---
title: "JusticeBots@LT-EDI 2026 — paper by Pranesh et al. (2026)"
description: "The paper describes the JusticeBots entry to Task 2 of the LT-EDI @ ACL 2026 shared task, which… 10 references, cited by 1 paper here."
authors: ["TT Pranesh", "K.K.Thamizhmathi", "S Vigneshwaran", "Bharathi B"]
year: 2026
venue: "Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion"
source: "https://aclanthology.org/2026.ltedi-1.21/"
doi: "10.18653/v1/2026.ltedi-1.21"
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/pranesh-2026-justicebots-lt-edi-2026-prompt/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pranesh-2026-justicebots-lt-edi-2026-prompt/)

[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/14/) / JusticeBots@LT-EDI 2026: Prompt-Based Counter-Narrative Generation for Homophobia and Transphobia Comments

# JusticeBots@LT-EDI 2026: Prompt-Based Counter-Narrative Generation for Homophobia and Transphobia Comments

**Authors:** [TT Pranesh](https://md.research.elamur.ai/free/en/authors/tt-pranesh/), [K.K.Thamizhmathi](https://md.research.elamur.ai/free/en/authors/k-k-thamizhmathi/), [S Vigneshwaran](https://md.research.elamur.ai/free/en/authors/s-vigneshwaran/) and [Bharathi B](https://md.research.elamur.ai/free/en/authors/bharathi-b/) · **Year:** 2026 · **Venue:** [Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion](https://md.research.elamur.ai/free/en/venues/ltedi/) ([Workshop on Language Technology for Equality, Diversity, Inclusion 2026](https://md.research.elamur.ai/free/en/venues/ltedi/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.ltedi-1.21/) · [PDF](https://aclanthology.org/2026.ltedi-1.21.pdf) · [DOI 10.18653/v1/2026.ltedi-1.21](https://doi.org/10.18653/v1/2026.ltedi-1.21) · [OpenAlex](https://openalex.org/W7166884951)

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

## Summary
The paper describes the JusticeBots entry to Task 2 of the LT-EDI @ ACL 2026 shared task, which asks for counter-narratives to homophobic and transphobic social media comments in English and Tamil. The team did no training or fine-tuning. Instead, they wrote one structured zero-shot prompt asking for calm, concise, inclusive replies in the input's language, with no slurs or repeated hateful wording. The same prompt, left unchanged and run with each platform's default settings, was given to three models: GPT-4o, Gemini 1.5 Pro, and Llama-3 Sonar Large, the last accessed through Perplexity AI.

Outputs were scored with BERTScore-F1 and Distinct-2, plus rubric metrics judged by GPT-4o. Gemini 1.5 Pro scored best overall, and Llama-3 Sonar Large was close behind. The official submission ranked clearly lower, especially on Tamil lexical diversity and on English quality and coherence. The authors' discussion ties that weak Tamil diversity to GPT-4o, which suggests the official run came from that model.

The work shows that off-the-shelf LLMs can serve as low-cost counter-speech tools for a low-resource language like Tamil. The authors note two caveats: outputs can be generic, and an LLM judge may bias the evaluation.

## Key points
- **Data:** Tamil has 800 training and 109 test comments; English has 1,800 training and 66 test comments, each labeled homophobic or transphobic. The task also had a span-detection subtask, which the team skipped.
- **Metrics:** BERTScore-F1 and Distinct-2 (D-2), plus three rubric scores judged by GPT-4o: PRS (politeness and respectfulness), QS (quality) and CCNC (contextual coherence).
- **Best system, Gemini 1.5 Pro:**
  - Tamil: F1 95.15, D-2 91.51, PRS 97.08, QS 92.76, CCNC 93.65.
  - English: F1 87.27, PRS 96.12, QS 91.34, CCNC 92.48. Llama-3 had the higher English D-2 (89.57).
- **Official submission:**
  - Tamil: D-2 only 27.01.
  - English: PRS 76.52, QS 52.27, CCNC 57.58.
  - Its English F1 (87.63) was nonetheless marginally the highest.
- **Limitations:** responses can be generic and lack cultural grounding. GPT-4o served as both a generator and the judge. The authors recommend human evaluation and few-shot prompting as next steps.

*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

- [Sri Sivasubramaniya Nadar College of Engineering](https://md.research.elamur.ai/free/en/universities/sri-sivasubramaniya-nadar-college-of-engineering/) — University, Chennai, India · 10 works · 9 citations

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Safety Research](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · 626 works

## Cite

Cite as: TT Pranesh, K.K.Thamizhmathi, S Vigneshwaran and Bharathi B. 2026. JusticeBots@LT-EDI 2026: Prompt-Based Counter-Narrative Generation for Homophobia and Transphobia Comments. Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion.

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

```bibtex
@inproceedings{pranesh2026justicebots,
  title = {{JusticeBots@LT-EDI 2026: Prompt-Based Counter-Narrative Generation for Homophobia and Transphobia Comments}},
  author = {TT Pranesh, K.K.Thamizhmathi, S Vigneshwaran and Bharathi B},
  booktitle = {Proceedings of the Sixth Workshop on Language Technology for Equality, Diversity, Inclusion},
  year = {2026},
  doi = {10.18653/v1/2026.ltedi-1.21},
  url = {https://doi.org/10.18653/v1/2026.ltedi-1.21}
}
```

- [← previous JTTE at ATE-IT: A CRF Model with Contextual Embeddings](https://md.research.elamur.ai/free/en/papers/tonneau-2026-jtte-ate-it-crf-model/)
- [next → K-NLPers at SemEval-2026 Task 7: Multiple LLM Agent Debate System for Everyday Knowledge Across Diverse Languages and Cultures](https://md.research.elamur.ai/free/en/papers/song-2026-k-nlpers-semeval-2026-task/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/14/)

## References

10 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Tommaso Caselli, Valerio Basile, Jelena Mitrović, Inga Kartoziya, and Michael Granitzer. 2020. [I feel offended, don’t be abusive!](https://md.research.elamur.ai/free/en/papers/caselli-2020-i-feel-offended-don-t/) implicit/explicit messages in offensive and abusive language. In Proceedings of the twelfth language resources and evaluation conference, pages 6193–6202.
2. Bharathi Raja Chakravarthi. 2024. Detection of homophobia and transphobia in youtube comments. International Journal of Data Science and Analytics, 18(1):49–68. Yi-Ling Chung, Elizaveta Kuzmenko, Serra Sinem Tekiroğlu, and Marco Guerini. 2019. Conan-counter narratives through nichesourcing: a multi… [find](https://scholar.google.com/scholar?q=Bharathi+Raja+Chakravarthi%2E+2024%2E+Detection+of+homophobia+and+transphobia+in+youtube+comments%2E+International+Journal+of+Data+Science+and+Analytics%2C+18%281%29%3A49%E2%80%9368%2E+Yi%2DLing+Chung%2C+Elizaveta+Kuzmenko%2C+Serr)
3. Prasanna Kumar Kumaresan, Devendra Deepak Kayande, Ruba Priyadharshini, Paul Buitelaar, and Bharathi Raja Chakravarthi. 2025. Homophobia and transphobia span identification in low-resource languages. Natural Language Processing Journal, page 100169. [find](https://scholar.google.com/scholar?q=Prasanna+Kumar+Kumaresan%2C+Devendra+Deepak+Kayande%2C+Ruba+Priyadharshini%2C+Paul+Buitelaar%2C+and+Bharathi+Raja+Chakravarthi%2E+2025%2E+Homophobia+and+transphobia+span+identification+in+low%2Dresource+languages%2E+)
4. Prasanna Kumar Kumaresan, Praveen Prasannan, Tanay Singh, Ruba Priyadharshini, Subalalitha Chinnaudayar Navaneethakrishnan, Saranya Rajiakodi, Paul Buitelaar, and Bharathi Raja Chakravarthi. 2026. Findings of the Shared Task on Counter-Narrative Generation on Homophobic and Transphobic Comments. In… [find](https://scholar.google.com/scholar?q=Prasanna+Kumar+Kumaresan%2C+Praveen+Prasannan%2C+Tanay+Singh%2C+Ruba+Priyadharshini%2C+Subalalitha+Chinnaudayar+Navaneethakrishnan%2C+Saranya+Rajiakodi%2C+Paul+Buitelaar%2C+and+Bharathi+Raja+Chakravarthi%2E+2026%2E+Fin)
5. Binny Mathew, Punyajoy Saha, Hardik Tharad, Subham Rajgaria, Prajwal Singhania, Suman Kalyan Maity, Pawan Goyal, and Animesh Mukherjee. 2019. Thou shalt not hate: Countering online hate speech. In Proceedings of the international AAAI conference on web and social media, volume 13, pages 369–380. [find](https://scholar.google.com/scholar?q=Binny+Mathew%2C+Punyajoy+Saha%2C+Hardik+Tharad%2C+Subham+Rajgaria%2C+Prajwal+Singhania%2C+Suman+Kalyan+Maity%2C+Pawan+Goyal%2C+and+Animesh+Mukherjee%2E+2019%2E+Thou+shalt+not+hate%3A+Countering+online+hate+speech%2E+In+Pro)
6. Praveen Prasannan, Prasanna Kumar Kumaresan, Saranya Rajiakodi, CN Subalalitha, and Bharathi Raja Chakravarthi. 2025. Counter-speech generation for homophobic and transphobic social media content in malayalam. Social Network Analysis and Mining, 15(1):87. [find](https://scholar.google.com/scholar?q=Praveen+Prasannan%2C+Prasanna+Kumar+Kumaresan%2C+Saranya+Rajiakodi%2C+CN+Subalalitha%2C+and+Bharathi+Raja+Chakravarthi%2E+2025%2E+Counter%2Dspeech+generation+for+homophobic+and+transphobic+social+media+content+in+m)
7. Jing Qian, Anna Bethke, Yinyin Liu, Elizabeth Belding, and William Yang Wang. 2019. [A benchmark dataset for learning to intervene in online hate speech](https://md.research.elamur.ai/free/en/papers/qian-2019-benchmark-dataset-learning-intervene-online/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lan…
8. Carla Schieb and Mike Preuss. 2016. Governing hate speech by means of counterspeech on facebook. In 66th ica annual conference, at fukuoka, japan, pages 1–23. [find](https://scholar.google.com/scholar?q=Carla+Schieb+and+Mike+Preuss%2E+2016%2E+Governing+hate+speech+by+means+of+counterspeech+on+facebook%2E+In+66th+ica+annual+conference%2C+at+fukuoka%2C+japan%2C+pages+1%E2%80%9323%2E)
9. Serra Sinem Tekiroğlu, Yi-Ling Chung, and Marco Guerini. 2020. [Generating counter narratives against online hate speech: Data and strategies](https://md.research.elamur.ai/free/en/papers/tekiroglu-2020-generating-counter-narratives-against-online/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1177–1190.
10. Bertie Vidgen, Tristan Thrush, Zeerak Talat, and Douwe Kiela. 2021. [Learning from the worst: Dynamically generated datasets to improve online hate detection](https://md.research.elamur.ai/free/en/papers/vidgen-2021-learning-worst-dynamically-generated-datasets/). In Proceedings of the 59th annual meeting of the Association for Computational Linguistics and the 11th international joint conference on natu…

*Updated 1 November 2026*