04:00
2026-05-28
arxiv.org
artificial-intelligence
Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning
Researchers have found that hallucinations in small language models (SLMs) can be useful for solving complex multi-step reasoning problems. A new study proposes a "answer first-reason later" frameworkβ¦