Amit Sahai — accepted AI-conference papers

2025

Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking

Fabrice Y Harel-Canada, Boran Erol, Connor Choi, Jason Liu, Gary Jiarui Song, Nanyun Peng +1

ACL 2025long

Watermarking AI-generated text is critical for combating misuse. Yet recent theoretical work argues that any watermark can be erased via random walk attacks that perturb text while preserving quality. However, such attacks rely on two key assumptions: (1) rapid mixing (watermarks dissolve quickly un…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Measuring Psychological Depth in Language Models

Fabrice Y Harel-Canada, Hanyu Zhou, Sreya Muppalla, Zeynep Senahan Yildiz, Miryung Kim, Amit Sahai +1

EMNLP 2024main

Evaluations of creative stories generated by large language models (LLMs) often focus on objective properties of the text, such as its style, coherence, and diversity. While these metrics are indispensable, they do not speak to a story’s subjective, psychological impact from a reader’s perspective.…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗