BibTeX records: Aengus Lynch

download as .bib file

@article{DBLP:journals/corr/abs-2502-17578,
  author       = {Rylan Schaeffer and
                  Joshua Kazdan and
                  John Hughes and
                  Jordan Juravsky and
                  Sara Price and
                  Aengus Lynch and
                  Erik Jones and
                  Robert Kirk and
                  Azalia Mirhoseini and
                  Sanmi Koyejo},
  title        = {How Do Large Language Monkeys Get Their Power (Laws)?},
  journal      = {CoRR},
  volume       = {abs/2502.17578},
  year         = {2025},
  url          = {https://doi.org/10.48550/arXiv.2502.17578},
  doi          = {10.48550/ARXIV.2502.17578},
  eprinttype    = {arXiv},
  eprint       = {2502.17578},
  timestamp    = {Fri, 21 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2502-17578.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/nips/TanCLPKGK24,
  author       = {Daniel Tan and
                  David Chanin and
                  Aengus Lynch and
                  Brooks Paige and
                  Dimitrios Kanoulas and
                  Adri{\`{a}} Garriga{-}Alonso and
                  Robert Kirk},
  editor       = {Amir Globersons and
                  Lester Mackey and
                  Danielle Belgrave and
                  Angela Fan and
                  Ulrich Paquet and
                  Jakub M. Tomczak and
                  Cheng Zhang},
  title        = {Analysing the Generalisation and Reliability of Steering Vectors},
  booktitle    = {Advances in Neural Information Processing Systems 38: Annual Conference
                  on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver,
                  BC, Canada, December 10 - 15, 2024},
  year         = {2024},
  url          = {http://papers.nips.cc/paper\_files/paper/2024/hash/fb3ad59a84799bfb8d700e56d19c231b-Abstract-Conference.html},
  timestamp    = {Thu, 13 Feb 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/TanCLPKGK24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2402-16835,
  author       = {Aengus Lynch and
                  Phillip Guo and
                  Aidan Ewart and
                  Stephen Casper and
                  Dylan Hadfield{-}Menell},
  title        = {Eight Methods to Evaluate Robust Unlearning in LLMs},
  journal      = {CoRR},
  volume       = {abs/2402.16835},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2402.16835},
  doi          = {10.48550/ARXIV.2402.16835},
  eprinttype    = {arXiv},
  eprint       = {2402.16835},
  timestamp    = {Mon, 25 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2402-16835.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2407-12404,
  author       = {Daniel Tan and
                  David Chanin and
                  Aengus Lynch and
                  Dimitrios Kanoulas and
                  Brooks Paige and
                  Adri{\`{a}} Garriga{-}Alonso and
                  Robert Kirk},
  title        = {Analyzing the Generalization and Reliability of Steering Vectors},
  journal      = {CoRR},
  volume       = {abs/2407.12404},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2407.12404},
  doi          = {10.48550/ARXIV.2407.12404},
  eprinttype    = {arXiv},
  eprint       = {2407.12404},
  timestamp    = {Mon, 03 Mar 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2407-12404.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2407-15549,
  author       = {Abhay Sheshadri and
                  Aidan Ewart and
                  Phillip Guo and
                  Aengus Lynch and
                  Cindy Wu and
                  Vivek Hebbar and
                  Henry Sleight and
                  Asa Cooper Stickland and
                  Ethan Perez and
                  Dylan Hadfield{-}Menell and
                  Stephen Casper},
  title        = {Targeted Latent Adversarial Training Improves Robustness to Persistent
                  Harmful Behaviors in LLMs},
  journal      = {CoRR},
  volume       = {abs/2407.15549},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2407.15549},
  doi          = {10.48550/ARXIV.2407.15549},
  eprinttype    = {arXiv},
  eprint       = {2407.15549},
  timestamp    = {Mon, 19 Aug 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2407-15549.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2412-03556,
  author       = {John Hughes and
                  Sara Price and
                  Aengus Lynch and
                  Rylan Schaeffer and
                  Fazl Barez and
                  Sanmi Koyejo and
                  Henry Sleight and
                  Erik Jones and
                  Ethan Perez and
                  Mrinank Sharma},
  title        = {Best-of-N Jailbreaking},
  journal      = {CoRR},
  volume       = {abs/2412.03556},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2412.03556},
  doi          = {10.48550/ARXIV.2412.03556},
  eprinttype    = {arXiv},
  eprint       = {2412.03556},
  timestamp    = {Mon, 13 Jan 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2412-03556.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@inproceedings{DBLP:conf/nips/ConmyMLHG23,
  author       = {Arthur Conmy and
                  Augustine N. Mavor{-}Parker and
                  Aengus Lynch and
                  Stefan Heimersheim and
                  Adri{\`{a}} Garriga{-}Alonso},
  editor       = {Alice Oh and
                  Tristan Naumann and
                  Amir Globerson and
                  Kate Saenko and
                  Moritz Hardt and
                  Sergey Levine},
  title        = {Towards Automated Circuit Discovery for Mechanistic Interpretability},
  booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference
                  on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans,
                  LA, USA, December 10 - 16, 2023},
  year         = {2023},
  url          = {http://papers.nips.cc/paper\_files/paper/2023/hash/34e1dbe95d34d7ebaf99b9bcaeb5b2be-Abstract-Conference.html},
  timestamp    = {Fri, 01 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/ConmyMLHG23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2303-05470,
  author       = {Aengus Lynch and
                  Gb{\`{e}}tondji J.{-}S. Dovonon and
                  Jean Kaddour and
                  Ricardo Silva},
  title        = {Spawrious: {A} Benchmark for Fine Control of Spurious Correlation
                  Biases},
  journal      = {CoRR},
  volume       = {abs/2303.05470},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2303.05470},
  doi          = {10.48550/ARXIV.2303.05470},
  eprinttype    = {arXiv},
  eprint       = {2303.05470},
  timestamp    = {Wed, 05 Feb 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2303-05470.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2304-14997,
  author       = {Arthur Conmy and
                  Augustine N. Mavor{-}Parker and
                  Aengus Lynch and
                  Stefan Heimersheim and
                  Adri{\`{a}} Garriga{-}Alonso},
  title        = {Towards Automated Circuit Discovery for Mechanistic Interpretability},
  journal      = {CoRR},
  volume       = {abs/2304.14997},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2304.14997},
  doi          = {10.48550/ARXIV.2304.14997},
  eprinttype    = {arXiv},
  eprint       = {2304.14997},
  timestamp    = {Thu, 04 May 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2304-14997.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/corr/abs-2206-15475,
  author       = {Jean Kaddour and
                  Aengus Lynch and
                  Qi Liu and
                  Matt J. Kusner and
                  Ricardo Silva},
  title        = {Causal Machine Learning: {A} Survey and Open Problems},
  journal      = {CoRR},
  volume       = {abs/2206.15475},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2206.15475},
  doi          = {10.48550/ARXIV.2206.15475},
  eprinttype    = {arXiv},
  eprint       = {2206.15475},
  timestamp    = {Wed, 05 Feb 2025 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2206-15475.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.