arXiv cs.LG
· Papers
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation
arXiv:2608.06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements. When one call must return many verdicts, some decisions become weakly grounded in the evidence, even when that call receives the same token or tool budget as a panel of separate calls.