# Neurosymbolic AI approach to Attribution in Large Language Models

arXiv: https://arxiv.org/abs/2410.03726 · HTML: https://mlsanity.com/paper/2410.03726/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 30 Sep 2024.

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

- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://mlsanity.com/paper/2212.08037/) (2022)
- [ExpertQA: Expert-Curated Questions and Attributed Answers](https://mlsanity.com/paper/2309.07852/) (2023)
- [Reliable, Adaptable, and Attributable Language Models with Retrieval](https://mlsanity.com/paper/2403.03187/) (2024)
- [A Survey of Large Language Models Attribution](https://mlsanity.com/paper/2311.03731/) (2023)
- [Towards Verifiable Generation: A Benchmark for Knowledge-aware Language Model Attribution](https://mlsanity.com/paper/2310.05634/) (2023)
- [Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability, Explainability, and Safety](https://mlsanity.com/paper/2312.06798/) (2023)
- [Large Language Models are legal but they are not: Making the case for a powerful LegalLLM](https://mlsanity.com/paper/2311.08890/) (2023)
- [Thinking Fast and Slow in AI: the Role of Metacognition](https://mlsanity.com/paper/2110.01834/) (2021)
- [Abstention vs. Hallucination: Benchmarking LLM Source Attribution for Scientific Citations](https://mlsanity.com/paper/2405.02228/) (2024)
- [Grounding from an AI and Cognitive Science Lens](https://mlsanity.com/paper/2402.13290/) (2024)
- [Traceable LLM-based validation of statements in knowledge graphs](https://mlsanity.com/paper/2409.07507/) (2024)

## Built on by (most cited first, 3 of 3)

- [SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning](https://mlsanity.com/paper/2504.10369/) (2025)
- [Neurosymbolic Retrievers for Retrieval-augmented Generation](https://mlsanity.com/paper/2601.04568/) (2026)
- [SelfGraphRAG: Bridging the Supervision Gap in Graph-Based RAG with Synthetic QA Generation](https://mlsanity.com/paper/2608.25123/) (2026)

## Abstract (arXiv)

Attribution in large language models (LLMs) remains a significant challenge, particularly in ensuring the factual accuracy and reliability of the generated outputs. Current methods for citation or attribution, such as those employed by tools like Perplexity.ai and Bing Search-integrated LLMs, attempt to ground responses by providing real-time search results and citations. However, so far, these approaches suffer from issues such as hallucinations, biases, surface-level relevance matching, and the complexity of managing vast, unfiltered knowledge sources. While tools like Perplexity.ai dynamically integrate web-based information and citations, they often rely on inconsistent sources such as blog posts or unreliable sources, which limits their overall reliability. We present that these challenges can be mitigated by integrating Neurosymbolic AI (NesyAI), which combines the strengths of neural networks with structured symbolic reasoning. NesyAI offers transparent, interpretable, and dynamic reasoning processes, addressing the limitations of current attribution methods by incorporating structured symbolic knowledge with flexible, neural-based learning. This paper explores how NesyAI frameworks can enhance existing attribution models, offering more reliable, interpretable, and adaptable systems for LLMs.