---
title: "Adaptive Originality Filtering — Le 2025"
description: "The authors propose Adaptive Originality Filtering (AOF), a prompting loop that needs no fine-tuning. 103 references, cited by 1 paper here."
authors: ["Duy Le", "Kent Ziti", "Evan Girard-Sun", "Bakr Bouhaya", "Sean O'Brien", "Vasu Sharma", "Kevin Zhu"]
year: 2025
venue: "arXiv:2508.18709"
source: "https://arxiv.org/abs/2508.18709"
doi: "10.48550/arxiv.2508.18709"
arxiv: "2508.18709"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/le-2025-adaptive-originality-filtering-rejection-based/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/le-2025-adaptive-originality-filtering-rejection-based/)

[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/3/) / Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation

# Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation

**Authors:** Duy Le, Kent Ziti, Evan Girard-Sun, Bakr Bouhaya, Sean O'Brien, Vasu Sharma and Kevin Zhu · **Year:** 2025 · **Venue:** arXiv:2508.18709 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2508.18709) · [PDF](https://arxiv.org/pdf/2508.18709) · [DOI 10.48550/arxiv.2508.18709](https://doi.org/10.48550/arxiv.2508.18709) · [arXiv 2508.18709](https://arxiv.org/abs/2508.18709) · [OpenAlex](https://openalex.org/W4416391401)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 140,884 papers whose bibliographies we read

## Summary
When LLMs are asked to write riddles in several languages, they tend to reuse familiar templates or repeat riddles they memorized during pretraining. Common metrics such as BLEU or BERTScore reveal little about originality or cultural fit. The authors propose Adaptive Originality Filtering (AOF), a prompting loop that needs no fine-tuning. Each candidate riddle is embedded with MiniLM and compared by cosine similarity against reference riddles from BiRdQA. If the similarity is above 0.75, the candidate is discarded and regenerated, for up to k attempts. Prompt-level constraints on structure and literary devices are added on top. To score the output, they define RiddleScore, a weighted combination of novelty, Distinct-2 diversity, perplexity-based fluency and BERTScore alignment with the answer, with weights fitted to human ratings. They test GPT-4o, LLaMA 3.1 and DeepSeek Reasoning on English, Chinese, Arabic, Japanese and French. Compared with zero-shot, few-shot, CoT and adversarial prompting, AOF gives less repetitive, more varied riddles and higher human ratings for fluency, creativity and cultural fit. The practical lesson is that a cheap generate-and-reject filter, paired with a human-calibrated metric, can steer creative generation away from memorized material.

## Key points
- The rejection threshold θ = 0.75 comes from a sensitivity study. Lower values let templates leak through, and higher values raise the generation failure rate by 14%.
- GPT-4o with AOF in Japanese reaches Self-BLEU 0.177 (−63.4%) and Distinct-2 0.915. RiddleScore improves by up to +57.1% in Arabic.
- RiddleScore weights are α=0.30 (novelty), β=0.20 (diversity), γ=0.30 (fluency) and δ=0.20 (alignment). They were found by grid search on a 120-item dev set and raise Spearman ρ with human scores from 0.71 (uniform weights) to 0.83.
- The gains from AOF are larger for fine-tuned models than for pretrained ones. Chinese shows the largest gain: RiddleScore rises from 0.453 to 0.728 (+48.3%) and human ratings from 3.91 to 4.50.
- The data is BiRdQA (6,614 English and 8,751 Chinese multiple-choice riddles), decoded at temperature 0.7. The authors note several limitations:
  - lower-resource languages are not covered;
  - inter-annotator agreement analysis was limited;
  - cosine filtering can miss subtle redundancy.

## Interesting ideas
- Generation is wrapped in an external accept/reject loop: each output is embedded, compared against a reference pool, and retried if it is too close to something already known, with no change to the model.
- Novelty is measured as embedding distance from a known corpus, which acts as a detector of memorized or copied output.
- The composite metric's weights are chosen by maximizing rank correlation with a small set of human ratings, and compared against a uniform-weight baseline.
- The filtering threshold is picked by a sweep that tracks both output quality and failure rate, rather than being fixed by intuition.
- The metric includes a component that checks whether the generated text actually points to its intended answer, not only whether it is fluent and new.

## For Mova

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

- **I1** (back): Mova's generator could check paraphrases or compressor outputs against the source text and resample when the "new" wording just copies the input.
- **I2** (learn): LLM-teacher examples could be screened against existing treebank and test sentences, so that near-duplicates do not quietly inflate training or evaluation data.
- **I3** (learn): Mova's per-stage evaluation scores could be combined into one figure whose weights are fitted to a small hand-judged set, with uniform weights reported as a control.
- **I4** (learn): confidence cutoffs for accepting silver data agreed by several witness parsers could be tuned the same way, trading agreement quality against how much data gets discarded.
- **I5** (answer): generated test questions or word problems could be checked by solving them with Mova's own reader and keeping only items whose derived answer matches the intended one.

*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 (1): [🗣️ Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/) · 4,876 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 1,079 works · [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 388 works

## Cite

Cite as: Duy Le, Kent Ziti, Evan Girard-Sun, Bakr Bouhaya, Sean O'Brien, Vasu Sharma and Kevin Zhu. 2025. Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation. arXiv:2508.18709.

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

```bibtex
@misc{le2025adaptive,
  title = {{Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generation}},
  author = {Duy Le, Kent Ziti, Evan Girard-Sun, Bakr Bouhaya, Sean O'Brien, Vasu Sharma and Kevin Zhu},
  year = {2025},
  doi = {10.48550/arxiv.2508.18709},
  eprint = {2508.18709},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2508.18709}
}
```

- [← previous A Derivational ChainBank for Modern Standard Arabic](https://md.research.elamur.ai/free/en/papers/marzouk-2025-derivational-chainbank-modern-standard-arabic/)
- [next → Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines](https://md.research.elamur.ai/free/en/papers/sibaee-2025-advancing-arabic-reverse-dictionary-systems/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/3/)

## References

103 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abu Uthman Amr ibn Bahr Al-Jahiz. 869. Clarity and Eloquence (Al-Bayan wa Al-Tabyin). Basra. Original classical Arabic manuscript; various modern editions available. Abd al-Karim Al-Khatib. 1988. The Art of Riddles in Arabic Literature. Dar Al-Fikr, Beirut. [find](https://scholar.google.com/scholar?q=Abu+Uthman+Amr+ibn+Bahr+Al%2DJahiz%2E+869%2E+Clarity+and+Eloquence+%28Al%2DBayan+wa+Al%2DTabyin%29%2E+Basra%2E+Original+classical+Arabic+manuscript%3B+various+modern+editions+available%2E+Abd+al%2DKarim+Al%2DKhatib%2E+1988%2E+The+)
2. Muhammad Al-Marzouki. 2012. The Poetics of Ambiguity and Interpretation in Modern Arabic Poetry. Dar Kunooz Al-Maarifa, Amman. [find](https://scholar.google.com/scholar?q=Muhammad+Al%2DMarzouki%2E+2012%2E+The+Poetics+of+Ambiguity+and+Interpretation+in+Modern+Arabic+Poetry%2E+Dar+Kunooz+Al%2DMaarifa%2C+Amman%2E)
3. Tran Nguyen An. 2023. Hilbert multiplicity and irreducible multiplicity of idealizations. arXiv preprint arXiv:2311.04719. [↗](https://arxiv.org/abs/2311.04719)
4. Dalia Antar. 2023. The effectiveness of using chatgpt4 in creative writing in arabic: Poetry and short story as a model. Information Sciences Letters, 12(12):2445–2459. [find](https://scholar.google.com/scholar?q=Dalia+Antar%2E+2023%2E+The+effectiveness+of+using+chatgpt4+in+creative+writing+in+arabic%3A+Poetry+and+short+story+as+a+model%2E+Information+Sciences+Letters%2C+12%2812%29%3A2445%E2%80%932459%2E)
5. Anirudh Atmakuru, Jatin Nainani, Rohith Siddhartha Reddy Bheemreddy, Anirudh Lakkaraju, Zonghai Yao, Hamed Zamani, and Haw-Shiuan Chang. 2024. Cs4: Measuring the creativity of large language models automatically by controlling the number of story-writing constraints. arXiv preprint arXiv:2410.04197. [↗](https://arxiv.org/abs/2410.04197)
6. Salvatore Attardo. 1994. Linguistic Theories of Humor. Walter de Gruyter. [find](https://scholar.google.com/scholar?q=Salvatore+Attardo%2E+1994%2E+Linguistic+Theories+of+Humor%2E+Walter+de+Gruyter%2E)
7. Santiago Adrian Aytes, Jihun Baek, and Sung Ju Hwang. 2025. Sketch-of-thought: Efficient llm reasoning with adaptive cognitive-inspired sketching. arXiv preprint arXiv:2503.05179. [↗](https://arxiv.org/abs/2503.05179)
8. Bhuwan Bhatt and Valeriia Kuka. 2025. Llm parameters explained: A practical guide with examples for openai api in python. LearnPrompting blog. Available: [https://learnprompting.org/](https://learnprompting.org/) blog/llm-parameters. [↗](https://learnprompting.org/)
9. Kim Binsted. 1996. Machine humour: An implemented model of puns. Ph.D. thesis, University of Edinburgh. [find](https://scholar.google.com/scholar?q=Kim+Binsted%2E+1996%2E+Machine+humour%3A+An+implemented+model+of+puns%2E+Ph%2ED%2E+thesis%2C+University+of+Edinburgh%2E)
10. Tom B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020a. Language models are few-shot learners. arXiv preprint arXiv:2005.14165. [↗](https://arxiv.org/abs/2005.14165) [our card](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
11. Tom B. Brown, Benjamin Mann, and Nick et al. Ryder. 2020b. Language models are few-shot learners. In NeurIPS. [our card](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/)
12. Sahan Bulathwela, María Pérez-Ortiz, Catherine Holloway, Mutlu Cukurova, and John Shawe-Taylor. 2024. Artificial intelligence alone will not democratise education: On educational inequality, techno-solutionism and inclusive tools. Sustainability, 16(2):781. [find](https://scholar.google.com/scholar?q=Sahan+Bulathwela%2C+Mar%C3%ADa+P%C3%A9rez%2DOrtiz%2C+Catherine+Holloway%2C+Mutlu+Cukurova%2C+and+John+Shawe%2DTaylor%2E+2024%2E+Artificial+intelligence+alone+will+not+democratise+education%3A+On+educational+inequality%2C+techno%2Dso)
13. Aoife Cahill. 2009. Evaluation metrics for natural language generation. In ENLG. [find](https://scholar.google.com/scholar?q=Aoife+Cahill%2E+2009%2E+Evaluation+metrics+for+natural+language+generation%2E+In+ENLG%2E)
14. Aoife Cahill, Martin Forst, et al. 2009. Evaluation metrics for natural language generation. In ENLG. [find](https://scholar.google.com/scholar?q=Aoife+Cahill%2C+Martin+Forst%2C+et+al%2E+2009%2E+Evaluation+metrics+for+natural+language+generation%2E+In+ENLG%2E)
15. Tuhin Chakrabarty, Debanjan Ghosh, and Smaranda Muresan. 2021. Mermaid: Metaphor generation with symbolism and discriminative decoding. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics, pages 866–879. [find](https://scholar.google.com/scholar?q=Tuhin+Chakrabarty%2C+Debanjan+Ghosh%2C+and+Smaranda+Muresan%2E+2021%2E+Mermaid%3A+Metaphor+generation+with+symbolism+and+discriminative+decoding%2E+In+Proceedings+of+the+2021+Conference+of+the+North+American+Chap)
16. Winnie Chan. 1996. The riddle and the enigma: Traditional genres in french oral culture. Marvels & Tales, 10(1):15–27. [find](https://scholar.google.com/scholar?q=Winnie+Chan%2E+1996%2E+The+riddle+and+the+enigma%3A+Traditional+genres+in+french+oral+culture%2E+Marvels+%26+Tales%2C+10%281%29%3A15%E2%80%9327%2E)
17. Yu Chen and Tania Avgustinova. 2021. Are language-agnostic sentence representations actually language-agnostic? In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 274–280. [find](https://scholar.google.com/scholar?q=Yu+Chen+and+Tania+Avgustinova%2E+2021%2E+Are+language%2Dagnostic+sentence+representations+actually+language%2Dagnostic%3F+In+Proceedings+of+the+International+Conference+on+Recent+Advances+in+Natural+Language+Pr)
18. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116. [↗](https://arxiv.org/abs/1911.02116)
19. Yuwei Dang, Zhiheng Lin, Jiale Ma, Wayne Xin Zhao, and Ji-Rong Wen. 2022. Evaluating the creativity of text generation models. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1561–1574. [find](https://scholar.google.com/scholar?q=Yuwei+Dang%2C+Zhiheng+Lin%2C+Jiale+Ma%2C+Wayne+Xin+Zhao%2C+and+Ji%2DRong+Wen%2E+2022%2E+Evaluating+the+creativity+of+text+generation+models%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+EMNLP+2022%2C)
20. Jean Delisle. 1999. Translation and the poetic function: The influence of linguistic and literary theories on translation studies. University of Ottawa Press. [find](https://scholar.google.com/scholar?q=Jean+Delisle%2E+1999%2E+Translation+and+the+poetic+function%3A+The+influence+of+linguistic+and+literary+theories+on+translation+studies%2E+University+of+Ottawa+Press%2E)
21. P. V. DiStefano and J. D. Patterson. 2024. Automatic scoring of metaphor creativity with large language models. Creativity Research Journal. [find](https://scholar.google.com/scholar?q=P%2E+V%2E+DiStefano+and+J%2E+D%2E+Patterson%2E+2024%2E+Automatic+scoring+of+metaphor+creativity+with+large+language+models%2E+Creativity+Research+Journal%2E)
22. Ziwei Dou, Xiaoyu Ye, Xiang Ren, and Yue Zhang. 2022. Scill: Structured chain-of-thought for interpretable language learning. arXiv preprint arXiv:2210.01206. [↗](https://arxiv.org/abs/2210.01206)
23. Philipp Dufter. 2021a. Distributed Representations for Multilingual Language Processing. Ph.D. thesis, LMU Munich. [find](https://scholar.google.com/scholar?q=Philipp+Dufter%2E+2021a%2E+Distributed+Representations+for+Multilingual+Language+Processing%2E+Ph%2ED%2E+thesis%2C+LMU+Munich%2E)
24. Philipp Dufter. 2021b. Distributed representations for multilingual language processing. Ph.D. thesis, lmu. [find](https://scholar.google.com/scholar?q=Philipp+Dufter%2E+2021b%2E+Distributed+representations+for+multilingual+language+processing%2E+Ph%2ED%2E+thesis%2C+lmu%2E)
25. Encyclopædia Britannica. 2025. Internal rhyme. Internal rhyme: rhyme within a line enhances cohesion and rhythm in poetry. [find](https://scholar.google.com/scholar?q=Encyclop%C3%A6dia+Britannica%2E+2025%2E+Internal+rhyme%2E+Internal+rhyme%3A+rhyme+within+a+line+enhances+cohesion+and+rhythm+in+poetry%2E)
26. Ilan Falkum. 2009. A pragmatic account of the interpretation of figurative language. UCL Working Papers in Linguistics, 21:55–77. [find](https://scholar.google.com/scholar?q=Ilan+Falkum%2E+2009%2E+A+pragmatic+account+of+the+interpretation+of+figurative+language%2E+UCL+Working+Papers+in+Linguistics%2C+21%3A55%E2%80%9377%2E)
27. Angela Fan, Mike Lewis, and Yann Dauphin. 2018. Hierarchical neural story generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 889–898. [find](https://scholar.google.com/scholar?q=Angela+Fan%2C+Mike+Lewis%2C+and+Yann+Dauphin%2E+2018%2E+Hierarchical+neural+story+generation%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+889%E2%80%93898%2E)
28. Gilles Fauconnier and Mark Turner. 2002. The Way We Think: Conceptual Blending and the Mind’s Hidden Complexities. Basic Books. [find](https://scholar.google.com/scholar?q=Gilles+Fauconnier+and+Mark+Turner%2E+2002%2E+The+Way+We+Think%3A+Conceptual+Blending+and+the+Mind%E2%80%99s+Hidden+Complexities%2E+Basic+Books%2E)
29. Dedre Gentner. 1983. Structure-mapping: A theoretical framework for analogy. Cognitive Science, 7(2):155–170. [find](https://scholar.google.com/scholar?q=Dedre+Gentner%2E+1983%2E+Structure%2Dmapping%3A+A+theoretical+framework+for+analogy%2E+Cognitive+Science%2C+7%282%29%3A155%E2%80%93170%2E)
30. Marjan Ghazvininejad, Xing Shi, Jay Priyadarshi, and Kevin Knight. 2017. Hafez: An interactive poetry generation system. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics-System Demonstrations, pages 43–48. [find](https://scholar.google.com/scholar?q=Marjan+Ghazvininejad%2C+Xing+Shi%2C+Jay+Priyadarshi%2C+and+Kevin+Knight%2E+2017%2E+Hafez%3A+An+interactive+poetry+generation+system%2E+In+Proceedings+of+the+55th+Annual+Meeting+of+the+Association+for+Computational+)
31. Panagiotis Giadikiaroglou, Maria Lymperaiou, Giorgos Filandrianos, and Giorgos Stamou. 2024. Puzzle solving using reasoning of large language models: A survey. arXiv preprint arXiv:2402.11291. [↗](https://arxiv.org/abs/2402.11291) [our card](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/)
32. Ethan Heavey, James Hughes, and Milton King. 2024. Stfx-nlp at semeval-2024 task 9: Brainteaser: Three unsupervised riddle-solvers. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 28–33. [find](https://scholar.google.com/scholar?q=Ethan+Heavey%2C+James+Hughes%2C+and+Milton+King%2E+2024%2E+Stfx%2Dnlp+at+semeval%2D2024+task+9%3A+Brainteaser%3A+Three+unsupervised+riddle%2Dsolvers%2E+In+Proceedings+of+the+18th+International+Workshop+on+Semantic+Evalua)
33. Bernd Heine and Tania Kuteva. 2007. The Genesis of Grammar: A Reconstruction. Oxford University Press. [find](https://scholar.google.com/scholar?q=Bernd+Heine+and+Tania+Kuteva%2E+2007%2E+The+Genesis+of+Grammar%3A+A+Reconstruction%2E+Oxford+University+Press%2E)
34. Zhongzhan Huang, Shanshan Zhong, Pan Zhou, Shanghua Gao, Marinka Zitnik, and Liang Lin. 2025. A causality-aware paradigm for evaluating creativity of multimodal large language models. IEEE Transactions on Pattern Analysis and Machine Intelligence. [find](https://scholar.google.com/scholar?q=Zhongzhan+Huang%2C+Shanshan+Zhong%2C+Pan+Zhou%2C+Shanghua+Gao%2C+Marinka+Zitnik%2C+and+Liang+Lin%2E+2025%2E+A+causality%2Daware+paradigm+for+evaluating+creativity+of+multimodal+large+language+models%2E+IEEE+Transaction)
35. Manaf Ismayilzada, Dilan Circi, Jaakko Sälevä, and Hakan Sirin. 2024. Evaluating morphological compositional generalization in large language models. arXiv preprint arXiv:2410.12656. [↗](https://arxiv.org/abs/2410.12656)
36. Arun et al. Kabra. 2023. Multi-lingual and multi-cultural figurative language understanding. arXiv preprint arXiv:2305.16171. [↗](https://arxiv.org/abs/2305.16171)
37. Hiroko Kawamura. 2016. Cultural modes of reasoning in japanese riddles and proverbs. Japanese Language and Literature, 50(1):1–22. [find](https://scholar.google.com/scholar?q=Hiroko+Kawamura%2E+2016%2E+Cultural+modes+of+reasoning+in+japanese+riddles+and+proverbs%2E+Japanese+Language+and+Literature%2C+50%281%29%3A1%E2%80%9322%2E)
38. Arthur Koestler. 1964. The act of creation. Macmillan. [find](https://scholar.google.com/scholar?q=Arthur+Koestler%2E+1964%2E+The+act+of+creation%2E+Macmillan%2E)
39. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Tanaka. 2022. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems. [our card](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/)
40. Kalpesh Krishna, Ari Holtzman, Daniel Khashabi, Antoine Bosselut, Hannaneh Hajishirzi, and Yejin Choi. 2023. Reflexion: Language agents with verbal reinforcement learning. arXiv preprint arXiv:2303.11366. [↗](https://arxiv.org/abs/2303.11366) [our card](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/)
41. Huiyuan Lai, Jiali Mao, Antonio Toral, and Malvina Nissim. 2022. Human judgement as a compass to navigate automatic metrics for formality transfer. In HumEval. [find](https://scholar.google.com/scholar?q=Huiyuan+Lai%2C+Jiali+Mao%2C+Antonio+Toral%2C+and+Malvina+Nissim%2E+2022%2E+Human+judgement+as+a+compass+to+navigate+automatic+metrics+for+formality+transfer%2E+In+HumEval%2E)
42. George Lakoff and Mark Johnson. 1980. Metaphors We Live By. University of Chicago Press. [find](https://scholar.google.com/scholar?q=George+Lakoff+and+Mark+Johnson%2E+1980%2E+Metaphors+We+Live+By%2E+University+of+Chicago+Press%2E)
43. George Lakoff and Mark Johnson. 1999. Metaphor as language and thought. In Cognitive Semantics. Cambridge University Press. [find](https://scholar.google.com/scholar?q=George+Lakoff+and+Mark+Johnson%2E+1999%2E+Metaphor+as+language+and+thought%2E+In+Cognitive+Semantics%2E+Cambridge+University+Press%2E)
44. Guillaume Lample and Alexis Conneau. 2019. Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291. [↗](https://arxiv.org/abs/1901.07291)
45. Meisin Lee. 2025. Optimizing legal text summarization through dynamic retrieval-augmented generation. Symmetry. [find](https://scholar.google.com/scholar?q=Meisin+Lee%2E+2025%2E+Optimizing+legal+text+summarization+through+dynamic+retrieval%2Daugmented+generation%2E+Symmetry%2E)
46. Marc Leman. 2013. Figures et fictions: Les formes de l’imaginaire en littérature française. Presses Universitaires de France. [find](https://scholar.google.com/scholar?q=Marc+Leman%2E+2013%2E+Figures+et+fictions%3A+Les+formes+de+l%E2%80%99imaginaire+en+litt%C3%A9rature+fran%C3%A7aise%2E+Presses+Universitaires+de+France%2E)
47. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pages 110–119, San Diego, CA, USA. Association for Computational Linguistics. [our card](https://md.research.elamur.ai/free/en/papers/li-2016-diversity-promoting-objective-function-neural/)
48. Xiaorong Li. 2008. Riddles and wordplay in chinese folklore: A cultural and linguistic perspective. Folklore Studies. [find](https://scholar.google.com/scholar?q=Xiaorong+Li%2E+2008%2E+Riddles+and+wordplay+in+chinese+folklore%3A+A+cultural+and+linguistic+perspective%2E+Folklore+Studies%2E)
49. Yafu Li, Zhilin Wang, Leyang Cui, Wei Bi, Shuming Shi, and Yue Zhang. 2024. Spotting ai’s touch: Identifying llm-paraphrased spans in text. In Findings of ACL. [find](https://scholar.google.com/scholar?q=Yafu+Li%2C+Zhilin+Wang%2C+Leyang+Cui%2C+Wei+Bi%2C+Shuming+Shi%2C+and+Yue+Zhang%2E+2024%2E+Spotting+ai%E2%80%99s+touch%3A+Identifying+llm%2Dparaphrased+spans+in+text%2E+In+Findings+of+ACL%2E)
50. Yujia Li, Krishnamurthy Sreenivasan, Andreas Giannou, et al. 2023. Dissecting chain-of-thought: Compositionality through in-context filtering and learning. In Advances in Neural Information Processing Systems (NeurIPS). [find](https://scholar.google.com/scholar?q=Yujia+Li%2C+Krishnamurthy+Sreenivasan%2C+Andreas+Giannou%2C+et+al%2E+2023%2E+Dissecting+chain%2Dof%2Dthought%3A+Compositionality+through+in%2Dcontext+filtering+and+learning%2E+In+Advances+in+Neural+Information+Processing)
51. Emmy Liu, Chenxuan Cui, Kenneth Zheng, and Graham Neubig. 2022a. Testing the ability of language models to interpret figurative language. NAACL. [find](https://scholar.google.com/scholar?q=Emmy+Liu%2C+Chenxuan+Cui%2C+Kenneth+Zheng%2C+and+Graham+Neubig%2E+2022a%2E+Testing+the+ability+of+language+models+to+interpret+figurative+language%2E+NAACL%2E)
52. Emmy Liu, Chenxuan Cui, Kenneth Zheng, and Graham Neubig. 2022b. Testing the ability of language models to interpret figurative language. In Proceedings of NAACL-HLT 2022, pages 4437–4452. [find](https://scholar.google.com/scholar?q=Emmy+Liu%2C+Chenxuan+Cui%2C+Kenneth+Zheng%2C+and+Graham+Neubig%2E+2022b%2E+Testing+the+ability+of+language+models+to+interpret+figurative+language%2E+In+Proceedings+of+NAACL%2DHLT+2022%2C+pages+4437%E2%80%934452%2E)
53. Xiaofan Lu, Yixiao Zeng, Feiyang Ma, Zixu Yu, and Marco Levorato. 2024. Improving multi-candidate speculative decoding. In ICLR. [find](https://scholar.google.com/scholar?q=Xiaofan+Lu%2C+Yixiao+Zeng%2C+Feiyang+Ma%2C+Zixu+Yu%2C+and+Marco+Levorato%2E+2024%2E+Improving+multi%2Dcandidate+speculative+decoding%2E+In+ICLR%2E)
54. Aman Madaan, Bill Yuchen Lin, Xinyi Liu, Xudong Fu, Peggy Qian, Prahal Arora Bhargava, Ashish Sabharwal, and Hannaneh Hajishirzi. 2023. Self-refine: Iterative refinement with self-feedback. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Bill+Yuchen+Lin%2C+Xinyi+Liu%2C+Xudong+Fu%2C+Peggy+Qian%2C+Prahal+Arora+Bhargava%2C+Ashish+Sabharwal%2C+and+Hannaneh+Hajishirzi%2E+2023%2E+Self%2Drefine%3A+Iterative+refinement+with+self%2Dfeedback%2E+In+Proceed)
55. Danièle Meulemans. 2005. Jeux de langage: L’énigme et la devinette dans la tradition orale francophone. In Jeux et langages, pages 55–72. Presses Universitaires de Rennes. [find](https://scholar.google.com/scholar?q=Dani%C3%A8le+Meulemans%2E+2005%2E+Jeux+de+langage%3A+L%E2%80%99%C3%A9nigme+et+la+devinette+dans+la+tradition+orale+francophone%2E+In+Jeux+et+langages%2C+pages+55%E2%80%9372%2E+Presses+Universitaires+de+Rennes%2E)
56. Lili Mou, Zichao Ye, Wenpeng Yin, Wayne Xin Zhao, Duyu Tang, and Rui Yan. 2022. Cold decoding: Energy-based constrained text generation with langevin dynamics. arXiv preprint arXiv:2202.11726. [↗](https://arxiv.org/abs/2202.11726)
57. Masanari Ohi, Masahiro Kaneko, Naoaki Okazaki, and Nakamasa Inoue. 2024. Harmoniceval: Multi-modal, multi-task, multi-criteria automatic evaluation using vision language models. arXiv preprint arXiv:2412.14613. [↗](https://arxiv.org/abs/2412.14613)
58. Ioannis Panagiotopoulos, Giorgos Filandrianos, Maria Lymperaiou, and Giorgos Stamou. 2024. Riscore: Enhancing in-context riddle solving in language models through context-reconstructed example augmentation. arXiv preprint arXiv:2409.16383. [↗](https://arxiv.org/abs/2409.16383)
59. Siddhesh Pawar, Junyeong Park, and Jiho et al. Jin. 2024. Survey of cultural awareness in language models: Text and beyond. arXiv preprint arXiv:2411.00860. [↗](https://arxiv.org/abs/2411.00860)
60. Hao Peng, Yifan Hou, Mo Yu, Wenhui Wang, Shujie Liu, Yankai Lin, Zhiyuan Liu, Jing Ma, and Jianfeng Gao. 2023. Language models still struggle to learn hard commonsense knowledge from demonstrations. In ACL. [find](https://scholar.google.com/scholar?q=Hao+Peng%2C+Yifan+Hou%2C+Mo+Yu%2C+Wenhui+Wang%2C+Shujie+Liu%2C+Yankai+Lin%2C+Zhiyuan+Liu%2C+Jing+Ma%2C+and+Jianfeng+Gao%2E+2023%2E+Language+models+still+struggle+to+learn+hard+commonsense+knowledge+from+demonstrations%2E+I)
61. Sasa Petrović and David Matthews. 2013. Unsupervised joke generation from big data. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 228–232. [find](https://scholar.google.com/scholar?q=Sasa+Petrovic%CC%81+and+David+Matthews%2E+2013%2E+Unsupervised+joke+generation+from+big+data%2E+In+Proceedings+of+the+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+2%3A+Short+Papers%29)
62. Edoardo Maria Ponti, Peng Xu, Yixin Kim, Samuel Cahyawijaya, Zhihao Tan, Sebastian Ruder, Yichong Huang, Graham Neubig, Kevin Duh, Naman Goyal, et al. 2020. Xcopa: A multilingual dataset for causal commonsense reasoning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). [our card](https://md.research.elamur.ai/free/en/papers/ponti-2020-xcopa-multilingual-dataset-causal-commonsense/)
63. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI Blog, 1(8). [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+and+Ilya+Sutskever%2E+2019%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+Blog%2C+1%288%29%2E)
64. Ricardo Rei, Ana Farinha, Alon Lavie, et al. 2020. Comet: A neural framework for mt evaluation. In Proceedings of WMT. [our card](https://md.research.elamur.ai/free/en/papers/rei-2020-comet-neural-framework-mt-evaluation/)
65. Leticia Resck, Isabelle Augenstein, and Anna Korhonen. 2024. Explainability and interpretability of multilingual large language models: A survey. OpenReview. [our card](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/)
66. Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Semantically equivalent adversarial rules for debugging nlp models. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), pages 856–865. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Marco+Tulio+Ribeiro%2C+Sameer+Singh%2C+and+Carlos+Guestrin%2E+2018%2E+Semantically+equivalent+adversarial+rules+for+debugging+nlp+models%2E+In+Proceedings+of+the+56th+Annual+Meeting+of+the+Association+for+Compu)
67. Lucia Schmidtová and Shu Wu. 2024. Automatic metrics fail to capture creativity in multilingual generation. Transactions of the Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lucia+Schmidtov%C3%A1+and+Shu+Wu%2E+2024%2E+Automatic+metrics+fail+to+capture+creativity+in+multilingual+generation%2E+Transactions+of+the+Association+for+Computational+Linguistics%2E)
68. Terrence J Sejnowski. 2023. Large language models and the reverse turing test. Neural Computation, 35(3):309–342. [find](https://scholar.google.com/scholar?q=Terrence+J+Sejnowski%2E+2023%2E+Large+language+models+and+the+reverse+turing+test%2E+Neural+Computation%2C+35%283%29%3A309%E2%80%93342%2E)
69. Thibault Sellam, Dipanjan Das, and Ankur Parikh. 2020a. Bleurt: Learning robust metrics for text generation. Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Thibault+Sellam%2C+Dipanjan+Das%2C+and+Ankur+Parikh%2E+2020a%2E+Bleurt%3A+Learning+robust+metrics+for+text+generation%2E+Proceedings+of+ACL%2E)
70. Thibault Sellam, Dipanjan Das, and Ankur Parikh. 2020b. Bleurt: Learning robust metrics for text generation. In ACL. [find](https://scholar.google.com/scholar?q=Thibault+Sellam%2C+Dipanjan+Das%2C+and+Ankur+Parikh%2E+2020b%2E+Bleurt%3A+Learning+robust+metrics+for+text+generation%2E+In+ACL%2E)
71. Ekaterina Shutova. 2013. Metaphor identification as interpretation. In Proceedings of NAACL-HLT. [find](https://scholar.google.com/scholar?q=Ekaterina+Shutova%2E+2013%2E+Metaphor+identification+as+interpretation%2E+In+Proceedings+of+NAACL%2DHLT%2E)
72. Shaden Smith et al. 2022. Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. arXiv preprint arXiv:2201.11990. [↗](https://arxiv.org/abs/2201.11990) [our card](https://md.research.elamur.ai/free/en/papers/smith-2022-using-deepspeed-megatron-train-megatron/)
73. Dirk HR Spennemann. 2023. Chatgpt and the generation of digitally born “knowledge”: How does a generative ai language model interpret cultural heritage values? Knowledge, 3(3):480–512. [find](https://scholar.google.com/scholar?q=Dirk+HR+Spennemann%2E+2023%2E+Chatgpt+and+the+generation+of+digitally+born+%E2%80%9Cknowledge%E2%80%9D%3A+How+does+a+generative+ai+language+model+interpret+cultural+heritage+values%3F+Knowledge%2C+3%283%29%3A480%E2%80%93512%2E)
74. Chaofen Sun. 2006. Chinese character puzzles and riddle traditions. Journal of Chinese Linguistics, 34(2):223–248. [find](https://scholar.google.com/scholar?q=Chaofen+Sun%2E+2006%2E+Chinese+character+puzzles+and+riddle+traditions%2E+Journal+of+Chinese+Linguistics%2C+34%282%29%3A223%E2%80%93248%2E)
75. Prithviraj Tambwekar, Animesh Mehta, Lindsay Martin, Brent Harrison, and Mark O. Riedl. 2019. Controllable neural story plot generation via reward shaping. In IJCAI, pages 5982–5988. [find](https://scholar.google.com/scholar?q=Prithviraj+Tambwekar%2C+Animesh+Mehta%2C+Lindsay+Martin%2C+Brent+Harrison%2C+and+Mark+O%2E+Riedl%2E+2019%2E+Controllable+neural+story+plot+generation+via+reward+shaping%2E+In+IJCAI%2C+pages+5982%E2%80%935988%2E)
76. Chuanqi Tan, Furu Wei, Li Dong, Weifeng Lv, and Ming Zhou. 2016. Solving and generating chinese character riddles. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 846–855. [find](https://scholar.google.com/scholar?q=Chuanqi+Tan%2C+Furu+Wei%2C+Li+Dong%2C+Weifeng+Lv%2C+and+Ming+Zhou%2E+2016%2E+Solving+and+generating+chinese+character+riddles%2E+In+Proceedings+of+the+2016+Conference+on+Empirical+Methods+in+Natural+Language+Proces)
77. Peiyuan Teng and Min Xu. 2023. Random matrix time series. Journal of Statistical Theory and Practice, 17(3):42. [find](https://scholar.google.com/scholar?q=Peiyuan+Teng+and+Min+Xu%2E+2023%2E+Random+matrix+time+series%2E+Journal+of+Statistical+Theory+and+Practice%2C+17%283%29%3A42%2E)
78. Chris Van der Lee, Albert Gatt, Emiel van Miltenburg, and Emiel Krahmer. 2018. Fluency metrics for machine translation evaluation: A comprehensive analysis. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC). [find](https://scholar.google.com/scholar?q=Chris+Van+der+Lee%2C+Albert+Gatt%2C+Emiel+van+Miltenburg%2C+and+Emiel+Krahmer%2E+2018%2E+Fluency+metrics+for+machine+translation+evaluation%3A+A+comprehensive+analysis%2E+In+Proceedings+of+the+Eleventh+Internationa)
79. Chris van der Lee, Sander Wubben, and Emiel Krahmer. 2019. Assessing the evaluation of text generation. In Proceedings of the 12th International Conference on Natural Language Generation. [find](https://scholar.google.com/scholar?q=Chris+van+der+Lee%2C+Sander+Wubben%2C+and+Emiel+Krahmer%2E+2019%2E+Assessing+the+evaluation+of+text+generation%2E+In+Proceedings+of+the+12th+International+Conference+on+Natural+Language+Generation%2E)
80. Chris van der Lee et al. 2021. Hume: Human unified meaning evaluation. In Proceedings of ACL. [find](https://scholar.google.com/scholar?q=Chris+van+der+Lee+et+al%2E+2021%2E+Hume%3A+Human+unified+meaning+evaluation%2E+In+Proceedings+of+ACL%2E)
81. Tony Veale. 2011. Creative language retrieval: A robust hybrid of information retrieval and linguistic creativity. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pages 278–287. [find](https://scholar.google.com/scholar?q=Tony+Veale%2E+2011%2E+Creative+language+retrieval%3A+A+robust+hybrid+of+information+retrieval+and+linguistic+creativity%2E+In+Proceedings+of+the+49th+Annual+Meeting+of+the+Association+for+Computational+Lingui)
82. Eric Wallace, Shi Feng, Nikhil Kandpal, Matt Gardner, and Sameer Singh. 2019. Universal adversarial triggers for attacking and analyzing nlp. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2153–2162. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Eric+Wallace%2C+Shi+Feng%2C+Nikhil+Kandpal%2C+Matt+Gardner%2C+and+Sameer+Singh%2E+2019%2E+Universal+adversarial+triggers+for+attacking+and+analyzing+nlp%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods)
83. Chenguang Wang, Weijia Su, Qingyao Ai, and Yang Liu. 2024. Knowledge editing through chain-of-thought. arXiv preprint arXiv:2412.17727. [↗](https://arxiv.org/abs/2412.17727)
84. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. In NeurIPS. [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Furu+Wei%2C+Li+Dong%2C+Hangbo+Bao%2C+Nan+Yang%2C+and+Ming+Zhou%2E+2020%2E+Minilm%3A+Deep+self%2Dattention+distillation+for+task%2Dagnostic+compression+of+pre%2Dtrained+transformers%2E+In+NeurIPS%2E)
85. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023a. Chain-of-thought prompting elicits reasoning in large language models. In NeurIPS. [our card](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/)
86. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed Chi, Quoc Le, and Denny Zhou. 2023b. Chain-of-thought prompting elicits reasoning in large language models. [our card](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/)
87. Li Wei and Tong King Lee. 2021. Language play in and with chinese: traditional genres and contemporary developments. Global Chinese, 7(2):125–142. [find](https://scholar.google.com/scholar?q=Li+Wei+and+Tong+King+Lee%2E+2021%2E+Language+play+in+and+with+chinese%3A+traditional+genres+and+contemporary+developments%2E+Global+Chinese%2C+7%282%29%3A125%E2%80%93142%2E)
88. Orion Weller and Kevin Seppi. 2019. Humor detection: A transformer gets the joke. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pages 3621–3627. [find](https://scholar.google.com/scholar?q=Orion+Weller+and+Kevin+Seppi%2E+2019%2E+Humor+detection%3A+A+transformer+gets+the+joke%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+3621%E2%80%933627%2E)
89. Genta Indra Winata, Lucky Susanto, et al. 2024. Metametrics-mt: Tuning meta-metrics for machine translation via human preference calibration. In WMT. [find](https://scholar.google.com/scholar?q=Genta+Indra+Winata%2C+Lucky+Susanto%2C+et+al%2E+2024%2E+Metametrics%2Dmt%3A+Tuning+meta%2Dmetrics+for+machine+translation+via+human+preference+calibration%2E+In+WMT%2E)
90. Yaqing Xie, Jiaao Chen, Zijie Wu, et al. 2025. Sorry-bench: Systematically evaluating large language model safety refusal. In ACL. [find](https://scholar.google.com/scholar?q=Yaqing+Xie%2C+Jiaao+Chen%2C+Zijie+Wu%2C+et+al%2E+2025%2E+Sorry%2Dbench%3A+Systematically+evaluating+large+language+model+safety+refusal%2E+In+ACL%2E)
91. Fan Xu, Yunxiang Zhang, and Xiaojun Wan. 2022. Cc-riddle: A question answering dataset of chinese character riddles. arXiv preprint arXiv:2206.13778. [↗](https://arxiv.org/abs/2206.13778)
92. Jingjing Xu, Xuancheng Li, Lei Zhang, et al. 2018. Diversity-promoting gans for text generation. ACL 2018. [find](https://scholar.google.com/scholar?q=Jingjing+Xu%2C+Xuancheng+Li%2C+Lei+Zhang%2C+et+al%2E+2018%2E+Diversity%2Dpromoting+gans+for+text+generation%2E+ACL+2018%2E)
93. Jian Yao, Ran Cheng, Xingyu Wu, Jibin Wu, and Kay Chen Tan. 2025. Diversity-aware policy optimization for large language model reasoning. arXiv preprint arXiv:2505.23433. [↗](https://arxiv.org/abs/2505.23433)
94. Shinn Yao, Jeffrey Zhao, Dian Yu, Yuan Xu, Kaixuan Zhao, Shinn Cao, Eric Zhang, Shunyu Xu, Yihan Zhao, Yao Shen, et al. 2023. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601. [↗](https://arxiv.org/abs/2305.10601)
95. Hugh Zhang, Daniel Duckworth, Daphne Ippolito, Douglas Eck, and Arvind Neelakantan. 2021. Trading off diversity and quality in natural language generation. In Proceedings of the 2021 Workshop on Human Evaluation of NLP Systems (HumEval). [find](https://scholar.google.com/scholar?q=Hugh+Zhang%2C+Daniel+Duckworth%2C+Daphne+Ippolito%2C+Douglas+Eck%2C+and+Arvind+Neelakantan%2E+2021%2E+Trading+off+diversity+and+quality+in+natural+language+generation%2E+In+Proceedings+of+the+2021+Workshop+on+Human)
96. Jingqing Zhang, Jason Baldridge, and He He. 2020a. Learning to summarize with human attention. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3631–3642. [find](https://scholar.google.com/scholar?q=Jingqing+Zhang%2C+Jason+Baldridge%2C+and+He+He%2E+2020a%2E+Learning+to+summarize+with+human+attention%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+3631%E2%80%9336)
97. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q Weinberger, and Yoav Artzi. 2020b. Bertscore: Evaluating text generation with bert. In ICLR. [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2C+Varsha+Kishore%2C+Felix+Wu%2C+Kilian+Q+Weinberger%2C+and+Yoav+Artzi%2E+2020b%2E+Bertscore%3A+Evaluating+text+generation+with+bert%2E+In+ICLR%2E)
98. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020c. BERTScore: Evaluating text generation with BERT. In Proceedings of the International Conference on Learning Representations (ICLR). [find](https://scholar.google.com/scholar?q=Tianyi+Zhang%2C+Varsha+Kishore%2C+Felix+Wu%2C+Kilian+Q%2E+Weinberger%2C+and+Yoav+Artzi%2E+2020c%2E+BERTScore%3A+Evaluating+text+generation+with+BERT%2E+In+Proceedings+of+the+International+Conference+on+Learning+Represe)
99. Wei Zhang and Xiaojun Wan. 2025. Multilingual cultural generation with language models. Transactions of the Association for Computational Linguistics, 13:1234–1256. [find](https://scholar.google.com/scholar?q=Wei+Zhang+and+Xiaojun+Wan%2E+2025%2E+Multilingual+cultural+generation+with+language+models%2E+Transactions+of+the+Association+for+Computational+Linguistics%2C+13%3A1234%E2%80%931256%2E)
100. Yunxiang Zhang and Xiaojun Wan. 2022. Birdqa: A bilingual dataset for question answering on tricky riddles. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 11748–11756. [find](https://scholar.google.com/scholar?q=Yunxiang+Zhang+and+Xiaojun+Wan%2E+2022%2E+Birdqa%3A+A+bilingual+dataset+for+question+answering+on+tricky+riddles%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+36%2C+pages+11748%E2%80%93117)
101. Zhuosheng Zhang, Aston Zhang, Mu Li, and Alexander Smola. 2022. Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493. [↗](https://arxiv.org/abs/2210.03493) [our card](https://md.research.elamur.ai/free/en/papers/zhang-2022-automatic-chain-thought-prompting-large/)
102. Yichi Zhou and Yonatan Bisk. 2022. Visual puns: Multimodal understanding of double meanings. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pages 6034–6047. [find](https://scholar.google.com/scholar?q=Yichi+Zhou+and+Yonatan+Bisk%2E+2022%2E+Visual+puns%3A+Multimodal+understanding+of+double+meanings%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+pages+6034%E2%80%936047)
103. Yichong Zhou, Swaroop Mishra, Xiaodong Liu, et al. 2022. Crescendo: Iteratively growing reasoning graphs for question answering. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1610–1624. [find](https://scholar.google.com/scholar?q=Yichong+Zhou%2C+Swaroop+Mishra%2C+Xiaodong+Liu%2C+et+al%2E+2022%2E+Crescendo%3A+Iteratively+growing+reasoning+graphs+for+question+answering%2E+In+Proceedings+of+the+2022+Conference+on+Empirical+Methods+in+Natural+L)

*Updated 23 October 2026*