas Giudici, Udo Kruschwitz, Franca Garzotto and Dimitri Ognibene},
  booktitle = {Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024},
  year = {2024},
  doi = {10.63317/5ecukgse9ofw},
  url = {https://doi.org/10.63317/5ecukgse9ofw}
}
```

- [← previous Leveraging Syntactic Dependencies in Disambiguation: The Case of African American English](https://md.research.elamur.ai/free/en/papers/previlon-2024-leveraging-syntactic-dependencies-disambiguation-case/)
- [next → LSTM-Based Text Generation: A Study on Historical Datasets](https://md.research.elamur.ai/free/en/papers/hussein-2024-lstm-based-text-generation-study/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/13/)

## References

58 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eleni Adamopoulou and Lefteris Moussiades. 2020. Chatbots: History, technology, and applications. Machine Learning with Applications, 2:100006. [find](https://scholar.google.com/scholar?q=Eleni+Adamopoulou+and+Lefteris+Moussiades%2E+2020%2E+Chatbots%3A+History%2C+technology%2C+and+applications%2E+Machine+Learning+with+Applications%2C+2%3A100006%2E)
2. Stergos Afantenos, Eric Kow, Nicholas Asher, and Jérémy Perret. 2015. [Discourse parsing for multi-party chat dialogues](https://md.research.elamur.ai/free/en/papers/afantenos-2015-discourse-parsing-multi-party-chat/). In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 928–937, Lisbon, Portugal. Association for Computational Linguistics.
3. Toufique Ahmed and Premkumar Devanbu. 2023. Few-shot training llms for project-specific code-summarization. In Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, ASE ’22, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Toufique+Ahmed+and+Premkumar+Devanbu%2E+2023%2E+Few%2Dshot+training+llms+for+project%2Dspecific+code%2Dsummarization%2E+In+Proceedings+of+the+37th+IEEE%2FACM+International+Conference+on+Automated+Software+Engineeri)
4. Keith Allan. 1998. Meaning and speech acts. Retrieved June, 28:2004. [find](https://scholar.google.com/scholar?q=Keith+Allan%2E+1998%2E+Meaning+and+speech+acts%2E+Retrieved+June%2C+28%3A2004%2E)
5. James Allen and Mark Core. 1997. Draft of damsl: Dialog act markup in several layers. [find](https://scholar.google.com/scholar?q=James+Allen+and+Mark+Core%2E+1997%2E+Draft+of+damsl%3A+Dialog+act+markup+in+several+layers%2E)
6. Nicholas Asher, Julie Hunter, Mathieu Morey, Benamara Farah, and Stergos Afantenos. 2016. [Discourse structure and dialogue acts in multiparty dialogue: the STAC corpus](https://md.research.elamur.ai/free/en/papers/asher-2016-discourse-structure-dialogue-acts-multiparty/). In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 2721– 2727, Portorož, Slovenia. European Language Resources Association (ELRA). [↗](https://doi.org/10.63317/3dr9b3ndpn84)
7. Nicholas Asher and Alex Lascarides. 2003. Logics of conversation. Cambridge University Press. [find](https://scholar.google.com/scholar?q=Nicholas+Asher+and+Alex+Lascarides%2E+2003%2E+Logics+of+conversation%2E+Cambridge+University+Press%2E)
8. John Langshaw Austin. 1975. How to do things with words, volume 88. Oxford university press. [find](https://scholar.google.com/scholar?q=John+Langshaw+Austin%2E+1975%2E+How+to+do+things+with+words%2C+volume+88%2E+Oxford+university+press%2E)
9. Kent Bach and Robert M Harnish. 1979. Linguistic communication and speech acts. [find](https://scholar.google.com/scholar?q=Kent+Bach+and+Robert+M+Harnish%2E+1979%2E+Linguistic+communication+and+speech+acts%2E)
10. Yejin Bang, Samuel Cahyawijaya, Nayeon Lee, Wenliang Dai, Dan Su, Bryan Wilie, Holy Lovenia, Ziwei Ji, Tiezheng Yu, Willy Chung, Quyet V. Do, Yan Xu, and Pascale Fung. 2023. [A multitask, multilingual, multimodal evaluation of chatgpt on reasoning, hallucination, and interactivity](https://md.research.elamur.ai/free/en/papers/bang-2023-multitask-multilingual-multimodal-evaluation-chatgpt/).
11. Chiara Barattieri di San Pietro, Federico Frau, Veronica Mangiaterra, and Valentina Bambini. 2023. The pragmatic profile of chatgpt: Assessing the communicative skills of a conversational agent. Sistemi intelligenti, 35(2):379–400. [find](https://scholar.google.com/scholar?q=Chiara+Barattieri+di+San+Pietro%2C+Federico+Frau%2C+Veronica+Mangiaterra%2C+and+Valentina+Bambini%2E+2023%2E+The+pragmatic+profile+of+chatgpt%3A+Assessing+the+communicative+skills+of+a+conversational+agent%2E+Siste)
12. Emily M Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell. 2021. On the dangers of stochastic parrots: Can language models be too big? In Proceedings of the 2021 ACM conference on fairness, accountability, and transparency, pages 610–623. [↗](https://doi.org/10.1145/3442188.3445922)
13. Emily M Bender and Alexander Koller. 2020. [Climbing towards nlu: On meaning, form, and understanding in the age of data](https://md.research.elamur.ai/free/en/papers/bender-2020-climbing-nlu-meaning-form-understanding/). In Proceedings of the 58th annual meeting of the association for computational linguistics, pages 5185–5198.
14. Ali Borji. 2023. [A categorical archive of chatgpt failures](https://md.research.elamur.ai/free/en/papers/borji-2023-categorical-archive-chatgpt-failures/). arXiv preprint arXiv:2302.03494. [↗](https://arxiv.org/abs/2302.03494)
15. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
16. Harry Bunt. 1994. Context and dialogue control. Think Quarterly, 3(1):19–31. [find](https://scholar.google.com/scholar?q=Harry+Bunt%2E+1994%2E+Context+and+dialogue+control%2E+Think+Quarterly%2C+3%281%29%3A19%E2%80%9331%2E)
17. Harry C Bunt. 1981. Rules for the interpretation, evaluation and generation of dialogue acts. IPO annual progress report, 16:99–107. [find](https://scholar.google.com/scholar?q=Harry+C+Bunt%2E+1981%2E+Rules+for+the+interpretation%2C+evaluation+and+generation+of+dialogue+acts%2E+IPO+annual+progress+report%2C+16%3A99%E2%80%93107%2E)
18. Anais Cadilhac, Nicholas Asher, Farah Benamara, and Alex Lascarides. 2013. Grounding strategic conversation: Using negotiation dialogues to predict trades in a win-lose game. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 357–368. [find](https://scholar.google.com/scholar?q=Anais+Cadilhac%2C+Nicholas+Asher%2C+Farah+Benamara%2C+and+Alex+Lascarides%2E+2013%2E+Grounding+strategic+conversation%3A+Using+negotiation+dialogues+to+predict+trades+in+a+win%2Dlose+game%2E+In+Proceedings+of+the+201)
19. Chunkit Chan, Jiayang Cheng, Weiqi Wang, Yuxin Jiang, Tianqing Fang, Xin Liu, and Yangqiu Song. 2023. [Chatgpt evaluation on sentence level relations: A focus on temporal, causal, and discourse relations](https://md.research.elamur.ai/free/en/papers/chan-2024-exploring-potential-chatgpt-sentence-level/). arXiv preprint arXiv:2304.14827. [↗](https://arxiv.org/abs/2304.14827)
20. Alex Djalali, Sven Lauer, and Christopher Potts. 2011. Corpus evidence for preference-driven interpretation. In Proceedings of the 18th Amsterdam Colloquim Conference on Logic, Language and Meaning, AC’11, page 150–159, Berlin, Heidelberg. Springer-Verlag. [find](https://scholar.google.com/scholar?q=Alex+Djalali%2C+Sven+Lauer%2C+and+Christopher+Potts%2E+2011%2E+Corpus+evidence+for+preference%2Ddriven+interpretation%2E+In+Proceedings+of+the+18th+Amsterdam+Colloquim+Conference+on+Logic%2C+Language+and+Meaning%2C+A)
21. Fernanda Ferreira, Karl GD Bailey, and Vittoria Ferraro. 2002. Good-enough representations in language comprehension. Current directions in psychological science, 11(1):11–15. [find](https://scholar.google.com/scholar?q=Fernanda+Ferreira%2C+Karl+GD+Bailey%2C+and+Vittoria+Ferraro%2E+2002%2E+Good%2Denough+representations+in+language+comprehension%2E+Current+directions+in+psychological+science%2C+11%281%29%3A11%E2%80%9315%2E)
22. Shuyang Gao, Sanchit Agarwal, Tagyoung Chung, Di Jin, and Dilek Hakkani-Tur. 2020. From machine reading comprehension to dialogue state tracking: Bridging the gap. Publisher: [object Object] Version Number: 1. [find](https://scholar.google.com/scholar?q=Shuyang+Gao%2C+Sanchit+Agarwal%2C+Tagyoung+Chung%2C+Di+Jin%2C+and+Dilek+Hakkani%2DTur%2E+2020%2E+From+machine+reading+comprehension+to+dialogue+state+tracking%3A+Bridging+the+gap%2E+Publisher%3A+%5Bobject+Object%5D+Version+N)
23. H Paul Grice. 1957. Meaning. The philosophical review, 66(3):377–388. [find](https://scholar.google.com/scholar?q=H+Paul+Grice%2E+1957%2E+Meaning%2E+The+philosophical+review%2C+66%283%29%3A377%E2%80%93388%2E)
24. H Paul Grice. 1975. Logic and conversation. Syntax and Semantics, 3:43–58. [find](https://scholar.google.com/scholar?q=H+Paul+Grice%2E+1975%2E+Logic+and+conversation%2E+Syntax+and+Semantics%2C+3%3A43%E2%80%9358%2E)
25. Reto Gubelmann. 2024. Large language models, agency, and why speech acts are beyond them (for now)–a kantian-cum-pragmatist case. Philosophy & Technology, 37(1):32. [find](https://scholar.google.com/scholar?q=Reto+Gubelmann%2E+2024%2E+Large+language+models%2C+agency%2C+and+why+speech+acts+are+beyond+them+%28for+now%29%E2%80%93a+kantian%2Dcum%2Dpragmatist+case%2E+Philosophy+%26+Technology%2C+37%281%29%3A32%2E)
26. Laurence R Horn and Gregory L Ward. 2004. The handbook of pragmatics. Wiley Online Library. [↗](https://doi.org/10.1111/b.9780631225485.2005.00001.x)
27. Jennifer Hu, Sammy Floyd, Olessia Jouravlev, Evelina Fedorenko, and Edward Gibson. 2022. [A fine-grained comparison of pragmatic language understanding in humans and language models](https://md.research.elamur.ai/free/en/papers/hu-2023-fine-grained-comparison-pragmatic-language/). arXiv preprint arXiv:2212.06801. [↗](https://arxiv.org/abs/2212.06801)
28. Ozan Irsoy, Rakesh Gosangi, Haimin Zhang, Mu-Hsin Wei, Peter Lund, Duccio Pappadopulo, Brendan Fahy, Neophytos Nephytou, and Camilo Ortiz. 2019. [Dialogue act classification in group chats with dag-lstms](https://md.research.elamur.ai/free/en/papers/irsoy-2019-dialogue-act-classification-group-chats/). CoRR, abs/1908.01821. [↗](https://arxiv.org/abs/1908.01821)
29. Qi Jia, Yizhu Liu, Siyu Ren, Kenny Zhu, and Haifeng Tang. 2020. Multi-turn response selection using dialogue dependency relations. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1911–1920. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Qi+Jia%2C+Yizhu+Liu%2C+Siyu+Ren%2C+Kenny+Zhu%2C+and+Haifeng+Tang%2E+2020%2E+Multi%2Dturn+response+selection+using+dialogue+dependency+relations%2E+In+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural)
30. Daniel Jurafsky and James Martin. 2024. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. 3rd edition (draft), 3rd February 2024. [https://web.stanford.edu/~jurafsky/slp3/](https://web.stanford.edu/~jurafsky/slp3/). [↗](https://web.stanford.edu/~jurafsky/slp3/)
31. Hossein Karimi and Fernanda Ferreira. 2016. Good-enough linguistic representations and online cognitive equilibrium in language processing. Quarterly journal of experimental psychology, 69(5):1013–1040. [find](https://scholar.google.com/scholar?q=Hossein+Karimi+and+Fernanda+Ferreira%2E+2016%2E+Good%2Denough+linguistic+representations+and+online+cognitive+equilibrium+in+language+processing%2E+Quarterly+journal+of+experimental+psychology%2C+69%285%29%3A1013%E2%80%93104)
32. Cansu Koyuturk, Mona Yavari, Emily Theophilou, Sathya Bursic, Gregor Donabauer, Alessia Telari, Alessia Testa, Raffaele Boiano, Alessandro Gab-biadini, Davinia Hernandez-Leo, et al. 2023. Developing effective educational chatbots with chatgpt prompts: Insights from preliminary tests in a case study on social media literacy. In 31st International Conference on Computers in Education. [find](https://scholar.google.com/scholar?q=Cansu+Koyuturk%2C+Mona+Yavari%2C+Emily+Theophilou%2C+Sathya+Bursic%2C+Gregor+Donabauer%2C+Alessia+Telari%2C+Alessia+Testa%2C+Raffaele+Boiano%2C+Alessandro+Gab%2Dbiadini%2C+Davinia+Hernandez%2DLeo%2C+et+al%2E+2023%2E+Developing+e)
33. János Kramár, Tom Eccles, Ian Gemp, Andrea Tacchetti, Kevin R McKee, Mateusz Malinowski, Thore Graepel, and Yoram Bachrach. 2022. Negotiation and honesty in artificial intelligence methods for the board game of diplomacy. Nature Communications, 13(1):7214. [find](https://scholar.google.com/scholar?q=J%C3%A1nos+Kram%C3%A1r%2C+Tom+Eccles%2C+Ian+Gemp%2C+Andrea+Tacchetti%2C+Kevin+R+McKee%2C+Mateusz+Malinowski%2C+Thore+Graepel%2C+and+Yoram+Bachrach%2E+2022%2E+Negotiation+and+honesty+in+artificial+intelligence+methods+for+the+boa)
34. Alex Lascarides and Nicholas Asher. 2009. Agreement, Disputes and Commitments in Dialogue. Journal of Semantics, 26(2):109–158. [find](https://scholar.google.com/scholar?q=Alex+Lascarides+and+Nicholas+Asher%2E+2009%2E+Agreement%2C+Disputes+and+Commitments+in+Dialogue%2E+Journal+of+Semantics%2C+26%282%29%3A109%E2%80%93158%2E)
35. Alessandro Lenci. 2023. Understanding natural language understanding systems. a critical analysis. arXiv preprint arXiv:2303.04229. [↗](https://arxiv.org/abs/2303.04229)
36. Wei Li, Luyao Zhu, Rui Mao, and Erik Cambria. 2023. SKIER: A symbolic knowledge integrated model for conversational emotion recognition. 37(11):13121–13129. [find](https://scholar.google.com/scholar?q=Wei+Li%2C+Luyao+Zhu%2C+Rui+Mao%2C+and+Erik+Cambria%2E+2023%2E+SKIER%3A+A+symbolic+knowledge+integrated+model+for+conversational+emotion+recognition%2E+37%2811%29%3A13121%E2%80%9313129%2E)
37. Youchao Lin, Miho Kasamatsu, Tengyang Chen, Takuya Fujita, Huanjin Deng, and Takehito Utsuro. 2020. Automatic annotation of werewolf game corpus with players revealing oneselves as seer/medium and divination/medium results. In Workshop on Games and Natural Language Processing, pages 85–93, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Youchao+Lin%2C+Miho+Kasamatsu%2C+Tengyang+Chen%2C+Takuya+Fujita%2C+Huanjin+Deng%2C+and+Takehito+Utsuro%2E+2020%2E+Automatic+annotation+of+werewolf+game+corpus+with+players+revealing+oneselves+as+seer%2Fmedium+and+div)
38. Cao Liu, Kang Liu, Shizhu He, Zaiqing Nie, and Jun Zhao. 2019. Incorporating interlocutor-aware context into response generation on multi-party chatbots. [find](https://scholar.google.com/scholar?q=Cao+Liu%2C+Kang+Liu%2C+Shizhu+He%2C+Zaiqing+Nie%2C+and+Jun+Zhao%2E+2019%2E+Incorporating+interlocutor%2Daware+context+into+response+generation+on+multi%2Dparty+chatbots%2E)
39. Khyati Mahajan and Samira Shaikh. 2021. On the need for thoughtful data collection for multi-party dialogue: A survey of available corpora and collection methods. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 338–352, Singapore and Online. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Khyati+Mahajan+and+Samira+Shaikh%2E+2021%2E+On+the+need+for+thoughtful+data+collection+for+multi%2Dparty+dialogue%3A+A+survey+of+available+corpora+and+collection+methods%2E+In+Proceedings+of+the+22nd+Annual+Mee)
40. Kyle Mahowald, Anna A. Ivanova, Idan A. Blank, Nancy Kanwisher, Joshua B. Tenenbaum, and Evelina Fedorenko. 2024. Dissociating language and thought in large language models. Trends in Cognitive Sciences. [find](https://scholar.google.com/scholar?q=Kyle+Mahowald%2C+Anna+A%2E+Ivanova%2C+Idan+A%2E+Blank%2C+Nancy+Kanwisher%2C+Joshua+B%2E+Tenenbaum%2C+and+Evelina+Fedorenko%2E+2024%2E+Dissociating+language+and+thought+in+large+language+models%2E+Trends+in+Cognitive+Scienc)
41. Michael McTear. 2022. Conversational ai: Dialogue systems, conversational agents, and chatbots. Springer Nature. [find](https://scholar.google.com/scholar?q=Michael+McTear%2E+2022%2E+Conversational+ai%3A+Dialogue+systems%2C+conversational+agents%2C+and+chatbots%2E+Springer+Nature%2E)
42. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744. [↗](https://doi.org/10.52202/068431-2011)
43. Laura Ruis, Akbir Khan, Stella Biderman, Sara Hooker, Tim Rocktäschel, and Edward Grefenstette. 2024. [The goldilocks of pragmatic understanding: Fine-tuning strategy matters for implicature resolution by llms](https://md.research.elamur.ai/free/en/papers/ruis-2022-goldilocks-pragmatic-understanding-fine-tuning/). Advances in Neural Information Processing Systems, 36. [↗](https://doi.org/10.52202/075280-0913)
44. John R Searle. 1969. Speech acts: An essay in the philosophy of language, volume 626. Cambridge university press. [find](https://scholar.google.com/scholar?q=John+R+Searle%2E+1969%2E+Speech+acts%3A+An+essay+in+the+philosophy+of+language%2C+volume+626%2E+Cambridge+university+press%2E)
45. John R Searle. 1975. A taxonomy of illocutionary acts. [find](https://scholar.google.com/scholar?q=John+R+Searle%2E+1975%2E+A+taxonomy+of+illocutionary+acts%2E)
46. Joseph Seering, Michal Luria, Connie Ye, Geoff Kaufman, and Jessica Hammer. 2020. It takes a village: Integrating an adaptive chatbot into an online gaming community. In Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems, CHI ’20, page 1–13, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Joseph+Seering%2C+Michal+Luria%2C+Connie+Ye%2C+Geoff+Kaufman%2C+and+Jessica+Hammer%2E+2020%2E+It+takes+a+village%3A+Integrating+an+adaptive+chatbot+into+an+online+gaming+community%2E+In+Proceedings+of+the+2020+CHI+Co)
47. Penelope Sibun. 1997. Beyond dialogue: the six w’s of multi-party interaction. In Working Notes of AAAI97 Spring Symposium On Mixed-Initiative Interaction, Stanford, CA, pages 145–150. [find](https://scholar.google.com/scholar?q=Penelope+Sibun%2E+1997%2E+Beyond+dialogue%3A+the+six+w%E2%80%99s+of+multi%2Dparty+interaction%2E+In+Working+Notes+of+AAAI97+Spring+Symposium+On+Mixed%2DInitiative+Interaction%2C+Stanford%2C+CA%2C+pages+145%E2%80%93150%2E)
48. Simon Stepputtis, Joseph Campbell, Yaqi Xie, Zhengyang Qi, Wenxin Zhang, Ruiyi Wang, Sanketh Rangreji, Charles Lewis, and Katia Sycara. 2023. Long-horizon dialogue understanding for role identification in the game of avalon with large language models. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11193–11208, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Simon+Stepputtis%2C+Joseph+Campbell%2C+Yaqi+Xie%2C+Zhengyang+Qi%2C+Wenxin+Zhang%2C+Ruiyi+Wang%2C+Sanketh+Rangreji%2C+Charles+Lewis%2C+and+Katia+Sycara%2E+2023%2E+Long%2Dhorizon+dialogue+understanding+for+role+identificatio)
49. Peter F Strawson. 2013. Intention and conventionin speech acts. In Symposium on JL Austin (Routledge Revivals), pages 380–400. Routledge. [find](https://scholar.google.com/scholar?q=Peter+F+Strawson%2E+2013%2E+Intention+and+conventionin+speech+acts%2E+In+Symposium+on+JL+Austin+%28Routledge+Revivals%29%2C+pages+380%E2%80%93400%2E+Routledge%2E)
50. Nicolas Wagner, Matthias Kraus, Tibor Tonn, and Wolfgang Minker. 2022. Comparing moderation strategies in group chats with multi-user chatbots. In Proceedings of the 4th Conference on Conversational User Interfaces, CUI ’22, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Nicolas+Wagner%2C+Matthias+Kraus%2C+Tibor+Tonn%2C+and+Wolfgang+Minker%2E+2022%2E+Comparing+moderation+strategies+in+group+chats+with+multi%2Duser+chatbots%2E+In+Proceedings+of+the+4th+Conference+on+Conversational+U)
51. Wolfgang Wahlster. 2023. Understanding computational dialogue understanding. Philosophical Transactions of the Royal Society A, 381(2251):20220049. [find](https://scholar.google.com/scholar?q=Wolfgang+Wahlster%2E+2023%2E+Understanding+computational+dialogue+understanding%2E+Philosophical+Transactions+of+the+Royal+Society+A%2C+381%282251%29%3A20220049%2E)
52. Zekun Moore Wang, Zhongyuan Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Man Zhang, et al. 2023. [Rolellm: Benchmarking, eliciting, and enhancing role-playing abilities of large language models](https://md.research.elamur.ai/free/en/papers/wang-2023-rolellm-benchmarking-eliciting-enhancing-role/). arXiv preprint arXiv:2310.00746. [↗](https://arxiv.org/abs/2310.00746)
53. Albert Webson and Ellie Pavlick. 2022. [Do prompt-based models really understand the meaning of their prompts?](https://md.research.elamur.ai/free/en/papers/webson-2022-do-prompt-based-models-really/) In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2300–2344, Seattle, United States. Association for Computational Linguistics.
54. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in Neural Information Processing Systems, 35:24824–24837.
55. Jimmy Wei, Kurt Shuster, Arthur Szlam, Jason Weston, Jack Urbanek, and Mojtaba Komeili. 2023. Multi-party chat: Conversational agents in group settings with humans and models. arXiv preprint arXiv:2304.13835. [↗](https://arxiv.org/abs/2304.13835)
56. Xi Ye and Greg Durrett. 2022. [The unreliability of explanations in few-shot prompting for textual reasoning](https://md.research.elamur.ai/free/en/papers/ye-2022-unreliability-explanations-few-shot-prompting/). Advances in neural information processing systems, 35:30378–30392.
57. Zihao Zhao, Eric Wallace, Shi Feng, Dan Klein, and Sameer Singh. 2021. [Calibrate before use: Improving few-shot performance of language models](https://md.research.elamur.ai/free/en/papers/zhao-2021-calibrate-before-use-improving-few/). In International Conference on Machine Learning, pages 12697–12706. PMLR.
58. Ozan İrsoy, Rakesh Gosangi, Haimin Zhang, Mu-Hsin Wei, Peter Lund, Duccio Pappadopulo, Brendan Fahy, Neophytos Nephytou, and Camilo Ortiz. 2019. [Dialogue act classification in group chats with dag-lstms](https://md.research.elamur.ai/free/en/papers/irsoy-2019-dialogue-act-classification-group-chats/).

*Updated 2 November 2026*