# Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks

arXiv: https://arxiv.org/abs/2506.02483 · HTML: https://mlsanity.com/paper/2506.02483/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 13 of 13)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Self-Reflection in LLM Agents: Effects on Problem-Solving Performance](https://mlsanity.com/paper/2405.06682/) (2024)
- [DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering](https://mlsanity.com/paper/2406.07348/) (2024)
- [Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustness](https://mlsanity.com/paper/2410.01171/) (2024)
- [Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models](https://mlsanity.com/paper/2408.10151/) (2024)
- [Evaluating Multilingual Long-Context Models for Retrieval and Reasoning](https://mlsanity.com/paper/2409.18006/) (2024)
- [XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples](https://mlsanity.com/paper/2405.05116/) (2024)

## Built on by (most cited first, 4 of 4)

- [MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanation](https://mlsanity.com/paper/2506.19073/) (2025)
- [VERAFI: Verified Agentic Financial Intelligence through Neurosymbolic Policy Generation](https://mlsanity.com/paper/2512.14744/) (2025)
- [The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus](https://mlsanity.com/paper/2603.20105/) (2026)
- [Signals Are Not States: Neuro-Symbolic Safeguards for Culturally Aware Classroom AI](https://mlsanity.com/paper/2603.22793/) (2026)

## Abstract (arXiv)

Large language models (LLMs) often struggle to perform multi-target reasoning in long-context scenarios where relevant information is scattered across extensive documents. To address this challenge, we introduce NeuroSymbolic Augmented Reasoning (NSAR), which combines the benefits of neural and symbolic reasoning during inference. NSAR explicitly extracts symbolic facts from text and generates executable Python code to handle complex reasoning steps. Through extensive experiments across seven languages and diverse context lengths, we demonstrate that NSAR significantly outperforms both a vanilla RAG baseline and advanced prompting strategies in accurately identifying and synthesizing multiple pieces of information. Our results highlight the effectiveness of combining explicit symbolic operations with neural inference for robust, interpretable, and scalable reasoning in multilingual settings.