JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models NAACL

Jillian Fisher | Ximing Lu | Jaehun Jung | Liwei Jiang | Zaid Harchaoui | Yejin Choi |

Impossible Distillation for Paraphrasing and Summarization: How to Make High-quality Lemonade out of Small, Low-quality Model NAACL

Jaehun Jung | Peter West | Liwei Jiang | Faeze Brahman | Ximing Lu | Jillian Fisher | Taylor Sorensen | Yejin Choi |

Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration EMNLP

Shangbin Feng | Taylor Sorensen | Yuhan Liu | Jillian Fisher | Chan Young Park | Yejin Choi | Yulia Tsvetkov |

StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements EMNLP

Jillian Fisher | Skyler Hallinan | Ximing Lu | Mitchell L Gordon | Zaid Harchaoui | Yejin Choi |

Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning EMNLP

Ximing Lu | Faeze Brahman | Peter West | Jaehun Jung | Khyathi Chandu | Abhilasha Ravichander | Prithviraj Ammanabrolu | Liwei Jiang | Sahana Ramnath | Nouha Dziri | Jillian Fisher | Bill Lin | Skyler Hallinan | Lianhui Qin | Xiang Ren | Sean Welleck | Yejin Choi |