Skip to content

Commit 3841834

Browse files
romanlutzCopilot
andauthored
DOC: Correct four citations in references.bib to published venues (#2119)
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
1 parent c9b3010 commit 3841834

1 file changed

Lines changed: 17 additions & 11 deletions

File tree

doc/references.bib

Lines changed: 17 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -99,9 +99,12 @@ @misc{odin2024
9999
@article{inie2025summon,
100100
title = {Summon a Demon and Bind it: A Grounded Theory of {LLM} Red Teaming},
101101
author = {Nanna Inie and Jonathan Stray and Leon Derczynski},
102-
journal = {PLoS ONE},
102+
journal = {PLOS ONE},
103+
volume = {20},
104+
number = {1},
105+
pages = {e0314658},
103106
year = {2025},
104-
url = {https://arxiv.org/abs/2311.06237},
107+
url = {https://doi.org/10.1371/journal.pone.0314658},
105108
}
106109

107110
@misc{vantaylor2024socialbias,
@@ -633,17 +636,19 @@ @article{rottger2025msts
633636
url = {https://arxiv.org/abs/2501.10057},
634637
}
635638

636-
@article{zong2024vlguard,
639+
@inproceedings{zong2024vlguard,
637640
title = {Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models},
638641
author = {Yongshuo Zong and Ondrej Bohdal and Tingyang Yu and Yongxin Yang and Timothy Hospedales},
639-
journal = {arXiv preprint arXiv:2402.02207},
642+
booktitle = {Proceedings of the 41st International Conference on Machine Learning (ICML)},
643+
pages = {62867--62891},
640644
year = {2024},
641-
url = {https://arxiv.org/abs/2402.02207},
645+
publisher = {PMLR},
646+
url = {https://proceedings.mlr.press/v235/zong24a.html},
642647
}
643648

644649
@article{lopez2024pyrit,
645650
title = {{PyRIT}: A Framework for Security Risk Identification and Red Teaming in Generative {AI} Systems},
646-
author = {Gary D. Lopez Munoz and Amanda J. Minnich and Roman Lutz and Richard Lundeen and Raja Sekhar Rao Dheekonda and Nina Chikanov and Bolor-Erdene Jagdagdorj and Martin Pouliot and Shiven Chawla and Whitney Maxwell and Blake Bullwinkel and Katherine Pratt and Joris de Gruyter and Charlotte Siska and Pete Bryan and Tori Westerhoff and Chang Kawaguchi and Christian Seifert and Ram Shankar Siva Kumar and Yonatan Zunger},
651+
author = {Gary D. {Lopez Munoz} and Amanda J. Minnich and Roman Lutz and Richard Lundeen and Raja Sekhar Rao Dheekonda and Nina Chikanov and Bolor-Erdene Jagdagdorj and Martin Pouliot and Shiven Chawla and Whitney Maxwell and Blake Bullwinkel and Katherine Pratt and Joris de Gruyter and Charlotte Siska and Pete Bryan and Tori Westerhoff and Chang Kawaguchi and Christian Seifert and Ram Shankar Siva Kumar and Yonatan Zunger},
647652
journal = {arXiv preprint arXiv:2410.02828},
648653
year = {2024},
649654
url = {https://arxiv.org/abs/2410.02828},
@@ -667,12 +672,13 @@ @inproceedings{wang2025siuo
667672
note = {Introduces the {SIUO} (Safe Inputs but Unsafe Output) benchmark},
668673
}
669674

670-
@misc{darkbench2025,
671-
title = {{DarkBench}: A Comprehensive Benchmark for Dark Design Patterns in Large Language Models},
672-
author = {{Apart Research}},
675+
@inproceedings{darkbench2025,
676+
title = {{DarkBench}: Benchmarking Dark Patterns in Large Language Models},
677+
author = {Esben Kran and Hieu Minh Nguyen and Akash Kundu and Sami Jawhar and Jinsuk Park and Mateusz Maria Jurewicz},
678+
booktitle = {International Conference on Learning Representations (ICLR)},
673679
year = {2025},
674-
url = {https://darkbench.ai/},
675-
note = {OpenReview: https://openreview.net/forum?id=odjMSBSWRt},
680+
url = {https://arxiv.org/abs/2503.10728},
681+
note = {Oral presentation at ICLR 2025},
676682
}
677683

678684
@misc{embracethered2025sneakybits,

0 commit comments

Comments
 (0)