Search papers, labs, and topics across Lattice.
IIIT Delhi, India
2
0
5
1
Scaling up LLMs doesn't uniformly improve context handling; instead, it paradoxically amplifies the tendency to copy irrelevant tokens while simultaneously improving resistance to misinformation.
Forget hand-crafted rules: MAC learns interpretable LLM constitutions that beat prompt optimization by 50% and rival fine-tuning, all without parameter updates.
