Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning

• URL: http://arxiv.org/abs/2502.17216v2
• Date: Wed, 21 May 2025 15:51:37 GMT
• Title: Intermediate Languages Matter: Formal Choice Drives Neurosymbolic LLM Reasoning
• Authors: Alexander Beiser, David Penz, Nysret Musliu,
• Abstract summary: We show that the choice of formal language affects both the syntactic and the semantic reasoning capability.<n>We conclude that on average, context-aware encodings help LLMs to reason, while there is no apparent effect of using comments or markdown syntax.
• Score: 50.99811144731619
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, it remains unclear what the contributing factors to the success of Neurosymbolic LLM reasoning are. This paper shows that one important factor is the choice of the formal language. By comparing 4 formal languages on 3 datasets over 6 LLMs, we show that the choice of formal language affects both the syntactic and the semantic reasoning capability. Thereby, we introduce the intermediate language challenge, which is the challenge of picking a suitable formal language for neurosymbolic reasoning. Further, we compare the effects of using different in-context-learning examples in an ablation study. We conclude that on average, context-aware encodings help LLMs to reason, while there is no apparent effect of using comments or markdown syntax.

Related papers

• Do Large Language Models Excel in Complex Logical Reasoning with Formal Language? [20.53475791645822]
  Large Language Models (LLMs) have been shown to achieve breakthrough performance on complex logical reasoning tasks.<n>This paper aims to conduct a comprehensive evaluation of LLMs across various logical reasoning problems utilizing formal languages.
  arXiv  Detail & Related papers  (2025-05-22T17:57:23Z)
• Memorization or Reasoning? Exploring the Idiom Understanding of LLMs [6.046971695786252]
  MIDAS is a large-scale dataset of idioms in six languages, each paired with its corresponding meaning.<n>Our findings suggest that LLMs rely not only on memorization, but also adopt a hybrid approach that integrates contextual cues and reasoning.<n>This implies that idiom understanding in LLMs emerges from an interplay between internal knowledge retrieval and reasoning-based inference.
  arXiv  Detail & Related papers  (2025-05-22T04:31:25Z)
• On the Thinking-Language Modeling Gap in Large Language Models [68.83670974539108]
  We show that there is a significant gap between the modeling of languages and thoughts.<n>We propose a new prompt technique termed Language-of-Thoughts (LoT) to demonstrate and alleviate this gap.
  arXiv  Detail & Related papers  (2025-05-19T09:31:52Z)
• The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units [16.317199232071232]
  Large language models (LLMs) exhibit remarkable capabilities on not just language tasks, but also various tasks that are not linguistic in nature.<n>In the human brain, neuroscience has identified a core language system that selectively and causally supports language processing.<n>We identify language-selective units within 18 popular LLMs, using the same localization approach that is used in neuroscience.
  arXiv  Detail & Related papers  (2024-11-04T17:09:10Z)
• Reliable Reasoning Beyond Natural Language [0.047888359248129786]
  Large Language models (LLMs) often exhibit limitations in their ability to reason reliably and flexibly. We propose a neurosymbolic approach that prompts LLMs to extract and encode all relevant information from a problem statement as logical code statements. We then use a logic programming language (Prolog) to conduct the iterative computations of explicit deductive reasoning.
  arXiv  Detail & Related papers  (2024-07-16T04:34:18Z)
• LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models [52.03659714625452]
  Recently developed large language models (LLMs) have been shown to perform remarkably well on a wide range of language understanding tasks. But, can they really "reason" over the natural language? This question has been receiving significant research attention and many reasoning skills such as commonsense, numerical, and qualitative have been studied.
  arXiv  Detail & Related papers  (2024-04-23T21:08:49Z)
• How Proficient Are Large Language Models in Formal Languages? An In-Depth Insight for Knowledge Base Question Answering [52.86931192259096]
  Knowledge Base Question Answering (KBQA) aims to answer natural language questions based on facts in knowledge bases. Recent works leverage the capabilities of large language models (LLMs) for logical form generation to improve performance.
  arXiv  Detail & Related papers  (2024-01-11T09:27:50Z)
• Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning [36.8749786658624]
  Large Language Models (LLM) exhibit zero-shot mathematical reasoning capacity as a behavior emergent with scale. We show that small LMs can achieve reasonable arithmetic reasoning if arithmetic word problems are posed as a formalize-then-solve task.
  arXiv  Detail & Related papers  (2023-12-09T13:20:49Z)
• CLadder: Assessing Causal Reasoning in Language Models [82.8719238178569]
  We investigate whether large language models (LLMs) can coherently reason about causality. We propose a new NLP task, causal inference in natural language, inspired by the "causal inference engine" postulated by Judea Pearl et al.
  arXiv  Detail & Related papers  (2023-12-07T15:12:12Z)
• LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers [60.009969929857704]
  Logical reasoning is an important task for artificial intelligence with potential impacts on science, mathematics, and society. In this work, we reformulating such tasks as modular neurosymbolic programming, which we call LINC. We observe significant performance gains on FOLIO and a balanced subset of ProofWriter for three different models in nearly all experimental conditions we evaluate.
  arXiv  Detail & Related papers  (2023-10-23T17:58:40Z)
• Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning [101.26814728062065]
  Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. This paper introduces a novel framework, Logic-LM, which integrates LLMs with symbolic solvers to improve logical problem-solving.
  arXiv  Detail & Related papers  (2023-05-20T22:25:38Z)
• PAL: Program-aided Language Models [112.94785609781503]
  We present Program-Aided Language models (PaL) to understand natural language problems. PaL offloads the solution step to a programmatic runtime such as a Python interpreter. We set new state-of-the-art results in all 12 benchmarks.
  arXiv  Detail & Related papers  (2022-11-18T18:56:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.