# LLM-Augmented Symbolic NLU System for More Reliable Continuous Causal Statement Interpretation

arXiv: https://arxiv.org/abs/2510.19988 · HTML: https://mlsanity.com/paper/2510.19988/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 22 Oct 2025.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence](https://mlsanity.com/paper/2002.06177/) (2020)
- [QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions](https://mlsanity.com/paper/1909.03553/) (2019)
- [A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners](https://mlsanity.com/paper/2406.11050/) (2024)
- [QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships](https://mlsanity.com/paper/1811.08048/) (2018)
- [Neuron-Level Knowledge Attribution in Large Language Models](https://mlsanity.com/paper/2312.12141/) (2023)
- [Apple Intelligence Foundation Language Models: Tech Report 2025](https://mlsanity.com/paper/2507.13575/) (2025)
- [Limits for Learning with Language Models](https://mlsanity.com/paper/2306.12213/) (2023)
- [Improving Language Model Prompting in Support of Semi-autonomous Task Learning](https://mlsanity.com/paper/2209.07636/) (2022)
- [Eliciting Problem Specifications via Large Language Models](https://mlsanity.com/paper/2405.12147/) (2024)

## Abstract (arXiv)

Despite the broad applicability of large language models (LLMs), their reliance on probabilistic inference makes them vulnerable to errors such as hallucination in generated facts and inconsistent output structure in natural language understanding (NLU) tasks. By contrast, symbolic NLU systems provide interpretable understanding grounded in curated lexicons, semantic resources, and syntactic & semantic interpretation rules. They produce relational representations that can be used for accurate reasoning and planning, as well as incremental debuggable learning. However, symbolic NLU systems tend to be more limited in coverage than LLMs and require scarce knowledge representation and linguistics skills to extend and maintain. This paper explores a hybrid approach that integrates the broad-coverage language processing of LLMs with the symbolic NLU capabilities of producing structured relational representations to hopefully get the best of both approaches. We use LLMs for rephrasing and text simplification, to provide broad coverage, and as a source of information to fill in knowledge gaps more automatically. We use symbolic NLU to produce representations that can be used for reasoning and for incremental learning. We evaluate this approach on the task of extracting and interpreting quantities and causal laws from commonsense science texts, along with symbolic- and LLM-only pipelines. Our results suggest that our hybrid method works significantly better than the symbolic-only pipeline.