---
title: "HARM — paper by Vecchi et al. (2026) — summary and ideas"
description: "The proposed HARM (Hate-Aware Reward Model) uses a lightweight adapter to re-weight the interpretable attribute outputs of… 84 references."
authors: ["Lorenzo Puppi Vecchi", "Alceu de Souza Britto Jr", "Emerson Cabrera Paraiso", "Rafael Menelau Cruz"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: EACL 2026"
source: "https://aclanthology.org/2026.findings-eacl.230/"
doi: "10.18653/v1/2026.findings-eacl.230"
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/vecchi-2026-harm-learning-hate-aware-reward/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/vecchi-2026-harm-learning-hate-aware-reward/)

[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/13/) / HARM: Learning Hate-Aware Reward Model for Evaluating Natural Language Explanations of Offensive Content

# HARM: Learning Hate-Aware Reward Model for Evaluating Natural Language Explanations of Offensive Content

**Authors:** Lorenzo Puppi Vecchi, Alceu de Souza Britto Jr, Emerson Cabrera Paraiso and Rafael Menelau Cruz · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: EACL 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-eacl.230/) · [PDF](https://aclanthology.org/2026.findings-eacl.230.pdf) · [DOI 10.18653/v1/2026.findings-eacl.230](https://doi.org/10.18653/v1/2026.findings-eacl.230) · [OpenAlex](https://openalex.org/W7140113325)

**Citations:** 1 citations (OpenAlex, 2026-10-14)

## Summary
Automated moderation systems increasingly justify their hate speech decisions with natural language explanations (NLEs), but scoring these explanations is hard. General-purpose reward models (RMs) are tuned for safety, so they tend to penalize explanations that must name stereotypes or offensive content to be faithful to the post. To study this, the authors built SBIC-Explain, a dataset of 370,788 LLM-generated NLEs grounded in the Social Bias Inference Corpus (SBIC). Explanations are produced under three tiers of human-annotated context: text-only, classification-aware, and semantics-informed (using SBIC implied statements). A human study supported the expected ordering: richer context gives higher-fidelity explanations, with Tier 3 judged better than Tier 1. Existing RMs, however, show the reverse pattern and score richer, more sensitive explanations lower. The proposed HARM (Hate-Aware Reward Model) uses a lightweight adapter to re-weight the interpretable attribute outputs of a multi-attribute RM backbone. It restores the expected tier ranking and beats both general-purpose RMs and LLM-as-a-Judge baselines on pairwise NLE preference. This matters for building trustworthy evaluators in sensitive domains.

## Key points
- **SBIC-Explain:** 370,788 synthetic NLEs from multiple models, organized into three context tiers. It builds on SBIC's roughly 34K free-text implied statements, which earlier explainability datasets such as HateCOT largely left unused.
- **Human validation:** the study covered 200 instances with 600 collected annotations, many of which were filtered out for quality. It confirmed significant differences between tiers.
- **Failure mode in existing evaluators:** safety-oriented RMs and LLM-as-a-Judge approaches systematically under-score context-rich explanations that reference stereotypes.
- **HARM design:**
  - It re-weights interpretable attributes from a backbone such as ArmoRM.
  - Its mixture-of-experts variants use output gating, either unsupervised (HARM-MOE-Un) or supervised with SBIC offensiveness annotations (HARM-MOE-Off).
  - HARM-MOE-Off improves expert–offensiveness correlation by 16.6% on average.
- **Limitations and availability:**
  - HARM inherits biases from its backbone RM and from SBIC annotations.
  - It works only as a post hoc evaluator.
  - The code is released at github.com/Lorenzo815/HARM.

*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

- [École de Technologie Supérieure](https://md.research.elamur.ai/free/en/universities/ecole-de-technologie-superieure/) — University, Montreal, Canada · 2 works · 60 citations

Also on the byline: [Pontifícia Universidade Católica do Paraná](https://ror.org/02x1vjk79).

📚 Shelves (4): [🖥️ 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 · [🤝 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

🧭 Topics (1): [🛡️ Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · 517 works

## Cite

Cite as: Lorenzo Puppi Vecchi, Alceu de Souza Britto Jr, Emerson Cabrera Paraiso and Rafael Menelau Cruz. 2026. HARM: Learning Hate-Aware Reward Model for Evaluating Natural Language Explanations of Offensive Content. Findings of the Association for Computational Linguistics: EACL 2026.

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

```bibtex
@inproceedings{vecchi2026harm,
  title = {{HARM: Learning Hate-Aware Reward Model for Evaluating Natural Language Explanations of Offensive Content}},
  author = {Lorenzo Puppi Vecchi, Alceu {de Souza Britto Jr}, Emerson Cabrera Paraiso and Rafael Menelau Cruz},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.230},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.230}
}
```

- [← previous Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment](https://md.research.elamur.ai/free/en/papers/azad-2026-harf-speech-clinically-aligned-framework/)
- [next → HARNESS: Lightweight Distilled Arabic Speech Foundation Models](https://md.research.elamur.ai/free/en/papers/sukhadia-2026-harness-lightweight-distilled-arabic-speech/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/13/)

## References

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

1. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann, James R. Lee, Yin Tat Lee, Yuanzhi Li, Weishung Liu, Caio C. T. Mendes, Anh Nguyen, Eric Price, Gustavo de Rosa, Olli Saarikivi, and 8 oth… — [Phi-4 Technical Report](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-4-technical-report/)
2. Monica Agrawal, Stefan Hegselmann, Hunter Lang, Yoon Kim, and David Sontag. 2022. [Large language models are few-shot clinical information extractors](https://md.research.elamur.ai/free/en/papers/agrawal-2022-large-language-models-few-shot/). Preprint, arXiv:2205.12689.
3. Kofi Arhin, Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, and Moninder Singh. 2021. Ground-truth, whose truth? – examining the challenges with annotating toxic text datasets. Preprint, arXiv:2112.03529. — [arXiv:2112.03529](https://arxiv.org/abs/2112.03529) [find](https://scholar.google.com/scholar?q=Kofi+Arhin%2C+Ioana+Baldini%2C+Dennis+Wei%2C+Karthikeyan+Natesan+Ramamurthy%2C+and+Moninder+Singh%2E+2021%2E+Ground%2Dtruth%2C+whose+truth%3F+%E2%80%93+examining+the+challenges+with+annotating+toxic+text+datasets%2E+Preprint%2C+ar)
4. Muhammad Umair Arshad and Waseem Shahzad. 2024. Understanding hate speech: the HateInsights dataset and model interpretability. 10:e2372. [find](https://scholar.google.com/scholar?q=Muhammad+Umair+Arshad+and+Waseem+Shahzad%2E+2024%2E+Understanding+hate+speech%3A+the+HateInsights+dataset+and+model+interpretability%2E+10%3Ae2372%2E)
5. Hüseyin Aydn, Kevin Godin-Dubois, Libio Goncalvez Braz, Floris den Hengst, Kim Baraka, Mustafa Mert Çelikok, Andreas Sauter, Shihan Wang, and Frans A. Oliehoek. 2025. Sharpie: A modular framework for reinforcement learning and human-ai interaction experiments. Preprint, arXiv:2501.19245. — [arXiv:2501.19245](https://arxiv.org/abs/2501.19245) [find](https://scholar.google.com/scholar?q=H%C3%BCseyin+Aydn%2C+Kevin+Godin%2DDubois%2C+Libio+Goncalvez+Braz%2C+Floris+den+Hengst%2C+Kim+Baraka%2C+Mustafa+Mert+%C3%87elikok%2C+Andreas+Sauter%2C+Shihan+Wang%2C+and+Frans+A%2E+Oliehoek%2E+2025%2E+Sharpie%3A+A+modular+framework+for+)
6. Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, Nicholas Joseph, Saurav Kadavath, Jackson Kernion, Tom Conerly, Sheer El-Showk, Nelson Elhage, Zac Hatfield-Dodds, Danny Hernandez, Tristan Hume, and 12 others. 202… [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+Nicholas+Joseph%2C+Saurav+Kadavath%2C+Jackson+Kernion%2C+Tom+Conerly%2C+)
7. Francesco Barbieri, Jose Camacho-Collados, Leonardo Neves, and Luis Espinosa-Anke. 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/). Preprint, arXiv:2010.12421.
8. Daniel Borkan, Lucas Dixon, Jeffrey Sorensen, Nithum Thain, and Lucy Vasserman. 2019. Nuanced metrics for measuring unintended bias with real data for text classification. CoRR, abs/1903.04561. — [arXiv:1903.04561](https://arxiv.org/abs/1903.04561) [find](https://scholar.google.com/scholar?q=Daniel+Borkan%2C+Lucas+Dixon%2C+Jeffrey+Sorensen%2C+Nithum+Thain%2C+and+Lucy+Vasserman%2E+2019%2E+Nuanced+metrics+for+measuring+unintended+bias+with+real+data+for+text+classification%2E+CoRR%2C+abs%2F1903%2E04561%2E+%E2%80%94+%5BarX)
9. Ralph Allan Bradley and Milton E. Terry. 1952. Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39:324. [find](https://scholar.google.com/scholar?q=Ralph+Allan+Bradley+and+Milton+E%2E+Terry%2E+1952%2E+Rank+analysis+of+incomplete+block+designs%3A+I%2E+the+method+of+paired+comparisons%2E+Biometrika%2C+39%3A324%2E)
10. Faeze Brahman, Sachin Kumar, Vidhisha Balachandran, Pradeep Dasigi, Valentina Pyatkin, Abhilasha Ravichander, Sarah Wiegreffe, Nouha Dziri, Khyathi Chandu, Jack Hessel, Yulia Tsvetkov, Noah A. Smith, Yejin Choi, and Hannaneh Hajishirzi. 2024. [The art of saying no: Contextual noncompliance in languag…](https://md.research.elamur.ai/free/en/papers/brahman-2024-art-saying-no-contextual-noncompliance/)
11. Marc Brysbaert. 2019. How many words do we read per minute? a review and meta-analysis of reading rate. Journal of Memory and Language, 109:104047. [find](https://scholar.google.com/scholar?q=Marc+Brysbaert%2E+2019%2E+How+many+words+do+we+read+per+minute%3F+a+review+and+meta%2Danalysis+of+reading+rate%2E+Journal+of+Memory+and+Language%2C+109%3A104047%2E)
12. Ilias Chalkidis, Manos Fergadiotis, and Ion Androutsopoulos. 2021. [MultiEURLEX - a multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer](https://md.research.elamur.ai/free/en/papers/chalkidis-2021-multieurlex-multi-lingual-multi-label/). In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6974–6996, Onl…
13. Lichang Chen, Chen Zhu, Davit Soselia, Jiuhai Chen, Tianyi Zhou, Tom Goldstein, Heng Huang, Mohammad Shoeybi, and Bryan Catanzaro. 2024a. Odin: Disentangled reward mitigates hacking in rlhf. Preprint, arXiv:2402.07319. [find](https://scholar.google.com/scholar?q=Lichang+Chen%2C+Chen+Zhu%2C+Davit+Soselia%2C+Jiuhai+Chen%2C+Tianyi+Zhou%2C+Tom+Goldstein%2C+Heng+Huang%2C+Mohammad+Shoeybi%2C+and+Bryan+Catanzaro%2E+2024a%2E+Odin%3A+Disentangled+reward+mitigates+hacking+in+rlhf%2E+Preprint%2C)
14. Yanjun Chen, Dawei Zhu, Yirong Sun, Xinghao Chen, Wei Zhang, and Xiaoyu Shen. 2024b. The accuracy paradox in RLHF: When better reward models don’t yield better language models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 2980–2989, Miami, Florida,… [find](https://scholar.google.com/scholar?q=Yanjun+Chen%2C+Dawei+Zhu%2C+Yirong+Sun%2C+Xinghao+Chen%2C+Wei+Zhang%2C+and+Xiaoyu+Shen%2E+2024b%2E+The+accuracy+paradox+in+RLHF%3A+When+better+reward+models+don%E2%80%99t+yield+better+language+models%2E+In+Proceedings+of+the+2)
15. Brian Christian, Hannah Rose Kirk, Jessica A.F. Thompson, Christopher Summerfield, and Tsvetomira Dumbalska. 2025. Reward model interpretability via optimal and pessimal tokens. In Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, FAccT 25, page 10481059. ACM. [find](https://scholar.google.com/scholar?q=Brian+Christian%2C+Hannah+Rose+Kirk%2C+Jessica+A%2EF%2E+Thompson%2C+Christopher+Summerfield%2C+and+Tsvetomira+Dumbalska%2E+2025%2E+Reward+model+interpretability+via+optimal+and+pessimal+tokens%2E+In+Proceedings+of+the+)
16. Jaymari Chua, Yun Li, Shiyi Yang, Chen Wang, and Lina Yao. 2024. Ai safety in generative ai [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). Preprint, arXiv:2407.18369. — [arXiv:2407.18369](https://arxiv.org/abs/2407.18369)
17. Simone Conia, Daniel Lee, Min Li, Umar Farooq Minhas, Saloni Potdar, and Yunyao Li. 2024. Towards cross-cultural machine translation with retrieval-augmented generation from multilingual knowledge graphs. Preprint, arXiv:2410.14057. [find](https://scholar.google.com/scholar?q=Simone+Conia%2C+Daniel+Lee%2C+Min+Li%2C+Umar+Farooq+Minhas%2C+Saloni+Potdar%2C+and+Yunyao+Li%2E+2024%2E+Towards+cross%2Dcultural+machine+translation+with+retrieval%2Daugmented+generation+from+multilingual+knowledge+gra)
18. Ganqu Cui, Lifan Yuan, Ning Ding, Guanming Yao, Bingxiang He, Wei Zhu, Yuan Ni, Guotong Xie, Ruobing Xie, Yankai Lin, Zhiyuan Liu, and Maosong Sun. 2024. Ultrafeedback: Boosting language models with scaled ai feedback. Preprint, arXiv:2310.01377. [find](https://scholar.google.com/scholar?q=Ganqu+Cui%2C+Lifan+Yuan%2C+Ning+Ding%2C+Guanming+Yao%2C+Bingxiang+He%2C+Wei+Zhu%2C+Yuan+Ni%2C+Guotong+Xie%2C+Ruobing+Xie%2C+Yankai+Lin%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2024%2E+Ultrafeedback%3A+Boosting+language+models+with+s)
19. Luigi Daniele and Suphavadeeprasit. 2023. Amplify-instruct: Synthetically generated diverse multi-turn conversations for efficient llm training. arXiv preprint arXiv:(coming soon). [find](https://scholar.google.com/scholar?q=Luigi+Daniele+and+Suphavadeeprasit%2E+2023%2E+Amplify%2Dinstruct%3A+Synthetically+generated+diverse+multi%2Dturn+conversations+for+efficient+llm+training%2E+arXiv+preprint+arXiv%3A%28coming+soon%29%2E)
20. Zahra Delbari, Nafise Sadat Moosavi, and Mohammad Taher Pilehvar. 2024. Spanning the spectrum of hatred detection: A persian multi-label hate speech dataset with annotator rationales. Proceedings of the AAAI Conference on Artificial Intelligence, 38(16):17889–17897. [find](https://scholar.google.com/scholar?q=Zahra+Delbari%2C+Nafise+Sadat+Moosavi%2C+and+Mohammad+Taher+Pilehvar%2E+2024%2E+Spanning+the+spectrum+of+hatred+detection%3A+A+persian+multi%2Dlabel+hate+speech+dataset+with+annotator+rationales%2E+Proceedings+of+t)
21. Nan Du, Yanping Huang, Andrew M. Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fedus, Maarten Bosma, Zongwei Zhou, Tao Wang, Yu Emma Wang, Kellie Webster, Marie Pellat, Kevin Robinson, and 8 others. 2022. [Glam: Efficient scalin…](https://md.research.elamur.ai/free/en/papers/du-2021-glam-efficient-scaling-language-models/)
22. Hui Huang, Xingyuan Bu, Hongli Zhou, Yingqi Qu, Jing Liu, Muyun Yang, Bing Xu, and Tiejun Zhao. 2025. An empirical study of LLM-as-a-judge for LLM evaluation: Fine-tuned judge model is not a general substitute for GPT-4. In Findings of the Association for Computational Linguistics: ACL 2025, pages 5… [find](https://scholar.google.com/scholar?q=Hui+Huang%2C+Xingyuan+Bu%2C+Hongli+Zhou%2C+Yingqi+Qu%2C+Jing+Liu%2C+Muyun+Yang%2C+Bing+Xu%2C+and+Tiejun+Zhao%2E+2025%2E+An+empirical+study+of+LLM%2Das%2Da%2Djudge+for+LLM+evaluation%3A+Fine%2Dtuned+judge+model+is+not+a+general+s)
23. Cesaire J. K. Fouodo, Lea L. Kronziel, Inke R. König, and Silke Szymczak. 2025. Effect of hyperparameters on variable selection in random forests. Preprint, arXiv:2309.06943. — [arXiv:2309.06943](https://arxiv.org/abs/2309.06943) [find](https://scholar.google.com/scholar?q=Cesaire+J%2E+K%2E+Fouodo%2C+Lea+L%2E+Kronziel%2C+Inke+R%2E+K%C3%B6nig%2C+and+Silke+Szymczak%2E+2025%2E+Effect+of+hyperparameters+on+variable+selection+in+random+forests%2E+Preprint%2C+arXiv%3A2309%2E06943%2E+%E2%80%94+%5BarXiv%3A2309%2E06943%5D%28http)
24. Olivia Huang, Eve Fleisig, and Dan Klein. 2023b. Incorporating worker perspectives into MTurk annotation practices for NLP. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 1010–1028, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Olivia+Huang%2C+Eve+Fleisig%2C+and+Dan+Klein%2E+2023b%2E+Incorporating+worker+perspectives+into+MTurk+annotation+practices+for+NLP%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natural+Langua)
25. Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2024. GPTScore: Evaluate as you desire. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 6556–6576, Mexico City, M… [find](https://scholar.google.com/scholar?q=Jinlan+Fu%2C+See%2DKiong+Ng%2C+Zhengbao+Jiang%2C+and+Pengfei+Liu%2E+2024%2E+GPTScore%3A+Evaluate+as+you+desire%2E+In+Proceedings+of+the+2024+Conference+of+the+North+American+Chapter+of+the+Association+for+Computation)
26. Tianyu Han, Lisa C. Adams, Jens-Michalis Papaioannou, Paul Grundmann, Tom Oberhauser, Alexei Figueroa, Alexander Löser, Daniel Truhn, and Keno K. Bressem. 2025. [Medalpaca – an open-source collection of medical conversational ai models and training data](https://md.research.elamur.ai/free/en/papers/han-2023-medalpaca-open-source-collection-medical/). Preprint, arXiv:2304.08247.
27. Phu Gia Hoang, Canh Duc Luu, Khanh Quoc Tran, Kiet Van Nguyen, and Ngan Luu-Thuy Nguyen. 2023. ViHOS: Hate speech spans detection for Vietnamese. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 652–669, Dubrovnik, Croatia. Associa… [find](https://scholar.google.com/scholar?q=Phu+Gia+Hoang%2C+Canh+Duc+Luu%2C+Khanh+Quoc+Tran%2C+Kiet+Van+Nguyen%2C+and+Ngan+Luu%2DThuy+Nguyen%2E+2023%2E+ViHOS%3A+Hate+speech+spans+detection+for+Vietnamese%2E+In+Proceedings+of+the+17th+Conference+of+the+European+)
28. Sanne Hoeken, Sina Zarrieß, and Özge Alacam. 2024. Hateful word in context classification. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 172–186, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sanne+Hoeken%2C+Sina+Zarrie%C3%9F%2C+and+%C3%96zge+Alacam%2E+2024%2E+Hateful+word+in+context+classification%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+172%E2%80%93186%2C+Mia)
29. Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, and Eduard Hovy. 2013. [Learning whom to trust with MACE](https://md.research.elamur.ai/free/en/papers/hovy-2013-learning-whom-trust-mace/). In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1120–1130, Atlanta, Georgia. Associati…
30. Fan Huang, Haewoon Kwak, and Jisun An. 2023a. Chain of explanation: New prompting method to generate quality natural language explanation for implicit hate speech. In Companion Proceedings of the ACM Web Conference 2023, WWW ’23 Companion, page 9093, New York, NY, USA. Association for Computing Mach… [find](https://scholar.google.com/scholar?q=Fan+Huang%2C+Haewoon+Kwak%2C+and+Jisun+An%2E+2023a%2E+Chain+of+explanation%3A+New+prompting+method+to+generate+quality+natural+language+explanation+for+implicit+hate+speech%2E+In+Companion+Proceedings+of+the+ACM+)
31. Fan Huang, Haewoon Kwak, Kunwoo Park, and Jisun An. 2024. Chatgpt rates natural language explanation quality like humans: But on which scales? Preprint, arXiv:2403.17368. [find](https://scholar.google.com/scholar?q=Fan+Huang%2C+Haewoon+Kwak%2C+Kunwoo+Park%2C+and+Jisun+An%2E+2024%2E+Chatgpt+rates+natural+language+explanation+quality+like+humans%3A+But+on+which+scales%3F+Preprint%2C+arXiv%3A2403%2E17368%2E)
32. Md Saroar Jahan and Mourad Oussalah. 2021. A systematic review of hate speech automatic detection using natural language processing. Preprint, arXiv:2106.00742. — [arXiv:2106.00742](https://arxiv.org/abs/2106.00742) [find](https://scholar.google.com/scholar?q=Md+Saroar+Jahan+and+Mourad+Oussalah%2E+2021%2E+A+systematic+review+of+hate+speech+automatic+detection+using+natural+language+processing%2E+Preprint%2C+arXiv%3A2106%2E00742%2E+%E2%80%94+%5BarXiv%3A2106%2E00742%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
33. Jiaming Ji, Mickel Liu, Juntao Dai, Xuehai Pan, Chi Zhang, Ce Bian, Chi Zhang, Ruiyang Sun, Yizhou Wang, and Yaodong Yang. 2023. [Beavertails: Towards improved safety alignment of llm via a human-preference dataset](https://md.research.elamur.ai/free/en/papers/ji-2023-beavertails-towards-improved-safety-alignment/). Preprint, arXiv:2307.04657.
34. Dongfu Jiang, Yishan Li, Ge Zhang, Wenhao Huang, Bill Yuchen Lin, and Wenhu Chen. 2024. TIGER-Score: Towards building explainable metric for all text generation tasks. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Dongfu+Jiang%2C+Yishan+Li%2C+Ge+Zhang%2C+Wenhao+Huang%2C+Bill+Yuchen+Lin%2C+and+Wenhu+Chen%2E+2024%2E+TIGER%2DScore%3A+Towards+building+explainable+metric+for+all+text+generation+tasks%2E+Transactions+on+Machine+Learning)
35. Junqi Jiang, Tom Bewley, Saumitra Mishra, Freddy Lecue, and Manuela Veloso. 2025. Interpreting language reward models via contrastive explanations. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Junqi+Jiang%2C+Tom+Bewley%2C+Saumitra+Mishra%2C+Freddy+Lecue%2C+and+Manuela+Veloso%2E+2025%2E+Interpreting+language+reward+models+via+contrastive+explanations%2E+In+The+Thirteenth+International+Conference+on+Learni)
36. Masahiro Kaneko and Danushka Bollegala. 2021. Unmasking the mask – evaluating social biases in masked language models. Preprint, arXiv:2104.07496. — [arXiv:2104.07496](https://arxiv.org/abs/2104.07496) [find](https://scholar.google.com/scholar?q=Masahiro+Kaneko+and+Danushka+Bollegala%2E+2021%2E+Unmasking+the+mask+%E2%80%93+evaluating+social+biases+in+masked+language+models%2E+Preprint%2C+arXiv%3A2104%2E07496%2E+%E2%80%94+%5BarXiv%3A2104%2E07496%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2104%2E07496)
37. Alex Kendall, Yarin Gal, and Roberto Cipolla. 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. Preprint, arXiv:1705.07115. — [arXiv:1705.07115](https://arxiv.org/abs/1705.07115) [find](https://scholar.google.com/scholar?q=Alex+Kendall%2C+Yarin+Gal%2C+and+Roberto+Cipolla%2E+2018%2E+Multi%2Dtask+learning+using+uncertainty+to+weigh+losses+for+scene+geometry+and+semantics%2E+Preprint%2C+arXiv%3A1705%2E07115%2E+%E2%80%94+%5BarXiv%3A1705%2E07115%5D%28https%3A%2F%2Farx)
38. Ahrii Kim. 2025. RUBRIC-MQM : Span-level LLM-as-judge in machine translation for high-end models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track), pages 147–165, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ahrii+Kim%2E+2025%2E+RUBRIC%2DMQM+%3A+Span%2Dlevel+LLM%2Das%2Djudge+in+machine+translation+for+high%2Dend+models%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+%28Volume+6%3A+)
39. Seungone Kim, Jamin Shin, Yejin Cho, Joel Jang, Shayne Longpre, Hwaran Lee, Sangdoo Yun, Seongjin Shin, Sungdong Kim, James Thorne, and Minjoon Seo. 2024. [Prometheus: Inducing fine-grained evaluation capability in language models](https://md.research.elamur.ai/free/en/papers/kim-2023-prometheus-inducing-fine-grained-evaluation/). In The Twelfth International Conference on Learning Representations.
40. Youngwook Kim, Shinwoo Park, Youngsoo Namgoong, and Yo-Sub Han. 2023. ConPrompt: Pre-training a language model with machine-generated data for implicit hate speech detection. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10964–10980, Singapore. Association for Compu… [find](https://scholar.google.com/scholar?q=Youngwook+Kim%2C+Shinwoo+Park%2C+Youngsoo+Namgoong%2C+and+Yo%2DSub+Han%2E+2023%2E+ConPrompt%3A+Pre%2Dtraining+a+language+model+with+machine%2Dgenerated+data+for+implicit+hate+speech+detection%2E+In+Findings+of+the+Associ)
41. Saumya Malik, Valentina Pyatkin, Sander Land, Jacob Morrison, Noah A. Smith, Hannaneh Hajishirzi, and Nathan Lambert. 2025. Rewardbench 2: Advancing reward model evaluation. Preprint, arXiv:2506.01937. — [arXiv:2506.01937](https://arxiv.org/abs/2506.01937) [find](https://scholar.google.com/scholar?q=Saumya+Malik%2C+Valentina+Pyatkin%2C+Sander+Land%2C+Jacob+Morrison%2C+Noah+A%2E+Smith%2C+Hannaneh+Hajishirzi%2C+and+Nathan+Lambert%2E+2025%2E+Rewardbench+2%3A+Advancing+reward+model+evaluation%2E+Preprint%2C+arXiv%3A2506%2E01937)
42. Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 64056416, Red Hook, NY, USA. Curran Associat… [find](https://scholar.google.com/scholar?q=Balaji+Lakshminarayanan%2C+Alexander+Pritzel%2C+and+Charles+Blundell%2E+2017%2E+Simple+and+scalable+predictive+uncertainty+estimation+using+deep+ensembles%2E+In+Proceedings+of+the+31st+International+Conference+)
43. Binny Mathew, Punyajoy Saha, Seid Muhie Yimam, Chris Biemann, Pawan Goyal, and Animesh Mukherjee. 2022. Hatexplain: A benchmark dataset for explainable hate speech detection. Preprint, arXiv:2012.10289. [find](https://scholar.google.com/scholar?q=Binny+Mathew%2C+Punyajoy+Saha%2C+Seid+Muhie+Yimam%2C+Chris+Biemann%2C+Pawan+Goyal%2C+and+Animesh+Mukherjee%2E+2022%2E+Hatexplain%3A+A+benchmark+dataset+for+explainable+hate+speech+detection%2E+Preprint%2C+arXiv%3A2012%2E1028)
44. Nathan Lambert, Valentina Pyatkin, Jacob Morrison, LJ Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, and Hannaneh Hajishirzi. 2024. Rewardbench: Evaluating reward models for language modeling. Preprint, arXiv:2403.13787. [find](https://scholar.google.com/scholar?q=Nathan+Lambert%2C+Valentina+Pyatkin%2C+Jacob+Morrison%2C+LJ+Miranda%2C+Bill+Yuchen+Lin%2C+Khyathi+Chandu%2C+Nouha+Dziri%2C+Sachin+Kumar%2C+Tom+Zick%2C+Yejin+Choi%2C+Noah+A%2E+Smith%2C+and+Hannaneh+Hajishirzi%2E+2024%2E+Rewardben)
45. Yongqi Leng, Renren Jin, Yue Chen, Zhuowen Han, Ling Shi, Jianxiang Peng, Lei Yang, Juesi Xiao, and Deyi Xiong. 2025. Praetor: A fine-grained generative LLM evaluator with instance-level customizable evaluation criteria. In Proceedings of the 63rd Annual Meeting of the Association for Computational… [find](https://scholar.google.com/scholar?q=Yongqi+Leng%2C+Renren+Jin%2C+Yue+Chen%2C+Zhuowen+Han%2C+Ling+Shi%2C+Jianxiang+Peng%2C+Lei+Yang%2C+Juesi+Xiao%2C+and+Deyi+Xiong%2E+2025%2E+Praetor%3A+A+fine%2Dgrained+generative+LLM+evaluator+with+instance%2Dlevel+customizable+)
46. Haitao Li, Qian Dong, Junjie Chen, Huixue Su, Yujia Zhou, Qingyao Ai, Ziyi Ye, and Yiqun Liu. 2024. [Llms-as-judges: A comprehensive survey on llm-based evaluation methods](https://md.research.elamur.ai/free/en/papers/li-2024-llms-judges-comprehensive-survey-llm/). Preprint, arXiv:2412.05579.
47. Chin-Yew Lin. 2004. [ROUGE: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics.
48. Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu. 2023. [G-eval: Nlg evaluation using gpt-4 with better human alignment](https://md.research.elamur.ai/free/en/papers/liu-2023-g-eval-nlg-evaluation-gpt/). Preprint, arXiv:2303.16634.
49. Xingzhou Lou, Dong Yan, Wei Shen, Yuzi Yan, Jian Xie, and Junge Zhang. 2025. Uncertainty-aware reward model: Teaching reward models to know what is unknown. Preprint, arXiv:2410.00847. — [arXiv:2410.00847](https://arxiv.org/abs/2410.00847) [find](https://scholar.google.com/scholar?q=Xingzhou+Lou%2C+Dong+Yan%2C+Wei+Shen%2C+Yuzi+Yan%2C+Jian+Xie%2C+and+Junge+Zhang%2E+2025%2E+Uncertainty%2Daware+reward+model%3A+Teaching+reward+models+to+know+what+is+unknown%2E+Preprint%2C+arXiv%3A2410%2E00847%2E+%E2%80%94+%5BarXiv%3A2410%2E0)
50. Lu Lu, Nathan Neale, Nathaniel D. Line, and Mark Bonn. 2022. Improving data quality using amazon mechanical turk through platform setup. Cornell Hospitality Quarterly, 63(2):231–246. [find](https://scholar.google.com/scholar?q=Lu+Lu%2C+Nathan+Neale%2C+Nathaniel+D%2E+Line%2C+and+Mark+Bonn%2E+2022%2E+Improving+data+quality+using+amazon+mechanical+turk+through+platform+setup%2E+Cornell+Hospitality+Quarterly%2C+63%282%29%3A231%E2%80%93246%2E)
51. Qing Lyu, Marianna Apidianaki, and Chris Callison-Burch. 2024. [Towards faithful model explanation in NLP: A survey](https://md.research.elamur.ai/free/en/papers/lyu-2024-faithful-model-explanation-nlp-survey/). Computational Linguistics, 50(2):657–723.
52. Jitendra Singh Malik, Hezhe Qiao, Guansong Pang, and Anton van den Hengel. 2023. Deep learning for hate speech detection: A comparative study. Preprint, arXiv:2202.09517. — [arXiv:2202.09517](https://arxiv.org/abs/2202.09517) [find](https://scholar.google.com/scholar?q=Jitendra+Singh+Malik%2C+Hezhe+Qiao%2C+Guansong+Pang%2C+and+Anton+van+den+Hengel%2E+2023%2E+Deep+learning+for+hate+speech+detection%3A+A+comparative+study%2E+Preprint%2C+arXiv%3A2202%2E09517%2E+%E2%80%94+%5BarXiv%3A2202%2E09517%5D%28https%3A%2F%2F)
53. Michael D McKay, Richard J Beckman, and William J Conover. 2000. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics, 42(1):55–61. [find](https://scholar.google.com/scholar?q=Michael+D+McKay%2C+Richard+J+Beckman%2C+and+William+J+Conover%2E+2000%2E+A+comparison+of+three+methods+for+selecting+values+of+input+variables+in+the+analysis+of+output+from+a+computer+code%2E+Technometrics%2C+42)
54. Dauglas Montgomery and Cahyono St. 2022. Design and Analysis of Experiments, 9th Edition. [find](https://scholar.google.com/scholar?q=Dauglas+Montgomery+and+Cahyono+St%2E+2022%2E+Design+and+Analysis+of+Experiments%2C+9th+Edition%2E)
55. Rachna Narula and Poonam Chaudhary. 2024. A comprehensive review on detection of hate speech for multi-lingual data. Social Network Analysis and Mining, 14(1):244. [find](https://scholar.google.com/scholar?q=Rachna+Narula+and+Poonam+Chaudhary%2E+2024%2E+A+comprehensive+review+on+detection+of+hate+speech+for+multi%2Dlingual+data%2E+Social+Network+Analysis+and+Mining%2C+14%281%29%3A244%2E)
56. Huy Nghiem and Hal Daumé Iii. 2024. HateCOT: An explanation-enhanced dataset for generalizable offensive speech detection via large language models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5938–5956, Miami, Florida, USA. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Huy+Nghiem+and+Hal+Daum%C3%A9+Iii%2E+2024%2E+HateCOT%3A+An+explanation%2Denhanced+dataset+for+generalizable+offensive+speech+detection+via+large+language+models%2E+In+Findings+of+the+Association+for+Computational+Li)
57. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. [Train…](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)
58. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 311–318, Philadelphia, Pennsylvania, USA. Association for Computational…
59. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Te-jani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, and 2 others. 2019.… — [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/)
60. John Pavlopoulos, Jeffrey Sorensen, Léo Laugier, and Ion Androutsopoulos. 2021. [SemEval-2021 task 5: Toxic spans detection](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2021-semeval-2021-task-5-toxic/). In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 59–69, Online. Association for Computational Linguistics.
61. Jonas Pfeiffer, Sebastian Ruder, Ivan Vuli, and Edoardo Maria Ponti. 2024. Modular deep learning. Preprint, arXiv:2302.11529. — [arXiv:2302.11529](https://arxiv.org/abs/2302.11529) [find](https://scholar.google.com/scholar?q=Jonas+Pfeiffer%2C+Sebastian+Ruder%2C+Ivan+Vuli%2C+and+Edoardo+Maria+Ponti%2E+2024%2E+Modular+deep+learning%2E+Preprint%2C+arXiv%3A2302%2E11529%2E+%E2%80%94+%5BarXiv%3A2302%2E11529%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2302%2E11529%29)
62. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. 2023. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). In Advances in Neural Information Processing Systems, volume 36, pages 53728–53741. Curran Associates, Inc.
63. Manikandan Ravikiran and Subbiah Annamalai. 2021. DOSA: Dravidian code-mixed offensive span identification dataset. In Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages, pages 10–17, Kyiv. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Manikandan+Ravikiran+and+Subbiah+Annamalai%2E+2021%2E+DOSA%3A+Dravidian+code%2Dmixed+offensive+span+identification+dataset%2E+In+Proceedings+of+the+First+Workshop+on+Speech+and+Language+Technologies+for+Dravidi)
64. Paul Röttger, Hannah Rose Kirk, Bertie Vidgen, Giuseppe Attanasio, Federico Bianchi, and Dirk Hovy. 2024. [Xstest: A test suite for identifying exaggerated safety behaviours in large language models](https://md.research.elamur.ai/free/en/papers/rottger-2023-xstest-test-suite-identifying-exaggerated/). Preprint, arXiv:2308.01263.
65. Ananya B. Sai, Akash Kumar Mohankumar, and Mitesh M. Khapra. 2020. A survey of evaluation metrics used for nlg systems. Preprint, arXiv:2008.12009. [find](https://scholar.google.com/scholar?q=Ananya+B%2E+Sai%2C+Akash+Kumar+Mohankumar%2C+and+Mitesh+M%2E+Khapra%2E+2020%2E+A+survey+of+evaluation+metrics+used+for+nlg+systems%2E+Preprint%2C+arXiv%3A2008%2E12009%2E)
66. Isadora Salles, Francielle Vargas, and Fabrício Benevenuto. 2025. HateBRXplain: A benchmark dataset with human-annotated rationales for explainable hate speech detection in Brazilian Portuguese. In Proceedings of the 31st International Conference on Computational Linguistics, pages 6659–6669, Abu Dh… [find](https://scholar.google.com/scholar?q=Isadora+Salles%2C+Francielle+Vargas%2C+and+Fabr%C3%ADcio+Benevenuto%2E+2025%2E+HateBRXplain%3A+A+benchmark+dataset+with+human%2Dannotated+rationales+for+explainable+hate+speech+detection+in+Brazilian+Portuguese%2E+In+Pr)
67. 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.
68. Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky, Noah A. Smith, and Yejin Choi. 2020. [Social bias frames: Reasoning about social and power implications of language](https://md.research.elamur.ai/free/en/papers/sap-2020-social-bias-frames-reasoning-about/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5477–5490, Online. Association…
69. Chantal Shaib, Joe Barrow, Jiuding Sun, Alexa F. Siu, Byron C. Wallace, and Ani Nenkova. 2025. Standardizing the measurement of text diversity: A tool and a comparative analysis of scores. Preprint, arXiv:2403.00553. — [arXiv:2403.00553](https://arxiv.org/abs/2403.00553) [find](https://scholar.google.com/scholar?q=Chantal+Shaib%2C+Joe+Barrow%2C+Jiuding+Sun%2C+Alexa+F%2E+Siu%2C+Byron+C%2E+Wallace%2C+and+Ani+Nenkova%2E+2025%2E+Standardizing+the+measurement+of+text+diversity%3A+A+tool+and+a+comparative+analysis+of+scores%2E+Preprint%2C+a)
70. Sheng Shen, Le Hou, Yanqi Zhou, Nan Du, Shayne Longpre, Jason Wei, Hyung Won Chung, Barret Zoph, William Fedus, Xinyun Chen, Tu Vu, Yuexin Wu, Wuyang Chen, Albert Webson, Yunxuan Li, Vincent Zhao, Hongkun Yu, Kurt Keutzer, Trevor Darrell, and Denny Zhou. 2023. [Mixture-of-experts meets instruction tu…](https://md.research.elamur.ai/free/en/papers/shen-2023-mixture-experts-meets-instruction-tuning/)
71. Tianxiang Sun, Junliang He, Xipeng Qiu, and Xuanjing Huang. 2022. BERTScore is unfair: On social bias in language model-based metrics for text generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3726–3739, Abu Dhabi, United Arab Emirates. Asso… [find](https://scholar.google.com/scholar?q=Tianxiang+Sun%2C+Junliang+He%2C+Xipeng+Qiu%2C+and+Xuanjing+Huang%2E+2022%2E+BERTScore+is+unfair%3A+On+social+bias+in+language+model%2Dbased+metrics+for+text+generation%2E+In+Proceedings+of+the+2022+Conference+on+Empi)
72. Falcon-LLM Team. 2024. The falcon 3 family of open models. [find](https://scholar.google.com/scholar?q=Falcon%2DLLM+Team%2E+2024%2E+The+falcon+3+family+of+open+models%2E)
73. Gemma Team, Aishwarya Kamath, Johan Ferret, Shreya Pathak, Nino Vieillard, Ramona Merhej, Sarah Perrin, Tatiana Matejovicova, Alexandre Ramé, Morgane Rivière, Louis Rouillard, Thomas Mesnard, Geoffrey Cideron, Jean bastien Grill, Sabela Ramos, Edouard Yvinec, Michelle Casbon, Etienne Pot, Ivo Penche… [find](https://scholar.google.com/scholar?q=Gemma+Team%2C+Aishwarya+Kamath%2C+Johan+Ferret%2C+Shreya+Pathak%2C+Nino+Vieillard%2C+Ramona+Merhej%2C+Sarah+Perrin%2C+Tatiana+Matejovicova%2C+Alexandre+Ram%C3%A9%2C+Morgane+Rivi%C3%A8re%2C+Louis+Rouillard%2C+Thomas+Mesnard%2C+Geoffrey)
74. Haoxiang Wang, Wei Xiong, Tengyang Xie, Han Zhao, and Tong Zhang. 2024a. [Interpretable preferences via multi-objective reward modeling and mixture-of-experts](https://md.research.elamur.ai/free/en/papers/wang-2024-interpretable-preferences-multi-objective-reward/). In EMNLP.
75. Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, and Zhifang Sui. 2024b. Large language models are not fair evaluators. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers),… [find](https://scholar.google.com/scholar?q=Peiyi+Wang%2C+Lei+Li%2C+Liang+Chen%2C+Zefan+Cai%2C+Dawei+Zhu%2C+Binghuai+Lin%2C+Yunbo+Cao%2C+Lingpeng+Kong%2C+Qi+Liu%2C+Tianyu+Liu%2C+and+Zhifang+Sui%2E+2024b%2E+Large+language+models+are+not+fair+evaluators%2E+In+Proceedings+)
76. Yuxia Wang, Haonan Li, Xudong Han, Preslav Nakov, and Timothy Baldwin. 2023a. [Do-not-answer: A dataset for evaluating safeguards in llms](https://md.research.elamur.ai/free/en/papers/wang-2023-answer-dataset-evaluating-safeguards-llms/). Preprint, arXiv:2308.13387.
77. Zhilin Wang, Yi Dong, Jiaqi Zeng, Virginia Adams, Makesh Narsimhan Sreedhar, Daniel Egert, Olivier Delalleau, Jane Polak Scowcroft, Neel Kant, Aidan Swope, and Oleksii Kuchaiev. 2023b. [Helpsteer: Multi-attribute helpfulness dataset for steerlm](https://md.research.elamur.ai/free/en/papers/wang-2024-helpsteer-multi-attribute-helpfulness-dataset/). Preprint, arXiv:2311.09528.
78. Martin Weyssow, Aton Kamanda, Xin Zhou, and Houari Sahraoui. 2024. Codeultrafeedback: An llm-as-ajudge dataset for aligning large language models to coding preferences. Preprint, arXiv:2403.09032. — [arXiv:2403.09032](https://arxiv.org/abs/2403.09032) [find](https://scholar.google.com/scholar?q=Martin+Weyssow%2C+Aton+Kamanda%2C+Xin+Zhou%2C+and+Houari+Sahraoui%2E+2024%2E+Codeultrafeedback%3A+An+llm%2Das%2Dajudge+dataset+for+aligning+large+language+models+to+coding+preferences%2E+Preprint%2C+arXiv%3A2403%2E09032%2E+%E2%80%94+%5B)
79. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, and 3 others. 2020. [Transf…](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)
80. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, Chujie Zheng, Dayiheng Liu, Fan Zhou, Fei Huang, Feng Hu, Hao Ge, Haoran Wei, Huan Lin, Jialong Tang, and 41 others. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
81. Yue Yu, Zhengxing Chen, Aston Zhang, Liang Tan, Chenguang Zhu, Richard Yuanzhe Pang, Yundi Qian, Xuewei Wang, Suchin Gururangan, Chao Zhang, Melanie Kambadur, Dhruv Mahajan, and Rui Hou. 2025. Self-generated critiques boost reward modeling for language models. In Proceedings of the 2025 Conference o… [find](https://scholar.google.com/scholar?q=Yue+Yu%2C+Zhengxing+Chen%2C+Aston+Zhang%2C+Liang+Tan%2C+Chenguang+Zhu%2C+Richard+Yuanzhe+Pang%2C+Yundi+Qian%2C+Xuewei+Wang%2C+Suchin+Gururangan%2C+Chao+Zhang%2C+Melanie+Kambadur%2C+Dhruv+Mahajan%2C+and+Rui+Hou%2E+2025%2E+Self%2Dge)
82. Lining Zhang, Simon Mille, Yufang Hou, Daniel Deutsch, Elizabeth Clark, Yixin Liu, Saad Mahamood, Sebastian Gehrmann, Miruna Clinciu, Khyathi Raghavi Chandu, and João Sedoc. 2023. A needle in a haystack: An analysis of high-agreement workers on MTurk for summarization. In Proceedings of the 61st Ann… [find](https://scholar.google.com/scholar?q=Lining+Zhang%2C+Simon+Mille%2C+Yufang+Hou%2C+Daniel+Deutsch%2C+Elizabeth+Clark%2C+Yixin+Liu%2C+Saad+Mahamood%2C+Sebastian+Gehrmann%2C+Miruna+Clinciu%2C+Khyathi+Raghavi+Chandu%2C+and+Jo%C3%A3o+Sedoc%2E+2023%2E+A+needle+in+a+haysta)
83. Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. Bertscore: Evaluating text generation with bert. Preprint, arXiv:1904.09675. [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+2020%2E+Bertscore%3A+Evaluating+text+generation+with+bert%2E+Preprint%2C+arXiv%3A1904%2E09675%2E)
84. Xianbing Zhou, Yang Yong, Xiaochao Fan, Ge Ren, Yunfeng Song, Yufeng Diao, Liang Yang, and Hongfei Lin. 2021. Hate speech detection based on sentiment knowledge sharing. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer… [find](https://scholar.google.com/scholar?q=Xianbing+Zhou%2C+Yang+Yong%2C+Xiaochao+Fan%2C+Ge+Ren%2C+Yunfeng+Song%2C+Yufeng+Diao%2C+Liang+Yang%2C+and+Hongfei+Lin%2E+2021%2E+Hate+speech+detection+based+on+sentiment+knowledge+sharing%2E+In+Proceedings+of+the+59th+Ann)

*Updated 31 October 2026*