Robust Long-Context Multilingual Retrieval and Reasoning Enabled by Combined Neural and Symbolic Techniques
Neurosymbolic Artificial Intelligence · 2026-04 · 2
DOI: 10.1177/29498732261443192 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurosymbolic Artificial Intelligence, online erschienen am 16.04.2026. Verfasst von Sina Bagheri Nezhad und 1 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Large language models (LLMs) are increasingly deployed for multilingual information retrieval and reasoning over very long documents, yet they often struggle with extracting dispersed facts and synthesizing robust answers across linguistic boundaries. In this work, we propose a hybrid neural-symbolic framework that integrates scalable cross-lingual retrieval with explicit symbolic reasoning. Our approach, CROSS (Cross-lingual Retrieval Optimized for Scalable Solutions), efficiently narrows massive multilingual contexts using multilingual embeddings, dramatically improving retrieval accuracy and mitigating the “lost-in-the-middle” problem. Building on this, we introduce NeuroSymbolic Augmented Reasoning (NSAR) , which prompts LLMs to extract structured facts and generate executable Python code, enabling deterministic and interpretable multitarget reasoning. We evaluate our methods on the mLongRR-V2 benchmark, spanning seven languages, 49 cross-lingual pairs, and documents up to 512,000 words. Our experiments show that compared to neural-only baselines, CROSS boosts a retrieval accuracy of up to 92% and NSAR reduces reasoning failures fivefold, while maintaining stable performance across languages and context sizes. These results establish a new standard for robust, scalable, and interpretable multilingual information extraction, demonstrating the promise of hybrid neural-symbolic architectures for future artificial intelligence systems.
Zitieren
APA
Nezhad, S. B., & Agrawal, A. (2026). Robust Long-Context Multilingual Retrieval and Reasoning Enabled by Combined Neural and Symbolic Techniques. Neurosymbolic Artificial Intelligence, 2. https://doi.org/10.1177/29498732261443192
Vancouver
Nezhad SB, Agrawal A. Robust Long-Context Multilingual Retrieval and Reasoning Enabled by Combined Neural and Symbolic Techniques. Neurosymbolic Artificial Intelligence. 2026;2. doi:10.1177/29498732261443192
BibTeX
@article{Nezhad2026,
author = {Nezhad, Sina Bagheri and Agrawal, Ameeta},
title = {Robust Long-Context Multilingual Retrieval and Reasoning Enabled by Combined Neural and Symbolic Techniques},
journal = {Neurosymbolic Artificial Intelligence},
year = {2026},
volume = {2},
doi = {10.1177/29498732261443192}
}
EUVIMED