Publications of AlignAI sorted by recency
| Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets, , , , , , and , in: Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026 |
[URL] |
| Politics of Questions in News: A Mixed-Methods Study of Interrogative Stances as Markers of Voice and Power, , , and , in: Vol. 20 (2026): Proceedings of the Twentieth International AAAI Conference on Web and Social Media, 2026 |
|
| CarBoN: Calibrated Best-of-N Sampling Improves Test-time Reasoning, , and , in: arXiv, 2025 |
[URL] |