LexAgentHallu is introduced as a hierarchical benchmark for profiling hallucinations in legal agents. The benchmark cont...

LexAgentHallu is introduced as a hierarchical benchmark for profiling hallucinations in legal agents. The benchmark contains 3414 instances across 17 legal categories and 6 task types.Source: arXiv cs.AIhttps://arxiv.org/abs/2609.09754#MachineLearning

Read Original

Related