---
title: "Position — paper by Xu et al. (2026) — summary and ideas"
description: "They present no new experiments. 65 references, cited by 1 paper here. Among them: 0."
authors: ["Shanshan Xu", "Santosh T.Y.S.S", "Barbara Plank"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.1190/"
doi: "10.18653/v1/2026.findings-acl.1190"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/xu-2026-position-noise-signal-selbstzweck-reframing/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/xu-2026-position-noise-signal-selbstzweck-reframing/)

[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/16/) / Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP

# Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP

**Authors:** Shanshan Xu, [Santosh T.Y.S.S](https://md.research.elamur.ai/free/en/authors/santosh-t-y-s-s/) and [Barbara Plank](https://md.research.elamur.ai/free/en/authors/barbara-plank/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.1190/) · [PDF](https://aclanthology.org/2026.findings-acl.1190.pdf) · [DOI 10.18653/v1/2026.findings-acl.1190](https://doi.org/10.18653/v1/2026.findings-acl.1190) · [OpenAlex](https://openalex.org/W7166871087)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
This position paper addresses how NLP treats legitimate annotator disagreement, known as Human Label Variation (HLV), now that LLMs are post-trained on human preference data. The authors note that widely used preference datasets either rely on one annotator per item or merge several judgments into one consensus label. This erases the diversity of values that alignment is meant to reflect. They present no new experiments. Instead, they synthesize prior work into a three-stage framework. In it, HLV moves from noise to be removed, to a signal worth modeling, and finally to a Selbstzweck, meaning a value worth preserving for its own sake. Each stage is linked to the place of humans in NLP and to sociotechnical evaluation levels: capability, human interaction, and systemic impact. They then list weaknesses of current preference data and propose ways to build HLV into dataset construction. The work matters because preference data sits at the base of alignment, yet it receives less scrutiny than reward-learning algorithms or evaluation frameworks.

## Key points
- **Three-stage framework:** Human Adjacent (before the 1990s, expert annotation, a single gold label) → Human Aware (crowdsourcing, BERT-era applications) → Human Centered (after ChatGPT, open-ended LLMs with systemic societal effects).
- **Evidence of disagreement:** Citing Zhang et al. (2025), the authors report that over 30% of items in MultiPref and HelpSteer2 show annotator disagreement, and under 25% of those cases come from genuine annotation error.
- **Lack of transparency:** Chalkidis (2025) found that major LLM developers practically stopped disclosing annotator backgrounds and training after 2022.
- **Recommendations:**
  - Recruit annotator pools that are diverse and representative, in the way a survey sample would be.
  - Mix several kinds of feedback: numeric scores, comparisons between two or more responses, and example demonstrations.
  - Keep pluralism in the reasoning even when one final decision is required, similar to dissenting opinions in court rulings or LLM mediators (Tessler et al., 2024).
- **Proposed metrics:**
  - "Pluralism fidelity" compares model output distributions with human response distributions, for example via KL or Wasserstein distance.
  - "Minority regret" measures the utility lost by minority groups, in the spirit of MaxMin-RLHF.

*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 Copenhagen](https://md.research.elamur.ai/free/en/universities/university-of-copenhagen/) — University, Copenhagen, Denmark · 115 works · 15,292 citations
- [Ludwig-Maximilians-Universität München](https://md.research.elamur.ai/free/en/universities/ludwig-maximilians-universitat-munchen/) — University, Munich, Germany · 107 works · 56,478 citations
- [Amazon](https://md.research.elamur.ai/free/en/companies/amazon/) — Company, Seattle, United States · 112 works · 40,565 citations
- [Munich Center for Machine Learning](https://md.research.elamur.ai/free/en/universities/munich-center-for-machine-learning/) — University, Munich, Germany · 57 works · 1,094 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 · [🤝 Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · 543 works

## Cite

Cite as: Shanshan Xu, Santosh T.Y.S.S and Barbara Plank. 2026. Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{xu2026position,
  title = {{Position: From Noise to Signal to Selbstzweck - Reframing Human Label Variation in the Era of Post-training in NLP}},
  author = {Shanshan Xu, Santosh T.Y.S.S and Barbara Plank},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1190},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1190}
}
```

- [← previous Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions](https://md.research.elamur.ai/free/en/papers/zhang-2026-polynomial-expansion-rank-adaptation-enhancing/)
- [next → POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference](https://md.research.elamur.ai/free/en/papers/zhang-2026-postcondbench-benchmarking-correctness-completeness-formal/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/16/)

## References

65 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Daiwei Chen, Yi Chen, Aniket Rege, and Ramya Korlakai Vinayak. 2025. Pal: Pluralistic alignment framework for learning from heterogeneous preferences. URL https://arxiv.org/abs/2406.08469. — [arXiv:2406.08469](https://arxiv.org/abs/2406.08469) [↗](https://arxiv.org/abs/2406.08469)
2. Sirwan Khalid Ahmed. 2024. How to choose a sampling technique and determine sample size for research: A simplified guide for researchers. Oral Oncology Reports, 12:100662. [find](https://scholar.google.com/scholar?q=Sirwan+Khalid+Ahmed%2E+2024%2E+How+to+choose+a+sampling+technique+and+determine+sample+size+for+research%3A+A+simplified+guide+for+researchers%2E+Oral+Oncology+Reports%2C+12%3A100662%2E)
3. Lora Aroyo, Alex Taylor, Mark Diaz, Christopher Homan, Alicia Parrish, Gregory Serapio-García, Vinodkumar Prabhakaran, and Ding Wang. 2023. Dices dataset: Diversity in conversational ai evaluation for safety. Advances in Neural Information Processing Systems, 36:53330–53342. [find](https://scholar.google.com/scholar?q=Lora+Aroyo%2C+Alex+Taylor%2C+Mark+Diaz%2C+Christopher+Homan%2C+Alicia+Parrish%2C+Gregory+Serapio%2DGarc%C3%ADa%2C+Vinodkumar+Prabhakaran%2C+and+Ding+Wang%2E+2023%2E+Dices+dataset%3A+Diversity+in+conversational+ai+evaluation+for)
4. Lora Aroyo c and Chris Welty. 2015. [Truth is a lie: Crowd truth and the seven myths of human annotation](https://md.research.elamur.ai/free/en/papers/aroyo-2015-truth-lie-crowd-truth-seven/). AI Magazine, 36(1):15–24.
5. Christian Arzate Cruz and Takeo Igarashi. 2020. A survey on interactive reinforcement learning: Design principles and open challenges. In Proceedings of the 2020 ACM Designing Interactive Systems Conference, DIS ’20, page 11951209, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Christian+Arzate+Cruz+and+Takeo+Igarashi%2E+2020%2E+A+survey+on+interactive+reinforcement+learning%3A+Design+principles+and+open+challenges%2E+In+Proceedings+of+the+2020+ACM+Designing+Interactive+Systems+Conf)
6. Kevin D. Ashley. 1991. Modeling legal argument -reasoning with cases and hypotheticals. In Artificial intelligence and legal reasoning. [find](https://scholar.google.com/scholar?q=Kevin+D%2E+Ashley%2E+1991%2E+Modeling+legal+argument+%2Dreasoning+with+cases+and+hypotheticals%2E+In+Artificial+intelligence+and+legal+reasoning%2E)
7. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, and 1 others. 2022. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862. [find](https://scholar.google.com/scholar?q=Yuntao+Bai%2C+Andy+Jones%2C+Kamal+Ndousse%2C+Amanda+Askell%2C+Anna+Chen%2C+Nova+DasSarma%2C+Dawn+Drain%2C+Stanislav+Fort%2C+Deep+Ganguli%2C+Tom+Henighan%2C+and+1+others%2E+2022%2E+Training+a+helpful+and+harmless+assistant+wi)
8. Valerio Basile, Michael Fell, Tommaso Fornaciari, Dirk Hovy, Silviu Paun, Barbara Plank, Massimo Poesio, and Alexandra Uma. 2021. [We need to consider disagreement in evaluation](https://md.research.elamur.ai/free/en/papers/basile-2021-we-need-consider-disagreement-evaluation/). In Proceedings of the 1st Workshop on Benchmarking: Past, Present and Future, pages 15–21, Online. Association for Computa…
9. Yonatan Belinkov, Sebastian Gehrmann, and Ellie Pavlick. 2020. Interpretability and analysis in neural nlp. In Proceedings of the 58th annual meeting of the association for computational linguistics: tutorial abstracts, pages 1–5. [find](https://scholar.google.com/scholar?q=Yonatan+Belinkov%2C+Sebastian+Gehrmann%2C+and+Ellie+Pavlick%2E+2020%2E+Interpretability+and+analysis+in+neural+nlp%2E+In+Proceedings+of+the+58th+annual+meeting+of+the+association+for+computational+linguistics%3A+)
10. Tanise Ceron, Dmitry Nikolaev, Dominik Stammbach, and Debora Nozza. 2025. What is the political content in llms’ pre-and post-training data? arXiv preprint arXiv:2509.22367. — [arXiv:2509.22367](https://arxiv.org/abs/2509.22367) [find](https://scholar.google.com/scholar?q=Tanise+Ceron%2C+Dmitry+Nikolaev%2C+Dominik+Stammbach%2C+and+Debora+Nozza%2E+2025%2E+What+is+the+political+content+in+llms%E2%80%99+pre%2Dand+post%2Dtraining+data%3F+arXiv+preprint+arXiv%3A2509%2E22367%2E+%E2%80%94+%5BarXiv%3A2509%2E22367%5D%28https)
11. Souradip Chakraborty, Jiahao Qiu, Hui Yuan, Alec Koppel, Furong Huang, Dinesh Manocha, Amrit Bedi, and Mengdi Wang. 2024. Maxmin-rlhf: Towards equitable alignment of large language models with diverse human preferences. In ICML 2024 Workshop on Models of Human Feedback for AI Alignment. [find](https://scholar.google.com/scholar?q=Souradip+Chakraborty%2C+Jiahao+Qiu%2C+Hui+Yuan%2C+Alec+Koppel%2C+Furong+Huang%2C+Dinesh+Manocha%2C+Amrit+Bedi%2C+and+Mengdi+Wang%2E+2024%2E+Maxmin%2Drlhf%3A+Towards+equitable+alignment+of+large+language+models+with+diverse)
12. Jinghong Chen, Guangyu Yang, Weizhe Lin, Jingbiao Mei, and Bill Byrne. 2024. On extending direct preference optimization to accommodate ties. arXiv preprint arXiv:2409.17431. — [arXiv:2409.17431](https://arxiv.org/abs/2409.17431) [find](https://scholar.google.com/scholar?q=Jinghong+Chen%2C+Guangyu+Yang%2C+Weizhe+Lin%2C+Jingbiao+Mei%2C+and+Bill+Byrne%2E+2024%2E+On+extending+direct+preference+optimization+to+accommodate+ties%2E+arXiv+preprint+arXiv%3A2409%2E17431%2E+%E2%80%94+%5BarXiv%3A2409%2E17431%5D%28http)
13. Dorottya Demszky, Dana Movshovitz-Attias, Jeongwoo Ko, Alan Cowen, Gaurav Nemade, and Sujith Ravi. 2020. GoEmotions: A Dataset of Fine-Grained Emotions. In 58th Annual Meeting of the Association for Computational Linguistics (ACL). [find](https://scholar.google.com/scholar?q=Dorottya+Demszky%2C+Dana+Movshovitz%2DAttias%2C+Jeongwoo+Ko%2C+Alan+Cowen%2C+Gaurav+Nemade%2C+and+Sujith+Ravi%2E+2020%2E+GoEmotions%3A+A+Dataset+of+Fine%2DGrained+Emotions%2E+In+58th+Annual+Meeting+of+the+Association+for+C)
14. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. [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/). In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies,…
15. Esin Durmus, Karina Nguyen, Thomas I Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph, and 1 others. 2023. [Towards measuring the representation of subjective global opinions in language models](https://md.research.elamur.ai/free/en/papers/durmus-2023-towards-measuring-representation-subjective-global/). arXiv preprint arXiv:2306.16388.
16. Stephanie Eckman, Barbara Plank, and Frauke Kreuter. 2024. Position: Insights from survey methodology can improve training data. In International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Stephanie+Eckman%2C+Barbara+Plank%2C+and+Frauke+Kreuter%2E+2024%2E+Position%3A+Insights+from+survey+methodology+can+improve+training+data%2E+In+International+Conference+on+Machine+Learning%2E)
17. Tommaso Fornaciari, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, Massimo Poesio, and 1 others. 2021. [Beyond black & white: Leveraging annotator disagreement via soft-label multi-task learning](https://md.research.elamur.ai/free/en/papers/fornaciari-2021-beyond-black-white-leveraging-annotator/). In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computa…
18. Armin Ghane-Kanafi and Esmaile Khorram. 2015. A new scalarization method for finding the efficient frontier in non-convex multi-objective problems. Applied Mathematical Modelling, 39:7483–7498. [find](https://scholar.google.com/scholar?q=Armin+Ghane%2DKanafi+and+Esmaile+Khorram%2E+2015%2E+A+new+scalarization+method+for+finding+the+efficient+frontier+in+non%2Dconvex+multi%2Dobjective+problems%2E+Applied+Mathematical+Modelling%2C+39%3A7483%E2%80%937498%2E)
19. Joel Jang, Seungone Kim, Bill Yuchen Lin, Yizhong Wang, Jack Hessel, Luke Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, and Prithviraj Ammanabrolu. 2023. Personalized soups: Personalized large language model alignment via post-hoc parameter merging. arXiv preprint arXiv:2310.11564. [find](https://scholar.google.com/scholar?q=Joel+Jang%2C+Seungone+Kim%2C+Bill+Yuchen+Lin%2C+Yizhong+Wang%2C+Jack+Hessel%2C+Luke+Zettlemoyer%2C+Hannaneh+Hajishirzi%2C+Yejin+Choi%2C+and+Prithviraj+Ammanabrolu%2E+2023%2E+Personalized+soups%3A+Personalized+large+languag)
20. Nan-Jiang Jiang and Marie-Catherine de Marneffe. 2022. [Investigating reasons for disagreement in natural language inference](https://md.research.elamur.ai/free/en/papers/jiang-2022-investigating-reasons-disagreement-natural-language/). Transactions of the Association for Computational Linguistics, 10:1357–1374. 23767 6
21. Nan-Jiang Jiang, Chenhao Tan, and Marie-Catherine de Marneffe. 2023. [Understanding and predicting human label variation in natural language inference through explanation](https://md.research.elamur.ai/free/en/papers/jiang-2023-understanding-predicting-human-label-variation/). arXiv preprint arXiv:2304.12443.
22. Karen Sparck Jones and Julia R Galliers. 1995. Evaluating natural language processing systems: An analysis and review. [find](https://scholar.google.com/scholar?q=Karen+Sparck+Jones+and+Julia+R+Galliers%2E+1995%2E+Evaluating+natural+language+processing+systems%3A+An+analysis+and+review%2E)
23. Timo Kaufmann, Paul Weng, Viktor Bengs, and Eyke Hüllermeier. 2023. A survey of reinforcement learning from human feedback. ArXiv, abs/2312.14925. [find](https://scholar.google.com/scholar?q=Timo+Kaufmann%2C+Paul+Weng%2C+Viktor+Bengs%2C+and+Eyke+H%C3%BCllermeier%2E+2023%2E+A+survey+of+reinforcement+learning+from+human+feedback%2E+ArXiv%2C+abs%2F2312%2E14925%2E)
24. Changmao Li, Elaine Fisher, Rebecca Thomas, Steve Pittard, Vicki Hertzberg, and Jinho D. Choi. 2020. Competence-level prediction and resume & job description matching using context-aware transformer models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EM… [find](https://scholar.google.com/scholar?q=Changmao+Li%2C+Elaine+Fisher%2C+Rebecca+Thomas%2C+Steve+Pittard%2C+Vicki+Hertzberg%2C+and+Jinho+D%2E+Choi%2E+2020%2E+Competence%2Dlevel+prediction+and+resume+%26+job+description+matching+using+context%2Daware+transformer+m)
25. Robert Litschko, Max Müller-Eberstein, Rob van der Goot, Leon Weber-Genzel, and Barbara Plank. 2023. Establishing trustworthiness: Rethinking tasks and model evaluation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 193–203, Singapore. Association f… [find](https://scholar.google.com/scholar?q=Robert+Litschko%2C+Max+M%C3%BCller%2DEberstein%2C+Rob+van+der+Goot%2C+Leon+Weber%2DGenzel%2C+and+Barbara+Plank%2E+2023%2E+Establishing+trustworthiness%3A+Rethinking+tasks+and+model+evaluation%2E+In+Proceedings+of+the+2023+Con)
26. Shang Liu, Yu Pan, Guanting Chen, and Xiaocheng Li. 2024. Reward modeling with ordinal feedback: Wisdom of the crowd. arXiv preprint arXiv:2411.12843. — [arXiv:2411.12843](https://arxiv.org/abs/2411.12843) [find](https://scholar.google.com/scholar?q=Shang+Liu%2C+Yu+Pan%2C+Guanting+Chen%2C+and+Xiaocheng+Li%2E+2024%2E+Reward+modeling+with+ordinal+feedback%3A+Wisdom+of+the+crowd%2E+arXiv+preprint+arXiv%3A2411%2E12843%2E+%E2%80%94+%5BarXiv%3A2411%2E12843%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2411%2E1)
27. Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2021. [A survey on bias and fairness in machine learning](https://md.research.elamur.ai/free/en/papers/mehrabi-2019-survey-bias-fairness-machine-learning/). ACM computing surveys (CSUR), 54(6):1–35.
28. Yannick Metz, Andras Geiszl, Raphaël Baur, and Mennatallah El-Assady. 2025. Reward learning from multiple feedback types. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Yannick+Metz%2C+Andras+Geiszl%2C+Rapha%C3%ABl+Baur%2C+and+Mennatallah+El%2DAssady%2E+2025%2E+Reward+learning+from+multiple+feedback+types%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2E)
29. Lester James Validad Miranda, Yizhong Wang, Yanai Elazar, Sachin Kumar, Valentina Pyatkin, Faeze Brahman, Noah A. Smith, Hannaneh Hajishirzi, and Pradeep Dasigi. 2025. Hybrid preferences: Learning to route instances for human vs. AI feedback. In Proceedings of the 63rd Annual Meeting of the Associat… [find](https://scholar.google.com/scholar?q=Lester+James+Validad+Miranda%2C+Yizhong+Wang%2C+Yanai+Elazar%2C+Sachin+Kumar%2C+Valentina+Pyatkin%2C+Faeze+Brahman%2C+Noah+A%2E+Smith%2C+Hannaneh+Hajishirzi%2C+and+Pradeep+Dasigi%2E+2025%2E+Hybrid+preferences%3A+Learning+to+)
30. Yixin Nie, Xiang Zhou, and Mohit Bansal. 2020. [What can we learn from collective human opinions on natural language inference data?](https://md.research.elamur.ai/free/en/papers/nie-2020-what-can-we-learn-collective/) In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9131–9143, Online. Association for Computational Linguistics.
31. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). Accessed: 2023-09-27.
32. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, and 1 others. 2022. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in neural information processing systems, 35:27730–27744.
33. Mohammed Fayiz Parappan and Ricardo Henao. 2025. Learning subjective label distributions via sociocultural descriptors. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20322–20338, Suzhou, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Mohammed+Fayiz+Parappan+and+Ricardo+Henao%2E+2025%2E+Learning+subjective+label+distributions+via+sociocultural+descriptors%2E+In+Proceedings+of+the+2025+Conference+on+Empirical+Methods+in+Natural+Language+P)
34. Ellie Pavlick and Tom Kwiatkowski. 2019. [Inherent disagreements in human textual inferences](https://md.research.elamur.ai/free/en/papers/pavlick-2019-inherent-disagreements-human-textual-inferences/). Transactions of the Association for Computational Linguistics, 7:677–694.
35. Verónica Pérez-Rosas, Bennett Kleinberg, Alexandra Lefevre, and Rada Mihalcea. 2018. [Automatic detection of fake news](https://md.research.elamur.ai/free/en/papers/rosas-2018-automatic-detection-fake-news/). In Proceedings of the 27th International Conference on Computational Linguistics, pages 3391–3401, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
36. Barbara Plank. 2022. [The problem of human label variation: On ground truth in data, modeling and evaluation](https://md.research.elamur.ai/free/en/papers/plank-2022-problem-human-label-variation-ground/). In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10671–10682.
37. Barbara Plank, Dirk Hovy, and Anders Søgaard. 2014. [Linguistically debatable or just plain wrong?](https://md.research.elamur.ai/free/en/papers/plank-2014-linguistically-debatable-or-just-plain/) In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 507–511, Baltimore, Maryland. Association for Computational Linguistics.
38. Yujin Potter, Shiyang Lai, Junsol Kim, James Evans, and Dawn Song. 2024. Hidden persuaders: LLMs’ political leaning and their influence on voters. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4244–4275, Miami, Florida, USA. Association for Computat… [find](https://scholar.google.com/scholar?q=Yujin+Potter%2C+Shiyang+Lai%2C+Junsol+Kim%2C+James+Evans%2C+and+Dawn+Song%2E+2024%2E+Hidden+persuaders%3A+LLMs%E2%80%99+political+leaning+and+their+influence+on+voters%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Me)
39. Vinodkumar Prabhakaran, Aida Mostafazadeh Davani, and Mark Diaz. 2021. [On releasing annotator-level labels and information in datasets](https://md.research.elamur.ai/free/en/papers/prabhakaran-2021-releasing-annotator-level-labels-information/). In Proceedings of the Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop, pages 133–138, Punta Cana, Dominican…
40. Manish Raghavan, Aleksandrs Slivkins, Jennifer Vaughan Wortman, and Zhiwei Steven Wu. 2018. The externalities of exploration and how data diversity helps exploitation. In Conference on Learning Theory, pages 1724–1738. PMLR. [find](https://scholar.google.com/scholar?q=Manish+Raghavan%2C+Aleksandrs+Slivkins%2C+Jennifer+Vaughan+Wortman%2C+and+Zhiwei+Steven+Wu%2E+2018%2E+The+externalities+of+exploration+and+how+data+diversity+helps+exploitation%2E+In+Conference+on+Learning+Theory)
41. Alexandre Rame, Guillaume Couairon, Corentin Dancette, Jean-Baptiste Gaya, Mustafa Shukor, Laure Soulier, and Matthieu Cord. 2023. Rewarded 23768 7 soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. Advances in Neural Information Processing Systems, 36:71… [find](https://scholar.google.com/scholar?q=Alexandre+Rame%2C+Guillaume+Couairon%2C+Corentin+Dancette%2C+Jean%2DBaptiste+Gaya%2C+Mustafa+Shukor%2C+Laure+Soulier%2C+and+Matthieu+Cord%2E+2023%2E+Rewarded+23768+7+soups%3A+towards+pareto%2Doptimal+alignment+by+interpola)
42. Koster, Georgina Evans, Lucy Campbell-Gillingham, Tantum Collins, David C Parkes, and 1 others. 2024. Ai can help humans find common ground in democratic deliberation. Science, 386(6719):eadq2852. [find](https://scholar.google.com/scholar?q=Koster%2C+Georgina+Evans%2C+Lucy+Campbell%2DGillingham%2C+Tantum+Collins%2C+David+C+Parkes%2C+and+1+others%2E+2024%2E+Ai+can+help+humans+find+common+ground+in+democratic+deliberation%2E+Science%2C+386%286719%29%3Aeadq2852%2E)
43. Marta Sandri, Elisa Leonardelli, Sara Tonelli, and Elisabetta Jezek. 2023. Why don’t you do it right? analysing annotators’ disagreement in subjective tasks. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 2428–2441, Dubrovnik, Cr… [find](https://scholar.google.com/scholar?q=Marta+Sandri%2C+Elisa+Leonardelli%2C+Sara+Tonelli%2C+and+Elisabetta+Jezek%2E+2023%2E+Why+don%E2%80%99t+you+do+it+right%3F+analysing+annotators%E2%80%99+disagreement+in+subjective+tasks%2E+In+Proceedings+of+the+17th+Conference+of+t)
44. Alexandra N Uma, Tommaso Fornaciari, Dirk Hovy, Silviu Paun, Barbara Plank, and Massimo Poesio. 2021. Learning from disagreement: A survey. Journal of Artificial Intelligence Research, 72:1385–1470. [find](https://scholar.google.com/scholar?q=Alexandra+N+Uma%2C+Tommaso+Fornaciari%2C+Dirk+Hovy%2C+Silviu+Paun%2C+Barbara+Plank%2C+and+Massimo+Poesio%2E+2021%2E+Learning+from+disagreement%3A+A+survey%2E+Journal+of+Artificial+Intelligence+Research%2C+72%3A1385%E2%80%931470%2E)
45. Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. 2023. [Whose opinions do language models reflect?](https://md.research.elamur.ai/free/en/papers/santurkar-2023-whose-opinions-language-models-reflect/) In International Conference on Machine Learning, pages 29971–30004. PMLR.
46. Zhilin Wang, Yi Dong, Olivier Delalleau, Jiaqi Zeng, Gerald Shen, Daniel Egert, Jimmy Zhang, Makesh Narsimhan Sreedhar, and Oleksii Kuchaiev. 2024. Helpsteer 2: Open-source dataset for training top-performing reward models. Advances in Neural Information Processing Systems, 37:1474–1501. [find](https://scholar.google.com/scholar?q=Zhilin+Wang%2C+Yi+Dong%2C+Olivier+Delalleau%2C+Jiaqi+Zeng%2C+Gerald+Shen%2C+Daniel+Egert%2C+Jimmy+Zhang%2C+Makesh+Narsimhan+Sreedhar%2C+and+Oleksii+Kuchaiev%2E+2024%2E+Helpsteer+2%3A+Open%2Dsource+dataset+for+training+top%2Dpe)
47. Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, and Noah A. Smith. 2019. [The risk of racial bias in hate speech detection](https://md.research.elamur.ai/free/en/papers/sap-2019-risk-racial-bias-hate-speech/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 1668–1678, Florence, Italy. Association for Computational Linguistics.
48. Leon Weber-Genzel, Siyao Peng, Marie-Catherine De Marneffe, and Barbara Plank. 2024a. [VariErr NLI: Separating annotation error from human label variation](https://md.research.elamur.ai/free/en/papers/genzel-2024-varierr-nli-separating-annotation-error/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2256–2269, Bangkok, Tha…
49. Edwin Simpson, Erik-Lân Do Dinh, Tristan Miller, and Iryna Gurevych. 2019. Predicting humorousness and metaphor novelty with gaussian process preference learning. In Proceedings of the 57th annual meeting of the association for computational linguistics, pages 5716–5728. [find](https://scholar.google.com/scholar?q=Edwin+Simpson%2C+Erik%2DL%C3%A2n+Do+Dinh%2C+Tristan+Miller%2C+and+Iryna+Gurevych%2E+2019%2E+Predicting+humorousness+and+metaphor+novelty+with+gaussian+process+preference+learning%2E+In+Proceedings+of+the+57th+annual+mee)
50. Leon Weber-Genzel, Siyao Peng, Marie-Catherine De Marneffe, and Barbara Plank. 2024b. [Varierr nli: Separating annotation error from human label variation](https://md.research.elamur.ai/free/en/papers/genzel-2024-varierr-nli-separating-annotation-error/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2256–2269.
51. Irene Solaiman, Zeerak Talat, William Agnew, Lama Ahmad, Dylan Baker, Su Lin Blodgett, Canyu Chen, Hal Daumé III, Jesse Dodge, Isabella Duan, and 1 others. 2023. Evaluating the social impact of generative ai systems in systems and society. arXiv preprint arXiv:2306.05949. — [arXiv:2306.05949](https://arxiv.org/abs/2306.05949) [find](https://scholar.google.com/scholar?q=Irene+Solaiman%2C+Zeerak+Talat%2C+William+Agnew%2C+Lama+Ahmad%2C+Dylan+Baker%2C+Su+Lin+Blodgett%2C+Canyu+Chen%2C+Hal+Daum%C3%A9+III%2C+Jesse+Dodge%2C+Isabella+Duan%2C+and+1+others%2E+2023%2E+Evaluating+the+social+impact+of+genera)
52. Laura Weidinger, John FJ Mellor, Bernat Guillen Pegueroles, Nahema Marchal, Ravin Kumar, Kristian Lum, Canfer Akbulut, Mark Diaz, A Stevie Bergman, Mikel D Rodriguez, and 1 others. 2024. Star: Sociotechnical approach to red teaming language models. In Proceedings of the 2024 Conference on Empirical… [find](https://scholar.google.com/scholar?q=Laura+Weidinger%2C+John+FJ+Mellor%2C+Bernat+Guillen+Pegueroles%2C+Nahema+Marchal%2C+Ravin+Kumar%2C+Kristian+Lum%2C+Canfer+Akbulut%2C+Mark+Diaz%2C+A+Stevie+Bergman%2C+Mikel+D+Rodriguez%2C+and+1+others%2E+2024%2E+Star%3A+Sociote)
53. Taylor Sorensen, Liwei Jiang, Jena Hwang, Sydney Levine, Valentina Pyatkin, Peter West, Nouha Dziri, Ximing Lu, Kavel Rao, Chandra Bhagavatula, and 1 others. 2023. [Value kaleidoscope: Engaging ai with pluralistic human values, rights, and duties](https://md.research.elamur.ai/free/en/papers/sorensen-2023-value-kaleidoscope-engaging-ai-pluralistic/). arXiv preprint arXiv:2309.00779.
54. Taylor Sorensen, Pushkar Mishra, Roma Patel, Michael Henry Tessler, Michiel A. Bakker, Georgina Evans, Iason Gabriel, Noah Goodman, and Verena Rieser. 2025. [Value profiles for encoding human variation](https://md.research.elamur.ai/free/en/papers/sorensen-2025-value-profiles-encoding-human-variation/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 2…
55. Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell Gordon, Niloofar Mireshghallah, Christopher Michael Rytting, Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, and 1 others. 2024. Position: [a roadmap to pluralistic alignment](https://md.research.elamur.ai/free/en/papers/sorensen-2024-roadmap-pluralistic-alignment/). In Proceedings of the 41st International Conference on Machine Learning…
56. Michael Henry Tessler, Michiel A Bakker, Daniel Jarrett, Hannah Sheahan, Martin J Chadwick, Raphael Laura Weidinger, Maribeth Rauh, Nahema Marchal, Arianna Manzini, Lisa Anne Hendricks, Juan Mateos-Garcia, Stevie Bergman, Jackie Kay, Conor Griffin, Ben Bariach, and 1 others. 2023. Sociotechnical saf… — [arXiv:2310.11986](https://arxiv.org/abs/2310.11986) [find](https://scholar.google.com/scholar?q=Michael+Henry+Tessler%2C+Michiel+A+Bakker%2C+Daniel+Jarrett%2C+Hannah+Sheahan%2C+Martin+J+Chadwick%2C+Raphael+Laura+Weidinger%2C+Maribeth+Rauh%2C+Nahema+Marchal%2C+Arianna+Manzini%2C+Lisa+Anne+Hendricks%2C+Juan+Mateos%2DGa)
57. Susan Winter. 2024. The Road Less Taken: Pathways to Ethical and Responsible Technologies, pages 267–281. Springer Nature Switzerland, Cham. [find](https://scholar.google.com/scholar?q=Susan+Winter%2E+2024%2E+The+Road+Less+Taken%3A+Pathways+to+Ethical+and+Responsible+Technologies%2C+pages+267%E2%80%93281%2E+Springer+Nature+Switzerland%2C+Cham%2E)
58. Christian Wirth, Riad Akrour, Gerhard Neumann, and Johannes Fürnkranz. 2017. A survey of preference-based reinforcement learning methods. Journal of Machine Learning Research, 18(136):1–46. [find](https://scholar.google.com/scholar?q=Christian+Wirth%2C+Riad+Akrour%2C+Gerhard+Neumann%2C+and+Johannes+F%C3%BCrnkranz%2E+2017%2E+A+survey+of+preference%2Dbased+reinforcement+learning+methods%2E+Journal+of+Machine+Learning+Research%2C+18%28136%29%3A1%E2%80%9346%2E)
59. Nuoya Xiong and Aarti Singh. 2025. Projection optimization: A general framework for multi-objective and multi-group RLHF. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Nuoya+Xiong+and+Aarti+Singh%2E+2025%2E+Projection+optimization%3A+A+general+framework+for+multi%2Dobjective+and+multi%2Dgroup+RLHF%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2E)
60. Shanshan Xu, TYS Santosh, Yanai Elazar, Quirin Vogel, Barbara Plank, and Matthias Grabmair. 2025. Better aligned with survey respondents or training data? 23769 8 unveiling political leanings of llms on us supreme court cases. arXiv preprint arXiv:2502.18282. — [arXiv:2502.18282](https://arxiv.org/abs/2502.18282) [find](https://scholar.google.com/scholar?q=Shanshan+Xu%2C+TYS+Santosh%2C+Yanai+Elazar%2C+Quirin+Vogel%2C+Barbara+Plank%2C+and+Matthias+Grabmair%2E+2025%2E+Better+aligned+with+survey+respondents+or+training+data%3F+23769+8+unveiling+political+leanings+of+llms+)
61. Shanshan Xu, Leon Staufer, Oana Ichim, Corina Heri, Matthias Grabmair, and 1 others. 2023a. Vechr: A dataset for explainable and robust classification of vulnerability type in the european court of human rights. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processin… [find](https://scholar.google.com/scholar?q=Shanshan+Xu%2C+Leon+Staufer%2C+Oana+Ichim%2C+Corina+Heri%2C+Matthias+Grabmair%2C+and+1+others%2E+2023a%2E+Vechr%3A+A+dataset+for+explainable+and+robust+classification+of+vulnerability+type+in+the+european+court+of+hu)
62. Shanshan Xu, Santosh Tyss, Oana Ichim, Barbara Plank, and Matthias Grabmair. 2024a. Through the lens of split vote: Exploring disagreement, difficulty and calibration in legal case outcome classification. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Vol… [find](https://scholar.google.com/scholar?q=Shanshan+Xu%2C+Santosh+Tyss%2C+Oana+Ichim%2C+Barbara+Plank%2C+and+Matthias+Grabmair%2E+2024a%2E+Through+the+lens+of+split+vote%3A+Exploring+disagreement%2C+difficulty+and+calibration+in+legal+case+outcome+classificat)
63. Shanshan Xu, Santosh T.y.s.s, Oana Ichim, Barbara Plank, and Matthias Grabmair. 2024b. Through the lens of split vote: Exploring disagreement, difficulty and calibration in legal case outcome classification. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (… [find](https://scholar.google.com/scholar?q=Shanshan+Xu%2C+Santosh+T%2Ey%2Es%2Es%2C+Oana+Ichim%2C+Barbara+Plank%2C+and+Matthias+Grabmair%2E+2024b%2E+Through+the+lens+of+split+vote%3A+Exploring+disagreement%2C+difficulty+and+calibration+in+legal+case+outcome+classifi)
64. Shanshan Xu, Santosh T.y.s.s, Oana Ichim, Isabella Risini, Barbara Plank, and Matthias Grabmair. 2023b. From dissonance to insights: Dissecting disagreements in rationale construction for case outcome classification. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Proc… [find](https://scholar.google.com/scholar?q=Shanshan+Xu%2C+Santosh+T%2Ey%2Es%2Es%2C+Oana+Ichim%2C+Isabella+Risini%2C+Barbara+Plank%2C+and+Matthias+Grabmair%2E+2023b%2E+From+dissonance+to+insights%3A+Dissecting+disagreements+in+rationale+construction+for+case+outcome)
65. Michael JQ Zhang, Zhilin Wang, Jena D. Hwang, Yi Dong, Olivier Delalleau, Yejin Choi, Eunsol Choi, Xiang Ren, and Valentina Pyatkin. 2025. Diverging preferences: When do annotators disagree and do models know? In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Michael+JQ+Zhang%2C+Zhilin+Wang%2C+Jena+D%2E+Hwang%2C+Yi+Dong%2C+Olivier+Delalleau%2C+Yejin+Choi%2C+Eunsol+Choi%2C+Xiang+Ren%2C+and+Valentina+Pyatkin%2E+2025%2E+Diverging+preferences%3A+When+do+annotators+disagree+and+do+mod)

*Updated 31 October 2026*