activity
20242026
most citedUNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models

1 citations · 1 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probing

Parsa Mirtaheri, Mikhail Belkin

Large language models (LLMs) can produce chains of thought (CoT) that do not accurately reflect the actual factors driving their answers. In multiple-choice settings with an inject…

cs.LG2025

Task Generalization With AutoRegressive Compositional Structure: Can Learning From Tasks Generalize to Tasks?

Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen +3

Large language models (LLMs) exhibit remarkable task generalization, solving tasks they were never explicitly trained on with only a few demonstrations. This raises a fundamental q…