---
title: "Next Reply Prediction X (NRP-X) Dataset: Linguistic"
description: "The authors build NRP-X, a resource for testing this on authentic X (formerly Twitter) data in English and German, gathered… 38 references."
authors: ["Simon Münker", "Nils Schwager", "Kai Kugler", "Michael Heseltine", "Achim Rettinger"]
year: 2026
venue: "Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026"
source: "https://aclanthology.org/2026.llms4ssh-1.5/"
doi: "10.63317/5fmgng5iobv6"
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/munker-2026-next-reply-prediction-x-nrp/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/munker-2026-next-reply-prediction-x-nrp/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/38/) / Next Reply Prediction X (NRP-X) Dataset: Linguistic Discrepancies in Naively Generated Content

# Next Reply Prediction X (NRP-X) Dataset: Linguistic Discrepancies in Naively Generated Content

**Authors:** [Simon Münker](https://md.research.elamur.ai/free/en/authors/simon-munker/), [Nils Schwager](https://md.research.elamur.ai/free/en/authors/nils-schwager/), [Kai Kugler](https://md.research.elamur.ai/free/en/authors/kai-kugler/), Michael Heseltine and [Achim Rettinger](https://md.research.elamur.ai/free/en/authors/achim-rettinger/) · **Year:** 2026 · **Venue:** [Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/llms4ssh/) ([Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities @ LREC 2026](https://md.research.elamur.ai/free/en/venues/llms4ssh/2026/)) · **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/2026.llms4ssh-1.5/) · [PDF](https://aclanthology.org/2026.llms4ssh-1.5.pdf) · [DOI 10.63317/5fmgng5iobv6](https://doi.org/10.63317/5fmgng5iobv6) · [OpenAlex](https://openalex.org/W7166508313)

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

## Summary
Social scientists increasingly use LLMs as stand-ins for human participants. When models are simply prompted without behavioral constraints, their writing may differ from real users' in ways that undermine research validity. The authors build NRP-X, a resource for testing this on authentic X (formerly Twitter) data in English and German, gathered around US and German political debates in the first half of 2023.

They define a history-conditioned next reply prediction task. A model sees three earlier tweet–reply pairs from one user and must answer a fourth tweet. Replies come from the base Qwen3 8B and from a fine-tuned variant for each language, and both are set against the user's actual reply. The evaluation framework compares human and synthetic text on quantitative, morphological and semantic dimensions. It also tests detection classifiers built on tf-idf, static dense and transformer encoders.

The authors report that naive generation leaves measurable linguistic discrepancies, so better prompting and specialized datasets are needed. The resource matters as a benchmark for judging whether synthetic social media content is realistic enough for computational social science.

## Key points
- **Raw data and filtering:** the dumps contain about 3.38M German and 7.79M English replies. Tweet–reply pairs with URLs, images or GIFs were dropped. The most active repliers were removed (top 5% for DE, top 1% for EN), capping users at 24 (DE) or 21 (EN) samples. Train and test sets were split by user to prevent memorization of individuals.
- **Fine-tuning:** Qwen3 8B was trained separately per language on 5,000 examples for one epoch, with a warm-up ratio of 0.1 and a learning rate of 2e-5. Loss was computed only on the final assistant reply, and each model took about 100 minutes on one NVIDIA L40S GPU.
- **Generation:** each test prompt received one reply, using temperature 0.6, top_k 20, top_p 0.9 and a 200-token limit. No outputs were filtered after generation.
- **Released dataset (GitHub):** it holds 1,000 samples per language. Each sample includes the prompt in chat format, the authentic reply, the base model reply and the ft model reply. Intended uses are improving reply prediction, designing new human–LLM alignment metrics, and training synthetic-content detectors.
- **Research questions:** the study asks (1) whether synthetic posts are linguistically distinguishable from human ones, (2) whether fine-tuning improves authenticity over prompting, and (3) which classifier features best separate human from synthetic content. The authors hypothesize that fine-tuning reduces but does not remove detectable deviations.

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

## Institutions

- [University of Oxford](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) — University, Oxford, United Kingdom · 104 works · 157,183 citations
- [Universität Trier](https://md.research.elamur.ai/free/en/universities/universitat-trier/) — University, Trier, Germany · 8 works · 9 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 General Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/general-social-sciences/) · 227 works

## Cite

Cite as: Simon Münker, Nils Schwager, Kai Kugler, Michael Heseltine and Achim Rettinger. 2026. Next Reply Prediction X (NRP-X) Dataset: Linguistic Discrepancies in Naively Generated Content. Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026.

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

```bibtex
@inproceedings{munker2026next,
  title = {{Next Reply Prediction X (NRP-X) Dataset: Linguistic Discrepancies in Naively Generated Content}},
  author = {Simon Münker, Nils Schwager, Kai Kugler, Michael Heseltine and Achim Rettinger},
  booktitle = {Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026},
  year = {2026},
  doi = {10.63317/5fmgng5iobv6},
  url = {https://doi.org/10.63317/5fmgng5iobv6}
}
```

- [← previous News Credibility Assessment by LLMs and Humans: Implications for Political Bias](https://md.research.elamur.ai/free/en/papers/neves-2026-news-credibility-assessment-llms-humans/)
- [next → NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering](https://md.research.elamur.ai/free/en/papers/shi-2026-ng-router-graph-supervised-multi/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/38/)

## References

38 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Harika Abburi, Nirmala Pudota, Balaji Veeramani, Edward Bowen, and Sanmitra Bhattacharya. 2024. Toward robust generative ai text detection: Generalizable neural model. In 2024 International Conference on Machine Learning and Applications (ICMLA), pages 1651–1656. IEEE. [find](https://scholar.google.com/scholar?q=Harika+Abburi%2C+Nirmala+Pudota%2C+Balaji+Veeramani%2C+Edward+Bowen%2C+and+Sanmitra+Bhattacharya%2E+2024%2E+Toward+robust+generative+ai+text+detection%3A+Generalizable+neural+model%2E+In+2024+International+Conference)
2. Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794. [find](https://scholar.google.com/scholar?q=Tianqi+Chen+and+Carlos+Guestrin%2E+2016%2E+Xgboost%3A+A+scalable+tree+boosting+system%2E+In+Proceedings+of+the+22nd+acm+sigkdd+international+conference+on+knowledge+discovery+and+data+mining%2C+pages+785%E2%80%93794%2E)
3. Esma Aïmeur, Sabrine Amri, and Gilles Brassard. 2023. Fake news, disinformation and misinformation in social media: a review. Social Network Analysis and Mining, 13(1):30. [find](https://scholar.google.com/scholar?q=Esma+A%C3%AFmeur%2C+Sabrine+Amri%2C+and+Gilles+Brassard%2E+2023%2E+Fake+news%2C+disinformation+and+misinformation+in+social+media%3A+a+review%2E+Social+Network+Analysis+and+Mining%2C+13%281%29%3A30%2E)
4. Alicia Tsui Ying Chong, Hui Na Chua, Muhammed Basheer Jasser, and Richard TK Wong. 2023. Bot or human? detection of deepfake text with semantic, emoji, sentiment and linguistic features. In 2023 IEEE 13th International Conference on System Engineering and Technology (ICSET), pages 205–210. IEEE. [find](https://scholar.google.com/scholar?q=Alicia+Tsui+Ying+Chong%2C+Hui+Na+Chua%2C+Muhammed+Basheer+Jasser%2C+and+Richard+TK+Wong%2E+2023%2E+Bot+or+human%3F+detection+of+deepfake+text+with+semantic%2C+emoji%2C+sentiment+and+linguistic+features%2E+In+2023+IEEE+)
5. Meysam Alizadeh, Maël Kubli, Zeynab Samei, Shirin Dehghani, Mohammadmasiha Zahedivafa, Juan D Bermeo, Maria Korobeynikova, and Fabrizio Gilardi. 2025. Open-source llms for text annotation: a practical guide for model setting and fine-tuning. Journal of Computational Social Science, 8(1):17. [find](https://scholar.google.com/scholar?q=Meysam+Alizadeh%2C+Ma%C3%ABl+Kubli%2C+Zeynab+Samei%2C+Shirin+Dehghani%2C+Mohammadmasiha+Zahedivafa%2C+Juan+D+Bermeo%2C+Maria+Korobeynikova%2C+and+Fabrizio+Gilardi%2E+2025%2E+Open%2Dsource+llms+for+text+annotation%3A+a+practical)
6. Evan N Crothers, Nathalie Japkowicz, and Herna L Viktor. 2023. Machine-generated text: A comprehensive survey of threat models and detection methods. IEEE Access, 11:70977–71002. [find](https://scholar.google.com/scholar?q=Evan+N+Crothers%2C+Nathalie+Japkowicz%2C+and+Herna+L+Viktor%2E+2023%2E+Machine%2Dgenerated+text%3A+A+comprehensive+survey+of+threat+models+and+detection+methods%2E+IEEE+Access%2C+11%3A70977%E2%80%9371002%2E)
7. Dimosthenis Antypas, Asahi Ushio, Jose Camacho-Collados, Vitor Silva, Leonardo Neves, and Francesco Barbieri. 2022. Twitter topic classification. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3386–3400, Gyeongju, Republic of Korea. International Committee on… [find](https://scholar.google.com/scholar?q=Dimosthenis+Antypas%2C+Asahi+Ushio%2C+Jose+Camacho%2DCollados%2C+Vitor+Silva%2C+Leonardo+Neves%2C+and+Francesco+Barbieri%2E+2022%2E+Twitter+topic+classification%2E+In+Proceedings+of+the+29th+International+Conference+on)
8. Marie-Catherine De Marneffe, Christopher D Manning, Joakim Nivre, and Daniel Zeman. 2021. [Universal dependencies](https://md.research.elamur.ai/free/en/papers/marneffe-2021-universal-dependencies-2/). Computational linguistics, 47(2):255–308.
9. Brendan J Frey and Delbert Dueck. 2007. Clustering by passing messages between data points. science, 315(5814):972–976. [find](https://scholar.google.com/scholar?q=Brendan+J+Frey+and+Delbert+Dueck%2E+2007%2E+Clustering+by+passing+messages+between+data+points%2E+science%2C+315%285814%29%3A972%E2%80%93976%2E)
10. Francesco Barbieri, Jose Camacho-Collados, Luis Espinosa Anke, and Leonardo Neves. 2020. [Tweeteval: Unified benchmark and comparative evaluation for tweet classification](https://md.research.elamur.ai/free/en/papers/barbieri-2020-tweeteval-unified-benchmark-comparative-evaluation/). In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1644–1650.
11. Robert Gunning. 1968. The technique of clear writing. McGraw-Hill Book Company, New York. [find](https://scholar.google.com/scholar?q=Robert+Gunning%2E+1968%2E+The+technique+of+clear+writing%2E+McGraw%2DHill+Book+Company%2C+New+York%2E)
12. Kadhim Hayawi, Susmita Saha, Mohammad Mehedy Masud, Sujith Samuel Mathew, and Mohammed Kaosar. 2023. Social media bot detection with deep learning methods: a systematic review. Neural Computing and Applications, 35(12):8903–8918. [find](https://scholar.google.com/scholar?q=Kadhim+Hayawi%2C+Susmita+Saha%2C+Mohammad+Mehedy+Masud%2C+Sujith+Samuel+Mathew%2C+and+Mohammed+Kaosar%2E+2023%2E+Social+media+bot+detection+with+deep+learning+methods%3A+a+systematic+review%2E+Neural+Computing+and+Ap)
13. Ines Montani, Matthew Honnibal, Adriane Boyd, Sofie Van Landeghem, and Henning Peters. 2023. spacy: Industrial-strength nlp. Zenodo. [find](https://scholar.google.com/scholar?q=Ines+Montani%2C+Matthew+Honnibal%2C+Adriane+Boyd%2C+Sofie+Van+Landeghem%2C+and+Henning+Peters%2E+2023%2E+spacy%3A+Industrial%2Dstrength+nlp%2E+Zenodo%2E)
14. Simon Münker. 2025a. Cultural bias in large language models: Evaluating ai agents through moral questionnaires. In Proceedings of 0 th Moral and Legal AI Alignment Symposium, page 61. [find](https://scholar.google.com/scholar?q=Simon+M%C3%BCnker%2E+2025a%2E+Cultural+bias+in+large+language+models%3A+Evaluating+ai+agents+through+moral+questionnaires%2E+In+Proceedings+of+0+th+Moral+and+Legal+AI+Alignment+Symposium%2C+page+61%2E)
15. Daniel Hershcovich, Stella Frank, Heather Lent, Miryam de Lhoneux, Mostafa Abdou, Stephanie Brandl, Emanuele Bugliarello, Laura Cabello Piqueras, Ilias Chalkidis, Ruixiang Cui, et al. 2022. [Challenges and strategies in cross-cultural nlp](https://md.research.elamur.ai/free/en/papers/hershcovich-2022-challenges-strategies-cross-cultural-nlp/). In Proceedings of the 60th Annual Meeting of the Association…
16. Simon Münker. 2025b. Political bias in llms: Unaligned moral values in agent-centric simulations. Journal for Language Technology and Computational Linguistics, 38(2):125–138. [find](https://scholar.google.com/scholar?q=Simon+M%C3%BCnker%2E+2025b%2E+Political+bias+in+llms%3A+Unaligned+moral+values+in+agent%2Dcentric+simulations%2E+Journal+for+Language+Technology+and+Computational+Linguistics%2C+38%282%29%3A125%E2%80%93138%2E)
17. Simon Münker, Nils Schwager, and Achim Rettinger. 2026. [Don’t trust generative agents to mimic communication on social networks unless you benchmarked their empirical realism](https://md.research.elamur.ai/free/en/papers/munker-2026-don-t-trust-generative-agents/). In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Lo…
18. Michael Heseltine. 2025. Comparing large language models for text classification: Model selection across tasks, texts, and languages. [find](https://scholar.google.com/scholar?q=Michael+Heseltine%2E+2025%2E+Comparing+large+language+models+for+text+classification%3A+Model+selection+across+tasks%2C+texts%2C+and+languages%2E)
19. Benjamin D Horne, William Dron, Sara Khedr, and Sibel Adali. 2018. Assessing the news landscape: A multi-module toolkit for evaluating the credibility of news. In Companion Proceedings of the The Web Conference 2018, pages 235–238. [find](https://scholar.google.com/scholar?q=Benjamin+D+Horne%2C+William+Dron%2C+Sara+Khedr%2C+and+Sibel+Adali%2E+2018%2E+Assessing+the+news+landscape%3A+A+multi%2Dmodule+toolkit+for+evaluating+the+credibility+of+news%2E+In+Companion+Proceedings+of+the+The+Web+)
20. Yuan Pan, Guocong Feng, Kaitian Huang, and Chunmei Zhang. 2025. Qwen3-powered log classification for improved soc decision-making. In 2025 8th International Conference on Computer Information Science and Application Technology (CISAT), pages 651–655. IEEE. [find](https://scholar.google.com/scholar?q=Yuan+Pan%2C+Guocong+Feng%2C+Kaitian+Huang%2C+and+Chunmei+Zhang%2E+2025%2E+Qwen3%2Dpowered+log+classification+for+improved+soc+decision%2Dmaking%2E+In+2025+8th+International+Conference+on+Computer+Information+Science+)
21. Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov. 2017. Bag of tricks for efficient text classification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 427–431. Association for Computation… [find](https://scholar.google.com/scholar?q=Armand+Joulin%2C+Edouard+Grave%2C+Piotr+Bojanowski%2C+and+Tomas+Mikolov%2E+2017%2E+Bag+of+tricks+for+efficient+text+classification%2E+In+Proceedings+of+the+15th+Conference+of+the+European+Chapter+of+the+Associati)
22. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+36)
23. J Peter Kincaid, Robert P Fishburne Jr, Richard L Rogers, and Brad S Chissom. 1975. Derivation of new readability formulas (automated readability index, fog count and flesch reading ease formula) for navy enlisted personnel. Research Branch Report, Naval Technical Training Command, Millington. [find](https://scholar.google.com/scholar?q=J+Peter+Kincaid%2C+Robert+P+Fishburne+Jr%2C+Richard+L+Rogers%2C+and+Brad+S+Chissom%2E+1975%2E+Derivation+of+new+readability+formulas+%28automated+readability+index%2C+fog+count+and+flesch+reading+ease+formula%29+for+)
24. Karl Pearson. 1901. Liii. on lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin philosophical magazine and journal of science, 2(11):559–572. [find](https://scholar.google.com/scholar?q=Karl+Pearson%2E+1901%2E+Liii%2E+on+lines+and+planes+of+closest+fit+to+systems+of+points+in+space%2E+The+London%2C+Edinburgh%2C+and+Dublin+philosophical+magazine+and+journal+of+science%2C+2%2811%29%3A559%E2%80%93572%2E)
25. Maik Larooij and Petter Törnberg. 2025. Do large language models solve the problems of agent-based modeling? a critical review of generative social simulations. arXiv preprint arXiv:2504.03274. — [arXiv:2504.03274](https://arxiv.org/abs/2504.03274) [find](https://scholar.google.com/scholar?q=Maik+Larooij+and+Petter+T%C3%B6rnberg%2E+2025%2E+Do+large+language+models+solve+the+problems+of+agent%2Dbased+modeling%3F+a+critical+review+of+generative+social+simulations%2E+arXiv+preprint+arXiv%3A2504%2E03274%2E+%E2%80%94+%5BarX)
26. Jaime Pérez, Mario Castro, and Gregorio López. 2023. Serious games and ai: Challenges and opportunities for computational social science. IEEE Access, 11:62051–62061. [find](https://scholar.google.com/scholar?q=Jaime+P%C3%A9rez%2C+Mario+Castro%2C+and+Gregorio+L%C3%B3pez%2E+2023%2E+Serious+games+and+ai%3A+Challenges+and+opportunities+for+computational+social+science%2E+IEEE+Access%2C+11%3A62051%E2%80%9362061%2E)
27. Haocheng Lin. 2024. Designing domain-specific large language models: The critical role of fine-tuning in public opinion simulation. arXiv preprint arXiv:2409.19308. — [arXiv:2409.19308](https://arxiv.org/abs/2409.19308) [find](https://scholar.google.com/scholar?q=Haocheng+Lin%2E+2024%2E+Designing+domain%2Dspecific+large+language+models%3A+The+critical+role+of+fine%2Dtuning+in+public+opinion+simulation%2E+arXiv+preprint+arXiv%3A2409%2E19308%2E+%E2%80%94+%5BarXiv%3A2409%2E19308%5D%28https%3A%2F%2Farxiv%2E)
28. Juan Ramos et al. 2003. Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning, volume 242, pages 29–48. New Jersey, USA. [find](https://scholar.google.com/scholar?q=Juan+Ramos+et+al%2E+2003%2E+Using+tf%2Didf+to+determine+word+relevance+in+document+queries%2E+In+Proceedings+of+the+first+instructional+conference+on+machine+learning%2C+volume+242%2C+pages+29%E2%80%9348%2E+New+Jersey%2C+USA)
29. Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu, and Soroush Vosoughi. 2022. Quantifying and alleviating political bias in language models. Artificial Intelligence, 304:103654. [find](https://scholar.google.com/scholar?q=Ruibo+Liu%2C+Chenyan+Jia%2C+Jason+Wei%2C+Guangxuan+Xu%2C+and+Soroush+Vosoughi%2E+2022%2E+Quantifying+and+alleviating+political+bias+in+language+models%2E+Artificial+Intelligence%2C+304%3A103654%2E)
30. Nils Reimers and Iryna Gurevych. 2019. [Sentence-bert: Sentence embeddings using siamese bert-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992.
31. Anders Giovanni Møller and Luca Maria Aiello. 2024. Prompt refinement or fine-tuning? best practices for using llms in computational social science tasks. arXiv preprint arXiv:2408.01346. — [arXiv:2408.01346](https://arxiv.org/abs/2408.01346) [find](https://scholar.google.com/scholar?q=Anders+Giovanni+M%C3%B8ller+and+Luca+Maria+Aiello%2E+2024%2E+Prompt+refinement+or+fine%2Dtuning%3F+best+practices+for+using+llms+in+computational+social+science+tasks%2E+arXiv+preprint+arXiv%3A2408%2E01346%2E+%E2%80%94+%5BarXiv%3A240)
32. Arleen Salles, Kathinka Evers, and Michele Farisco. 2020. Anthropomorphism in ai. AJOB neuroscience, 11(2):88–95. [find](https://scholar.google.com/scholar?q=Arleen+Salles%2C+Kathinka+Evers%2C+and+Michele+Farisco%2E+2020%2E+Anthropomorphism+in+ai%2E+AJOB+neuroscience%2C+11%282%29%3A88%E2%80%9395%2E)
33. Nils Schwager, Simon Münker, Alistair Plum, and Achim Rettinger. 2026. [Towards simulating social media users with LLMs: Evaluating the operational validity of conditioned comment prediction](https://md.research.elamur.ai/free/en/papers/schwager-2026-simulating-social-media-users-llms/). In The Proceedings for the 15th Workshop on Computational Approaches to Subjectivity, Sentiment Social Media…
34. Surendrabikram Thapa, Shuvam Shiwakoti, Siddhant Bikram Shah, Surabhi Adhikari, Hariram Veeramani, Mehwish Nasim, and Usman Naseem. 2025. Large language models (llm) in computational social science: prospects, current state, and challenges. Social Network Analysis and Mining, 15(1):1–30. [find](https://scholar.google.com/scholar?q=Surendrabikram+Thapa%2C+Shuvam+Shiwakoti%2C+Siddhant+Bikram+Shah%2C+Surabhi+Adhikari%2C+Hariram+Veeramani%2C+Mehwish+Nasim%2C+and+Usman+Naseem%2E+2025%2E+Large+language+models+%28llm%29+in+computational+social+science%3A+p)
35. Leandro von Werra, Younes Belkada, Lewis Tunstall, Edward Beeching, Tristan Thrush, Nathan Lambert, Shengyi Huang, Kashif Rasul, and Quentin Gallouédec. 2020. Trl: Transformer reinforcement learning. [https://github.com/](https://github.com/) huggingface/trl. [↗](https://github.com/)
36. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388.
37. Shuo Yang, Kai Shu, Suhang Wang, Renjie Gu, Fan Wu, and Huan Liu. 2019. Unsupervised fake news detection on social media: A generative approach. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 5644–5651. [find](https://scholar.google.com/scholar?q=Shuo+Yang%2C+Kai+Shu%2C+Suhang+Wang%2C+Renjie+Gu%2C+Fan+Wu%2C+and+Huan+Liu%2E+2019%2E+Unsupervised+fake+news+detection+on+social+media%3A+A+generative+approach%2E+In+Proceedings+of+the+AAAI+conference+on+artificial+int)
38. Yanzhao Zhang, Mingxin Li, Dingkun Long, Xin Zhang, Huan Lin, Baosong Yang, Pengjun Xie, An Yang, Dayiheng Liu, Junyang Lin, et al. 2025. [Qwen3 embedding: Advancing text embedding and reranking through foundation models](https://md.research.elamur.ai/free/en/papers/zhang-2025-qwen3-embedding-advancing-text/). arXiv preprint arXiv:2506.05176.

*Updated 1 November 2026*