Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

GPT-HateCheck: Can LLMs Write Better Functional Tests for Hate Speech Detection? (2402.15238v2)

Published 23 Feb 2024 in cs.CL and cs.CY

Abstract: Online hate detection suffers from biases incurred in data sampling, annotation, and model pre-training. Therefore, measuring the averaged performance over all examples in held-out test data is inadequate. Instead, we must identify specific model weaknesses and be informed when it is more likely to fail. A recent proposal in this direction is HateCheck, a suite for testing fine-grained model functionalities on synthesized data generated using templates of the kind "You are just a [slur] to me." However, despite enabling more detailed diagnostic insights, the HateCheck test cases are often generic and have simplistic sentence structures that do not match the real-world data. To address this limitation, we propose GPT-HateCheck, a framework to generate more diverse and realistic functional tests from scratch by instructing LLMs. We employ an additional natural language inference (NLI) model to verify the generations. Crowd-sourced annotation demonstrates that the generated test cases are of high quality. Using the new functional tests, we can uncover model weaknesses that would be overlooked using the original HateCheck dataset.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258.
  2. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  3. HateBERT: Retraining BERT for abusive language detection in English. In Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021), pages 17–25, Online. Association for Computational Linguistics.
  4. I feel offended, don’t be abusive! implicit/explicit messages in offensive and abusive language. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6193–6202, Marseille, France. European Language Resources Association.
  5. Measuring and mitigating unintended bias in text classification. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pages 67–73, New Orleans, LA, USA.
  6. Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin, 76(5):378.
  7. Directions for nlp practices applied to online hate speech detection. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, page 11794–11805, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  8. Janis Goldzycher and Gerold Schneider. 2022. Hypothesis engineering for zero-shot hate speech detection. In Proceedings of the Third Workshop on Threat, Aggression and Cyberbullying (TRAC 2022), pages 75–90, Gyeongju, Republic of Korea. Association for Computational Linguistics.
  9. ToxiGen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3309–3326, Dublin, Ireland. Association for Computational Linguistics.
  10. A challenge set approach to evaluating machine translation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2486–2496, Copenhagen, Denmark. Association for Computational Linguistics.
  11. Confronting abusive language online: A survey from the ethical and human rights perspective. Journal of Artificial Intelligence Research, 71:431–478.
  12. PERSONACHATGEN: Generating personalized dialogues using GPT-3. In Proceedings of the 1st Workshop on Customized Chat Grounding Persona and Knowledge, pages 29–48, Gyeongju, Republic of Korea. Association for Computational Linguistics.
  13. A holistic approach to undesired content detection in the real world. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 37, pages 15009–15018, Washington DC, USA.
  14. Rebecca Marvin and Tal Linzen. 2018. Targeted syntactic evaluation of language models. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1192–1202, Brussels, Belgium. Association for Computational Linguistics.
  15. Stress test evaluation for natural language inference. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2340–2353, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
  16. Playing the part of the sharp bully: Generating adversarial examples for implicit hate speech detection. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2758–2772, Toronto, Canada. Association for Computational Linguistics.
  17. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, volume 35, pages 27730–27744, New Orleans, Louisiana, USA.
  18. Red teaming language models with language models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3419–3448, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
  19. Resources and benchmark corpora for hate speech detection: a systematic review. Language Resources and Evaluation, 55(2):477–523.
  20. Beyond accuracy: Behavioral testing of NLP models with CheckList. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4902–4912, Online. Association for Computational Linguistics.
  21. HateCheck: Functional tests for hate speech detection models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 41–58, Online. Association for Computational Linguistics.
  22. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
  23. Extremebb: A database for large-scale research into online hate, harassment, the manosphere and extremism. Apollo - University of Cambridge Repository.
  24. Emergent abilities of large language models. Transactions on Machine Learning Research.
  25. Semantically conditioned LSTM-based natural language generation for spoken dialogue systems. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1711–1721, Lisbon, Portugal. Association for Computational Linguistics.
  26. Detection of Abusive Language: the Problem of Biased Datasets. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 602–608, Minneapolis, Minnesota. Association for Computational Linguistics.
  27. A broad-coverage challenge corpus for sentence understanding through inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1112–1122. Association for Computational Linguistics.
  28. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 38–45, Online. Association for Computational Linguistics.
  29. Wenjie Yin and Arkaitz Zubiaga. 2021. Towards generalisable hate speech detection: a review on obstacles and solutions. PeerJ Computer Science, 7:e598.
  30. Benchmarking zero-shot text classification: Datasets, evaluation and entailment approach. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3914–3923, Hong Kong, China. Association for Computational Linguistics.
  31. A survey of large language models. arXiv preprint arXiv:2303.18223.
  32. Texygen: A benchmarking platform for text generation models. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pages 1097–1100, Ann Arbor, Michigan, USA. Association for Computing Machinery.
  33. HateCheck: Functional Tests for Hate Speech Detection Models. University of Oxford. Association for Computational Linguistics.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Yiping Jin (9 papers)
  2. Leo Wanner (10 papers)
  3. Alexander Shvets (9 papers)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets