publications
2024
-
- Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit AccessACL, 2024
- A Glitch in the Matrix? Locating and Detecting Language Model Grounding with FakepediaACL, 2024
-
- Symbolic Autoencoding for Self-Supervised Sequence LearningICML 2024 Workshop "Differentiable Almost Everything", 2024
2023
- Generating Faithful Synthetic Data with Large Language Models: A Case Study in Computational Social SciencearXiv, 2023