cd /news/artificial-intelligence/can-hallucinations-be-useful-solving… · home topics artificial-intelligence article
[ARTICLE · art-16067] src=arxiv.org pub= topic=artificial-intelligence verified=true sentiment=↑ positive

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" framework that allows SLMs to quickly generate initial answers before retrieving evidence for deeper reasoning, outperforming traditional "think-first" approaches on multi-hop question-answering benchmarks.

read1 min publishedMay 28, 2026

arXiv:2605.27596v1 Announce Type: new Abstract: Recently, there has been increased interest in Small Language Models (SLMs), which are fast, show good performance, and have lower hardware demands than large language models (LLMs). However, SLMs hallucinate more frequently than LLMs, impacting their ability to solve complex multi-step reasoning problems as early mistakes cascade to the final response. To address this, existing works think-first followed by iterative retrieval to reduce hallucination. We argue that the think-first strategy is not always necessary as we find that: (i) SLMs are often accurately confident in their initial answer and, (ii) hallucinations can actually be beneficial for honing in on the true answer. As such, we position our work as an inversion of this strategy, i.e., answer first-reason later. We propose a cognitively-inspired framework where the model is first allowed to quickly answer the question (System-I (zero-shot)) and then resorts to deeper thinking (System-II) based on evidence retrieved from a knowledge source using the initial hypothesis. By combining System-I and System-II style thinking, we show that our method can outperform prior work that takes the traditional think-first route on various multi-step question-answering benchmarks.

── more in #artificial-intelligence 4 stories · sorted by recency
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/can-hallucinations-b…] indexed:0 read:1min 2026-05-28 ·