We have 3 of 7 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Liminal training is introduced, an annealed KL-regularized fine-tuning method that constrains early drift from the base model and shows that KL timing matters: early regularization is more effective than late regularization, and sweeping the regularization strength reveals an empirical trade-off between task learning a...
The results show that sycophancy can corrupt the reasoning chain independently of the final answer, so answer-level evaluation alone is insufficient, and a failure taxonomy separating reasoning-chain from answer-level sycophancy is introduced, and a complementary sentence-level taxonomy locating where in the chain drif...
This work investigates memorization in transformer-based language models by analyzing their memorization dynamics during training over multiple epochs and finds that memorization is neither a constant accumulation of sequences nor simply dictated by the recency of exposure to these sequences.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
