collaborators

33 papers

cs.CL2024

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

Jillian Fisher, Skyler Hallinan, Ximing Lu +3

Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task. Current methods using large language models (LLM…

cs.CL2024

Symbolic Working Memory Enhances Language Models for Complex Rule Application

Siyuan Wang, Zhongyu Wei, Yejin Choi +1

Large Language Models (LLMs) have shown remarkable reasoning performance but struggle with multi-step deductive reasoning involving a series of rule application steps, especially w…

cs.LG20243 cited

Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement

Jaehun Jung, Faeze Brahman, Yejin Choi

We present a principled approach to provide LLM-based evaluation with a rigorous guarantee of human agreement. We first propose that a reliable evaluation method should not uncriti…

cs.CL20244 cited

Trust No Bot: Discovering Personal Disclosures in Human-LLM Conversations in the Wild

Niloofar Mireshghallah, Maria Antoniak, Yash More +2

Measuring personal disclosures made in human-chatbot interactions can provide a better understanding of users' AI literacy and facilitate privacy research for large language models…

cs.AI20242 cited

Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness

Khyathi Raghavi Chandu, Linjie Li, Anas Awadalla +5

The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present…

cs.CL2024

CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation

Tong Chen, Akari Asai, Niloofar Mireshghallah +6

Evaluating the degree of reproduction of copyright-protected content by language models (LMs) is of significant interest to the AI and legal communities. Although both literal and…