# Intermediate Languages Matter: Formal Languages and LLMs affect Neurosymbolic Reasoning

arXiv: https://arxiv.org/abs/2509.04083 · HTML: https://mlsanity.com/paper/2509.04083/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 4 Sep 2025.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought](https://mlsanity.com/paper/2210.01240/) (2022)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Neurosymbolic AI: The 3rd Wave](https://mlsanity.com/paper/2012.05876/) (2020)
- [FOLIO: Natural Language Reasoning with First-Order Logic](https://mlsanity.com/paper/2209.00840/) (2022)
- [Logic Tensor Networks](https://mlsanity.com/paper/2012.13635/) (2020)
- [Talking About Large Language Models](https://mlsanity.com/paper/2212.03551/) (2022)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [Injecting Numerical Reasoning Skills into Language Models](https://mlsanity.com/paper/2004.04487/) (2020)
- [Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models](https://mlsanity.com/paper/2005.00683/) (2020)
- [Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models](https://mlsanity.com/paper/2308.10379/) (2023)
- [LOGIC-LM++: Multi-Step Refinement for Symbolic Formulations](https://mlsanity.com/paper/2407.02514/) (2024)
- [LLASP: Fine-tuning Large Language Models for Answer Set Programming](https://mlsanity.com/paper/2407.18723/) (2024)
- [On the Foundations of Grounding in Answer Set Programming](https://mlsanity.com/paper/2108.04769/) (2021)
- [How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering](https://mlsanity.com/paper/2401.05777/) (2024)
- [Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language](https://mlsanity.com/paper/2505.16114/) (2025)
- [Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning](https://mlsanity.com/paper/2502.17216/) (2025)
- [Can Large Language Models put 2 and 2 together? Probing for Entailed Arithmetical Relationships](https://mlsanity.com/paper/2404.19432/) (2024)

## Abstract (arXiv)

Large language models (LLMs) achieve astonishing results on a wide range of tasks. However, their formal reasoning ability still lags behind. A promising approach is Neurosymbolic LLM reasoning. It works by using LLMs as translators from natural to formal languages and symbolic solvers for deriving correct results. Still, the contributing factors to the success of Neurosymbolic LLM reasoning remain unclear. This paper demonstrates that one previously overlooked factor is the choice of the formal language. We introduce the intermediate language challenge: selecting a suitable formal language for neurosymbolic reasoning. By comparing four formal languages across three datasets and seven LLMs, we show that the choice of formal language affects both syntactic and semantic reasoning capabilities. We also discuss the varying effects across different LLMs.