Papers by Amit Sahai
Measuring Psychological Depth in Language Models (2024.emnlp-main)
Copied to clipboard
Fabrice Harel-Canada, Hanyu Zhou, Sreya Muppalla, Zeynep Yildiz, Miryung Kim, Amit Sahai, Nanyun Peng
| Challenge: | Current evaluations of creative stories focus on objective properties of the text, such as its style, coherence, diversity, and creativity. |
| Approach: | They propose a framework that measures an LLM's ability to produce authentic and narratively complex stories that provoke emotion, empathy, and engagement. |
| Outcome: | The proposed framework shows that humans can consistently evaluate stories based on the PDS (0.72 Krippendorff’s alpha). |
Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking (2025.acl-long)
Copied to clipboard
Fabrice Y Harel-Canada, Boran Erol, Connor Choi, Jason Liu, Gary Jiarui Song, Nanyun Peng, Amit Sahai
| Challenge: | Recent theoretical work argues that any watermark can be erased via random walk attacks that perturb text while preserving quality. |
| Approach: | They propose that any watermark can be erased via random walk attacks that perturb text while preserving quality. |
| Outcome: | The proposed method underperforms the theoretical models in large-scale experiments and human-validated assessments. |