MIRAGE: A Framework for Multi-hop Reasoning under Dynamic Knowledge Injection

Multi-hop Question Answering (MQA) requires large language models (LLMs) to retrieve and synthesize multiple pieces of evidence into a coherent reasoning path, which is essential for complex tasks. However, prior work on knowledge updating for MQA has largely focused on simple fact edits, overlooking a more challenging and realistic setting---\emph{Knowledge Injection}---in which the model must simultaneously accommodate both conflicting updates and entirely novel information. Under this setting, a hop-level answer is often wrong simply because the model trusts the wrong knowledge source: it clings to outdated parametric memory when the injected knowledge conflicts with it (K2), and it cannot answer when the required fact is entirely new (K3). To investigate this, we introduce NEXUS, the first benchmark tailored for multi-hop reasoning under Knowledge Injection, which explicitly covers both conflicting (K2) and incremental (K3) knowledge. We further propose MIRAGE, an efficient, training-free framework whose core component, the Correlation-aware Dual-path Reasoner (CDR), resolves such per-hop source-trust errors via P(True)-based confidence routing, complemented by a lightweight template-guided corrector for residual structural deviations. Extensive experiments across four LLM families and two benchmarks demonstrate that MIRAGE consistently improves both final-answer accuracy and hop-level reasoning accuracy, establishing a new state of the art in this challenging setting.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.24058
Primary Topic
Topic Modeling
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

MIRAGE: A Framework for Multi-hop Reasoning under Dynamic Knowledge Injection

Hanwen Hao, Heyang Xu, Haifeng Wang, Haoyi Zhou et al.
arXiv (Cornell University)
Topic Modeling
preprint

MIRAGE: A Framework for Multi-hop Reasoning under Dynamic Knowledge Injection

Hanwen Hao, Heyang Xu, Haifeng Wang, Haoyi Zhou, Jianxin Li
preprint en

Abstract

Multi-hop Question Answering (MQA) requires large language models (LLMs) to retrieve and synthesize multiple pieces of evidence into a coherent reasoning path, which is essential for complex tasks. However, prior work on knowledge updating for MQA has largely focused on simple fact edits, overlooking a more challenging and realistic setting---\emph{Knowledge Injection}---in which the model must simultaneously accommodate both conflicting updates and entirely novel information. Under this setting, a hop-level answer is often wrong simply because the model trusts the wrong knowledge source: it clings to outdated parametric memory when the injected knowledge conflicts with it (K2), and it cannot answer when the required fact is entirely new (K3). To investigate this, we introduce NEXUS, the first benchmark tailored for multi-hop reasoning under Knowledge Injection, which explicitly covers both conflicting (K2) and incremental (K3) knowledge. We further propose MIRAGE, an efficient, training-free framework whose core component, the Correlation-aware Dual-path Reasoner (CDR), resolves such per-hop source-trust errors via P(True)-based confidence routing, complemented by a lightweight template-guided corrector for residual structural deviations. Extensive experiments across four LLM families and two benchmarks demonstrate that MIRAGE consistently improves both final-answer accuracy and hop-level reasoning accuracy, establishing a new state of the art in this challenging setting.

arXiv (Cornell University)
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon