Search papers, labs, and topics across Lattice.
Affiliation:, Pune Institute of Computer Technology
2
0
4
3
Unlearning in LLMs is not just about forgetting facts; it鈥檚 about mastering the nuanced balance of harmful and benign concept usage, and current methods fall short.
Post-solution confidence estimates can dramatically enhance pre-solution predictions, enabling more reliable decision-making in confidence-aware systems.
