# Can Hallucinations Be Useful? Solving Multi-Hop Questions With SLMs By Chaining System-I/II Reasoning

arXiv: https://arxiv.org/abs/2605.27596 · HTML: https://mlsanity.com/paper/2605.27596/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 15 of its 64 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)

## Builds on (most cited first, 15 of 15)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?](https://mlsanity.com/paper/2503.24235/) (2025)
- [Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning](https://mlsanity.com/paper/2507.21892/) (2025)
- [Guiding Reasoning in Small Language Models with LLM Assistance](https://mlsanity.com/paper/2504.09923/) (2025)
- [Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering](https://mlsanity.com/paper/2601.11255/) (2026)
- [Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet](https://mlsanity.com/paper/2509.06861/) (2025)
- [Small Language Models for Application Interactions: A Case Study](https://mlsanity.com/paper/2405.20347/) (2024)
- [Finding What Matters: Anchoring Context Knowledge with Evolving Indices for Iterative Retrieval](https://mlsanity.com/paper/2601.16462/) (2026)
- [SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches](https://mlsanity.com/paper/2601.09402/) (2026)
- [D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2601.08282/) (2026)

## Abstract (arXiv)

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.