How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries

📢 Accepted at AAAI Conference on Web and Social Media, ICWSM 2025

We are updating our repository. Read our paper from Arxiv.

The dataset TechHazardQA can be found at Huggingface.

If you are using this dataset, please cite our paper

@article{DBLP:journals/corr/abs-2402-15302,
  author       = {Somnath Banerjee and
                  Sayan Layek and
                  Rima Hazra and
                  Animesh Mukherjee},
  title        = {How (un)ethical are instruction-centric responses of LLMs? Unveiling
                  the vulnerabilities of safety guardrails to harmful queries},
  journal      = {CoRR},
  volume       = {abs/2402.15302},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.15302},
  doi          = {10.48550/ARXIV.2402.15302},
  eprinttype    = {arXiv},
  eprint       = {2402.15302},
  timestamp    = {Fri, 22 Mar 2024 12:19:03 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-15302.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}