---
title: "Irony Detection, Reasoning and Understanding in Zero-shot"
description: "The authors propose IDADP, a zero-shot prompting framework for LLMs (GPT and Gemini) that uses… 63 references, cited by 5 papers here."
authors: ["Peiling Yi", "Yuhan Xia", "Yunfei Long"]
year: 2025
venue: "arXiv:2501.16884"
source: "https://arxiv.org/abs/2501.16884"
doi: "10.48550/arxiv.2501.16884"
arxiv: "2501.16884"
licence: "arXiv non-exclusive distribution licence (read only, no redistribution)"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yi-2025-irony-detection-reasoning-understanding-zero/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yi-2025-irony-detection-reasoning-understanding-zero/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/11/) / Irony Detection, Reasoning and Understanding in Zero-shot Learning

# Irony Detection, Reasoning and Understanding in Zero-shot Learning

**Authors:** Peiling Yi, Yuhan Xia and [Yunfei Long](https://md.research.elamur.ai/free/en/authors/yunfei-long/) · **Year:** 2025 · **Venue:** arXiv:2501.16884 · **Licence:** [arXiv non-exclusive distribution licence (read only, no redistribution)](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2501.16884) · [PDF](https://arxiv.org/pdf/2501.16884) · [DOI 10.48550/arxiv.2501.16884](https://doi.org/10.48550/arxiv.2501.16884) · [arXiv 2501.16884](https://arxiv.org/abs/2501.16884) · [OpenAlex](https://openalex.org/W4406960621)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 5 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Irony on social media often says the opposite of what it means, and this can mislead downstream systems such as sentiment analysis, misinformation checking and recommendation. Existing irony detectors are usually trained on a single domain, transfer poorly to other platforms, rarely explain their decisions, and reduce the task to a yes/no label. The authors propose IDADP, a zero-shot prompting framework for LLMs (GPT and Gemini) that uses no ironic training examples.

IDADP works in two steps. First, the model is prompted to produce irony-focused background knowledge. That knowledge is then built into several task prompts, each aimed at a different facet of irony, and a vote combines their answers. The framework outputs three things: a binary irony decision, an explanation of the contrast or context behind it, and a literal, non-ironic restatement of the intended meaning.

Across six common irony datasets, IDADP beats six zero-shot baselines and comes close to three fine-tuned supervised models. This points to transparent irony handling that generalises across platforms.

## Key points
- The framework is named IDADP. It has an irony-focused knowledge extraction stage, a knowledge integration stage that builds task-specific prompts, and a voting step over the outputs.
- It was evaluated on six widely used irony detection datasets with two LLM families, GPT and Gemini. No ironic samples were used for training or as demonstrations.
- IDADP consistently outperforms six zero-shot baselines and approaches three fine-tuned supervised baselines. The exact scores fall in the omitted middle of the provided text.
- The task is split into detection (binary), reasoning (an explanation of the contrast or context) and understanding (rewriting into the intended non-ironic meaning). GPT's understanding ability is examined separately, and a qualitative error analysis identifies remaining challenges.
- The design draws on CoT, zero-shot "step by step" prompting, self-consistency and generated-knowledge prompting. The code is published at github.com/yipeiling/Irony.

## Interesting ideas
- Before classifying, have the model spell out what irony looks like (literal/intended contrast, exaggeration, praise of a bad situation), then feed those cues into the decision step; this turns a vague judgement into a checklist of named signals.
- Run several prompts, each focused on a different aspect, and combine them by vote; this damps the known sensitivity of LLMs to prompt wording and gives more stable labels.
- Treat understanding as producing a literal paraphrase that keeps the speaker's real intent, not just a label; this makes comprehension testable and usable by downstream tasks.
- Require three linked outputs (verdict, explanation of the contrast or context, intended meaning) so each decision is auditable and errors can be traced to the step that failed.
- Measure generalisation by testing one unchanged method on many datasets from different platforms, with fine-tuned supervised models as a reference ceiling.

## For Mova

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

- **I1** (frames): crate prag could keep an explicit inventory of irony cues (a positive evaluation attached to an undesirable state in the frame, hyperbole markers) and fire irony only when a named cue matches, so every irony flag carries its reason.
- **I2** (learn): LLM teacher tiers could label pragmatic phenomena with several aspect-specific prompts and accept a silver label only on majority agreement, much as witness parsers must agree on trees.
- **I3** (back): after prag marks an utterance as ironic, generation could render the inverted evaluation from the meaning graph as plain text, giving a human-checkable proof that the irony was resolved.
- **I4** (answer): readers answering questions about fables or tales with ironic narrators could report the literal claim, the detected contrast and the inferred intent as separate explainable steps.
- **I5** (learn): evaluation of the irony and implicature modules could use several out-of-domain sets plus a supervised upper bound, exposing overfitting to a single corpus.

*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 (2): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,685 works · [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 1,035 works

## Cite

Cite as: Peiling Yi, Yuhan Xia and Yunfei Long. 2025. Irony Detection, Reasoning and Understanding in Zero-shot Learning. arXiv:2501.16884.

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

```bibtex
@misc{yi2025irony,
  title = {{Irony Detection, Reasoning and Understanding in Zero-shot Learning}},
  author = {Peiling Yi, Yuhan Xia and Yunfei Long},
  year = {2025},
  doi = {10.48550/arxiv.2501.16884},
  eprint = {2501.16884},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2501.16884}
}
```

- [← previous InductionBench: LLMs Fail in the Simplest Complexity Class](https://md.research.elamur.ai/free/en/papers/hua-2025-inductionbench-llms-fail-simplest-complexity/)
- [next → It is not a piece of cake for GPT: Explaining Textual Entailment Recognition in the presence of Figurative Language](https://md.research.elamur.ai/free/en/papers/gallipoli-2025-it-is-not-piece-cake/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/11/)

## References

63 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. W. C. Booth, A rhetoric of irony. University of Chicago Press, 1974. [find](https://scholar.google.com/scholar?q=W%2E+C%2E+Booth%2C+A+rhetoric+of+irony%2E+University+of+Chicago+Press%2C+1974%2E)
2. J. Lear, A case for irony. Harvard University Press, 2011. [find](https://scholar.google.com/scholar?q=J%2E+Lear%2C+A+case+for+irony%2E+Harvard+University+Press%2C+2011%2E)
3. A. Joshi, P. Bhattacharyya, and M. J. Carman, “[Automatic sarcasm detection: A survey](https://md.research.elamur.ai/free/en/papers/joshi-2016-automatic-sarcasm-detection-survey/),” ACM Computing Surveys (CSUR), vol. 50, no. 5, pp. 1–22, 2017. [↗](https://doi.org/10.48550/arxiv.1602.03426)
4. J. Lucariello, “Situational irony: A concept of events gone awry.” Journal of Experimental Psychology: General, vol. 123, no. 2, p. 129, 1994. [↗](https://doi.org/10.1037//0096-3445.123.2.129)
5. A. Reyes, P. Rosso, and D. Buscaldi, “From humor recognition to irony detection: The figurative language of social media,” Data & Knowledge Engineering, vol. 74, pp. 1–12, 2012. [↗](https://doi.org/10.1016/j.datak.2012.02.005)
6. R. A. Potamias, G. Siolas, and A.-G. Stafylopatis, “[A transformer-based approach to irony and sarcasm detection](https://md.research.elamur.ai/free/en/papers/potamias-2019-transformer-based-approach-irony-sarcasm/),” Neural Computing and Applications, vol. 32, no. 23, pp. 17 309–17 320, 2020. [↗](https://doi.org/10.1007/s00521-020-05102-3)
7. H. Jang and D. Frassinelli, “[Generalizable sarcasm detection is just around the corner, of course!](https://md.research.elamur.ai/free/en/papers/jang-2024-generalizable-sarcasm-detection-is-just/)” arXiv preprint arXiv:2404.06357, 2024. [↗](https://arxiv.org/abs/2404.06357)
8. C. Van Hee, E. Lefever, and V. Hoste, “We usually don’t like going to the dentist: Using common sense to detect irony on twitter,” Computational Linguistics, vol. 44, no. 4, pp. 793–832, 2018. — [We Usually Don't Like Going to the Dentist: Using Common Sense to Detect Irony on Twitter](https://md.research.elamur.ai/free/en/papers/hee-2018-we-usually-don-t-like/)
9. I. A. Farha, S. Oprea, S. Wilson, and W. Magdy, “[Semeval-2022 task 6: isarcasmeval, intended sarcasm detection in english and arabic](https://md.research.elamur.ai/free/en/papers/farha-2022-semeval-2022-task-6-isarcasmeval/),” in The 16th International Workshop on Semantic Evaluation 2022. Association for Computational Linguistics, 2022, pp. 802–814.
10. C. Van Hee, E. Lefever, and V. Hoste, “[Semeval-2018 task 3: Irony detection in english tweets](https://md.research.elamur.ai/free/en/papers/hee-2018-semeval-2018-task-3-irony/),” in Proceedings of the 12th international workshop on semantic evaluation, 2018, pp. 39–50.
11. J. Yang, H. Jin, R. Tang, X. Han, Q. Feng, H. Jiang, S. Zhong, B. Yin, and X. Hu, “[Harnessing the power of llms in practice: A survey on chatgpt and beyond](https://md.research.elamur.ai/free/en/papers/yang-2023-harnessing-power-llms-practice-survey/),” ACM Transactions on Knowledge Discovery from Data, vol. 18, no. 6, pp. 1–32, 2024. [↗](https://doi.org/10.1145/3649506)
12. T. B. Brown, “[Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/),” arXiv preprint arXiv:2005.14165, 2020. [↗](https://arxiv.org/abs/2005.14165)
13. X. Cheng, J. Li, W. X. Zhao, and J.-R. Wen, “Chainlm: Empowering large language models with improved chain-of-thought prompting,” arXiv preprint arXiv:2403.14312, 2024. [↗](https://arxiv.org/abs/2403.14312)
14. J. Wei, X. Wang, D. Schuurmans, M. Bosma, F. Xia, E. Chi, Q. V. Le, D. Zhou et al., “[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, vol. 35, pp. 24 824–24 837, 2022.
15. W. Hariri, “Unlocking the potential of chatgpt: A comprehensive exploration of its applications, advantages, limitations, and future directions in natural language processing,” arXiv preprint arXiv:2304.02017, 2023. [↗](https://arxiv.org/abs/2304.02017)
16. L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray et al., “[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, vol. 35, pp. 27 730–27 744, 2022.
17. P. P. Ray, “Chatgpt: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope,” Internet of Things and Cyber-Physical Systems, vol. 3, pp. 121–154, 2023. [↗](https://doi.org/10.1016/j.iotcps.2023.04.003)
18. J. White, Q. Fu, S. Hays, M. Sandborn, C. Olea, H. Gilbert, A. Elnashar, J. Spencer-Smith, and D. C. Schmidt, “[A prompt pattern catalog to enhance prompt engineering with chatgpt](https://md.research.elamur.ai/free/en/papers/white-2023-prompt-pattern-catalog-enhance-prompt/),” arXiv preprint arXiv:2302.11382, 2023. [↗](https://arxiv.org/abs/2302.11382)
19. A. Azaria, R. Azoulay, and S. Reches, “Chatgpt is a remarkable tool—for experts,” Data Intelligence, vol. 6, no. 1, pp. 240–296, 2024. [↗](https://doi.org/10.1162/dint_a_00235)
20. S. K. Bharti, K. S. Babu, and S. K. Jena, “Parsing-based sarcasm sentiment recognition in twitter data,” in Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015, 2015, pp. 1373–1380. [find](https://scholar.google.com/scholar?q=S%2E+K%2E+Bharti%2C+K%2E+S%2E+Babu%2C+and+S%2E+K%2E+Jena%2C+%E2%80%9CParsing%2Dbased+sarcasm+sentiment+recognition+in+twitter+data%2C%E2%80%9D+in+Proceedings+of+the+2015+IEEE%2FACM+International+Conference+on+Advances+in+Social+Networks+Ana)
21. E. Riloff, A. Qadir, P. Surve, L. De Silva, N. Gilbert, and R. Huang, “[Sarcasm as contrast between a positive sentiment and negative situation](https://md.research.elamur.ai/free/en/papers/riloff-2013-sarcasm-as-contrast-between-positive/),” in Proceedings of the 2013 conference on empirical methods in natural language processing, 2013, pp. 704–714.
22. M. Mladenović, C. Krstev, J. Mitrović, and R. Stanković, “Using lexical resources for irony and sarcasm classification,” in Proceedings of the 8th Balkan Conference in Informatics, 2017, pp. 1–8. [find](https://scholar.google.com/scholar?q=M%2E+Mladenovic%CC%81%2C+C%2E+Krstev%2C+J%2E+Mitrovic%CC%81%2C+and+R%2E+Stankovic%CC%81%2C+%E2%80%9CUsing+lexical+resources+for+irony+and+sarcasm+classification%2C%E2%80%9D+in+Proceedings+of+the+8th+Balkan+Conference+in+Informatics%2C+2017%2C+pp%2E+1%E2%80%938%2E)
23. R. González-Ibánez, S. Muresan, and N. Wacholder, “[Identifying sarcasm in twitter: a closer look](https://md.research.elamur.ai/free/en/papers/ibanez-2011-identifying-sarcasm-twitter-closer-look/),” in Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, 2011, pp. 581–586.
24. D. G. Maynard and M. A. Greenwood, “[Who cares about sarcastic tweets? investigating the impact of sarcasm on sentiment analysis](https://md.research.elamur.ai/free/en/papers/maynard-2014-who-cares-about-sarcastic-tweets/),” in Lrec 2014 proceedings. ELRA, 2014.
25. J. Dimovska, M. Angelovska, D. Gjorgjevikj, and G. Madjarov, “Sarcasm and irony detection in english tweets,” in ICT Innovations 2018. Engineering and Life Sciences: 10th International Conference, ICT Innovations 2018, Ohrid, Macedonia, September 17–19, 2018, Proceedings 10. Springer, 2018, pp. 120–131. [find](https://scholar.google.com/scholar?q=J%2E+Dimovska%2C+M%2E+Angelovska%2C+D%2E+Gjorgjevikj%2C+and+G%2E+Madjarov%2C+%E2%80%9CSarcasm+and+irony+detection+in+english+tweets%2C%E2%80%9D+in+ICT+Innovations+2018%2E+Engineering+and+Life+Sciences%3A+10th+International+Conference%2C+ICT)
26. E. Fersini, F. A. Pozzi, and E. Messina, “Detecting irony and sarcasm in microblogs: The role of expressive signals and ensemble classifiers,” in 2015 IEEE international conference on data science and advanced analytics (DSAA). IEEE, 2015, pp. 1–8. [find](https://scholar.google.com/scholar?q=E%2E+Fersini%2C+F%2E+A%2E+Pozzi%2C+and+E%2E+Messina%2C+%E2%80%9CDetecting+irony+and+sarcasm+in+microblogs%3A+The+role+of+expressive+signals+and+ensemble+classifiers%2C%E2%80%9D+in+2015+IEEE+international+conference+on+data+science+and)
27. I. Hernández-Farı́as, J.-M. Benedı́, and P. Rosso, “Applying basic features from sentiment analysis for automatic irony detection,” in Pattern Recognition and Image Analysis: 7th Iberian Conference, IbPRIA 2015, Santiago de Compostela, Spain, June 17-19, 2015, Proceedings 7. Springer, 2015, pp. 337–344. [find](https://scholar.google.com/scholar?q=I%2E+Herna%CC%81ndez%2DFar%C4%B1%CC%81as%2C+J%2E%2DM%2E+Bened%C4%B1%CC%81%2C+and+P%2E+Rosso%2C+%E2%80%9CApplying+basic+features+from+sentiment+analysis+for+automatic+irony+detection%2C%E2%80%9D+in+Pattern+Recognition+and+Image+Analysis%3A+7th+Iberian+Conference%2C+)
28. J. Karoui, F. Benamara, V. Moriceau, N. Aussenac-Gilles, and L. H. Belguith, “[Towards a contextual pragmatic model to detect irony in tweets](https://md.research.elamur.ai/free/en/papers/karoui-2015-contextual-pragmatic-model-detect-irony/),” in 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015), vol. 2. ACL: Association for Computational Linguistics, 2015, pp. 644–650.
29. A. Kumar and G. Garg, “Empirical study of shallow and deep learning models for sarcasm detection using context in benchmark datasets,” Journal of ambient intelligence and humanized computing, vol. 14, no. 5, pp. 5327–5342, 2023. [find](https://scholar.google.com/scholar?q=A%2E+Kumar+and+G%2E+Garg%2C+%E2%80%9CEmpirical+study+of+shallow+and+deep+learning+models+for+sarcasm+detection+using+context+in+benchmark+datasets%2C%E2%80%9D+Journal+of+ambient+intelligence+and+humanized+computing%2C+vol%2E+14%2C)
30. Y.-H. Huang, H.-H. Huang, and H.-H. Chen, “Irony detection with attentive recurrent neural networks,” in Advances in Information Retrieval: 39th European Conference on IR Research, ECIR 2017, Aberdeen, UK, April 8-13, 2017, Proceedings 39. Springer, 2017, pp. 534–540. [find](https://scholar.google.com/scholar?q=Y%2E%2DH%2E+Huang%2C+H%2E%2DH%2E+Huang%2C+and+H%2E%2DH%2E+Chen%2C+%E2%80%9CIrony+detection+with+attentive+recurrent+neural+networks%2C%E2%80%9D+in+Advances+in+Information+Retrieval%3A+39th+European+Conference+on+IR+Research%2C+ECIR+2017%2C+Aberdeen)
31. R. Ahuja and S. C. Sharma, “Transformer-based word embedding with cnn model to detect sarcasm and irony,” Arabian Journal for Science and Engineering, vol. 47, no. 8, pp. 9379–9392, 2022. [↗](https://doi.org/10.1007/s13369-021-06193-3)
32. D. Olaniyan, R. O. Ogundokun, O. P. Bernard, J. Olaniyan, R. Maskeliūnas, and H. B. Akande, “Utilizing an attention-based lstm model for detecting sarcasm and irony in social media,” Computers, vol. 12, no. 11, p. 231, 2023. [↗](https://doi.org/10.3390/computers12110231)
33. M. Belal, J. She, and S. Wong, “Leveraging chatgpt as text annotation tool for sentiment analysis,” arXiv preprint arXiv:2306.17177, 2023. [↗](https://arxiv.org/abs/2306.17177)
34. M. Gole, W.-P. Nwadiugwu, and A. Miranskyy, “On sarcasm detection with openai gpt-based models,” arXiv preprint arXiv:2312.04642, 2023. [↗](https://arxiv.org/abs/2312.04642)
35. M. U. Aytekin and O. A. Erdem, “Generative pre-trained transformer (gpt) models for irony detection and classification,” in 2023 4th International Informatics and Software Engineering Conference (IISEC). IEEE, 2023, pp. 1–8. [find](https://scholar.google.com/scholar?q=M%2E+U%2E+Aytekin+and+O%2E+A%2E+Erdem%2C+%E2%80%9CGenerative+pre%2Dtrained+transformer+%28gpt%29+models+for+irony+detection+and+classification%2C%E2%80%9D+in+2023+4th+International+Informatics+and+Software+Engineering+Conference+%28IISE)
36. A. Radford, “Improving language understanding by generative pre-training,” 2018. [find](https://scholar.google.com/scholar?q=A%2E+Radford%2C+%E2%80%9CImproving+language+understanding+by+generative+pre%2Dtraining%2C%E2%80%9D+2018%2E)
37. A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever et al., “Language models are unsupervised multitask learners,” OpenAI blog, vol. 1, no. 8, p. 9, 2019. [find](https://scholar.google.com/scholar?q=A%2E+Radford%2C+J%2E+Wu%2C+R%2E+Child%2C+D%2E+Luan%2C+D%2E+Amodei%2C+I%2E+Sutskever+et+al%2E%2C+%E2%80%9CLanguage+models+are+unsupervised+multitask+learners%2C%E2%80%9D+OpenAI+blog%2C+vol%2E+1%2C+no%2E+8%2C+p%2E+9%2C+2019%2E)
38. T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa, “[Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/),” Advances in neural information processing systems, vol. 35, pp. 22 199–22 213, 2022.
39. X. Wang, J. Wei, D. Schuurmans, Q. Le, E. Chi, S. Narang, A. Chowdhery, and D. Zhou, “[Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/),” arXiv preprint arXiv:2203.11171, 2022. [↗](https://arxiv.org/abs/2203.11171)
40. Z. Zhang, A. Zhang, M. Li, and A. Smola, “[Automatic chain of thought prompting in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-automatic-chain-thought-prompting-large/),” arXiv preprint arXiv:2210.03493, 2022. [↗](https://arxiv.org/abs/2210.03493)
41. S. Yao, D. Yu, J. Zhao, I. Shafran, T. Griffiths, Y. Cao, and K. Narasimhan, “Tree of thoughts: Deliberate problem solving with large language models,” Advances in Neural Information Processing Systems, vol. 36, 2024. [find](https://scholar.google.com/scholar?q=S%2E+Yao%2C+D%2E+Yu%2C+J%2E+Zhao%2C+I%2E+Shafran%2C+T%2E+Griffiths%2C+Y%2E+Cao%2C+and+K%2E+Narasimhan%2C+%E2%80%9CTree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2C%E2%80%9D+Advances+in+Neural+Information+Processing+System)
42. J. Long, “Large language model guided tree-of-thought,” arXiv preprint arXiv:2305.08291, 2023. [↗](https://arxiv.org/abs/2305.08291)
43. D. Hulbert, “Using tree-of-thought prompting to boost chatgpt’s reasoning,” 2023. [find](https://scholar.google.com/scholar?q=D%2E+Hulbert%2C+%E2%80%9CUsing+tree%2Dof%2Dthought+prompting+to+boost+chatgpt%E2%80%99s+reasoning%2C%E2%80%9D+2023%2E)
44. J. Liu, A. Liu, X. Lu, S. Welleck, P. West, R. L. Bras, Y. Choi, and H. Hajishirzi, “Generated knowledge prompting for commonsense reasoning,” arXiv preprint arXiv:2110.08387, 2021. [↗](https://arxiv.org/abs/2110.08387)
45. C. Yang, X. Wang, Y. Lu, H. Liu, Q. V. Le, D. Zhou, and X. Chen, “[Large language models as optimizers](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-optimizers/),” 2023. [↗](https://doi.org/10.48550/arxiv.2309.03409)
46. C. Fernando, D. Banarse, H. Michalewski, S. Osindero, and T. Rocktäschel, “[Promptbreeder: Self-referential self-improvement via prompt evolution](https://md.research.elamur.ai/free/en/papers/fernando-2023-promptbreeder-self-referential-self-improvement/),” arXiv preprint arXiv:2309.16797, 2023. [↗](https://arxiv.org/abs/2309.16797)
47. Y. Zhou, A. I. Muresanu, Z. Han, K. Paster, S. Pitis, H. Chan, and J. Ba, “[Large language models are human-level prompt engineers](https://md.research.elamur.ai/free/en/papers/zhou-2022-large-language-models-human-level/),” arXiv preprint arXiv:2211.01910, 2022. [↗](https://arxiv.org/abs/2211.01910)
48. W. Kong, S. A. Hombaiah, M. Zhang, Q. Mei, and M. Bendersky, “Prewrite: Prompt rewriting with reinforcement learning,” arXiv preprint arXiv:2401.08189, 2024. [↗](https://arxiv.org/abs/2401.08189)
49. L. Wang, W. Xu, Y. Lan, Z. Hu, Y. Lan, R. K.-W. Lee, and E.-P. Lim, “Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models,” arXiv preprint arXiv:2305.04091, 2023. [↗](https://arxiv.org/abs/2305.04091)
50. J. Wei, M. Bosma, V. Y. Zhao, K. Guu, A. W. Yu, B. Lester, N. Du, A. M. Dai, and Q. V. Le, “[Finetuned language models are zero-shot learners](https://md.research.elamur.ai/free/en/papers/wei-2021-finetuned-language-models-zero-shot/),” arXiv preprint arXiv:2109.01652, 2021. [↗](https://arxiv.org/abs/2109.01652)
51. V. Sanh, A. Webson, C. Raffel, S. H. Bach, L. Sutawika, Z. Alyafeai, A. Chaffin, A. Stiegler, T. L. Scao, A. Raja et al., “[Multitask prompted training enables zero-shot task generalization](https://md.research.elamur.ai/free/en/papers/sanh-2021-multitask-prompted-training-enables-zero/),” arXiv preprint arXiv:2110.08207, 2021. [↗](https://arxiv.org/abs/2110.08207)
52. S. Oraby, V. Harrison, L. Reed, E. Hernandez, E. Riloff, and M. Walker, “[Creating and characterizing a diverse corpus of sarcasm in dialogue](https://md.research.elamur.ai/free/en/papers/oraby-2016-creating-characterizing-diverse-corpus-sarcasm/),” arXiv preprint arXiv:1709.05404, 2017. [↗](https://arxiv.org/abs/1709.05404)
53. B. C. Wallace, L. Kertz, E. Charniak et al., “[Humans require context to infer ironic intent (so computers probably do, too)](https://md.research.elamur.ai/free/en/papers/wallace-2014-humans-require-context-infer-ironic/),” in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2014, pp. 512–516.
54. J. Devlin, “[Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/),” arXiv preprint arXiv:1810.04805, 2018. [↗](https://arxiv.org/abs/1810.04805)
55. Y. Liu, “[Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/),” arXiv preprint arXiv:1907.11692, 2019. [↗](https://arxiv.org/abs/1907.11692)
56. K. Song, X. Tan, T. Qin, J. Lu, and T.-Y. Liu, “[Mpnet: Masked and permuted pre-training for language understanding](https://md.research.elamur.ai/free/en/papers/song-2020-mpnet-masked-permuted-pre-training/),” Advances in neural information processing systems, vol. 33, pp. 16 857–16 867, 2020. [↗](https://doi.org/10.48550/arxiv.2004.09297)
57. Q. Zeng and A.-R. Li, “[A survey in automatic irony processing: Linguistic, cognitive, and multi-x perspectives](https://md.research.elamur.ai/free/en/papers/zeng-2022-survey-automatic-irony-processing-linguistic/),” arXiv preprint arXiv:2209.04712, 2022. [↗](https://arxiv.org/abs/2209.04712)
58. S. Shalev-Shwartz and S. Ben-David, Understanding machine learning: From theory to algorithms. Cambridge university press, 2014. [find](https://scholar.google.com/scholar?q=S%2E+Shalev%2DShwartz+and+S%2E+Ben%2DDavid%2C+Understanding+machine+learning%3A+From+theory+to+algorithms%2E+Cambridge+university+press%2C+2014%2E)
59. N. Duan, D. Tang, and M. Zhou, “Machine reasoning: Technology, dilemma and future,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Tutorial Abstracts, 2020, pp. 1–6. [find](https://scholar.google.com/scholar?q=N%2E+Duan%2C+D%2E+Tang%2C+and+M%2E+Zhou%2C+%E2%80%9CMachine+reasoning%3A+Technology%2C+dilemma+and+future%2C%E2%80%9D+in+Proceedings+of+the+2020+Conference+on+Empirical+Methods+in+Natural+Language+Processing%3A+Tutorial+Abstracts%2C+2020%2C)
60. R. Bruntsch and W. Ruch, “Studying irony detection beyond ironic criticism: Let’s include ironic praise,” Frontiers in Psychology, vol. 8, p. 606, 2017. [find](https://scholar.google.com/scholar?q=R%2E+Bruntsch+and+W%2E+Ruch%2C+%E2%80%9CStudying+irony+detection+beyond+ironic+criticism%3A+Let%E2%80%99s+include+ironic+praise%2C%E2%80%9D+Frontiers+in+Psychology%2C+vol%2E+8%2C+p%2E+606%2C+2017%2E)
61. Y. Zhang, “Meta prompting for agi systems,” arXiv preprint arXiv:2311.11482, 2023. [↗](https://arxiv.org/abs/2311.11482)
62. L. Wang, W. Xu, Y. Lan, Z. Hu, Y. Lan, R. Lee, and E. Lim, “Plan-and-solve prompting: improving zero-shot chain-of-thought reasoning by large language models (2023),” arXiv preprint arXiv:2305.04091, 2024. [↗](https://arxiv.org/abs/2305.04091)
63. J. N. Farr, J. J. Jenkins, and D. G. Paterson, “Simplification of flesch reading ease formula.” Journal of applied psychology, vol. 35, no. 5, p. 333, 1951. [↗](https://doi.org/10.1037/h0062427)

*Updated 2 November 2026*