Papers by Amit Sahai

2 papers
Measuring Psychological Depth in Language Models (2024.emnlp-main)

Copied to clipboard

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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations