mlsanityData to 14 Oct 2026

Auto-Formalizing Neuro-Symbolic Predictors

arXiv 2610.01519 ↗First posted 1 Oct 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Neuro-Symbolic (NeSy) predictors incorporate prior knowledge into the prediction process of neural networks, ensuring that outputs satisfy specified constraints, making them particularly suitable for high-stakes applications where compliance with domain knowledge is essential. A key bottleneck in this paradigm is the acquisition of symbolic constraints: encoding domain knowledge into logical formulas remains a manual and expert-intensive process. In this work, we investigate the extent to which auto-formalization via LLMs can systematically translate textual knowledge into symbolic knowledge that can be plugged into NeSy predictors. To this end, we introduce auto-nesy-bench, a new benchmark for evaluating constraint formalization and its impact on downstream accuracy of NeSy predictors. Through an extensive evaluation across several domains, we find that LLMs can formalize constraints to a meaningful extent, generating formulas that are often similar to those provided by human experts. Moreover, when the generated formulas are syntactically valid, they can lead to high-quality downstream predictions. The code and benchmark are available at https://unitn-sml.github.io/auto-nesy-bench/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 136 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

26 of 136 references.

References · 26

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2021Program Synthesis with Large Language Modelscited by 3,637
  6. 2023Mistral 7Bcited by 3,164
  7. 2025Gemma 3 Technical Reportcited by 1,824
  8. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  9. 2024DeepSeek-V3 Technical Reportcited by 811
  10. 2026Gemma 4 Technical Reportcited by 259
  11. 2025Phi-4-reasoning Technical Reportcited by 151
  12. 2023Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performancecited by 147
14 more
  1. 2026Qwen3-Coder-Next Technical Reportcited by 71
  2. 2023Holy Grail 2.0: From Natural Language to Constraint Modelscited by 26
  3. 2025Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transitioncited by 14
  4. 2024The Role of Foundation Models in Neuro-Symbolic Learning and Reasoningcited by 12
  5. 2025To Ask or Not to Ask: Learning to Require Human Feedbackcited by 6
  6. 2025The DeepLog Neurosymbolic Machinecited by 5
  7. 2025The Road to Generalizable Neuro-Symbolic Learning Should be Paved with Foundation Modelscited by 4
  8. 2025DCP-Bench-Open: Evaluating LLMs for Constraint Modelling of Discrete Combinatorial Problemscited by 4
  9. 2025A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Datacited by 2
  10. 2025LangSAT: A Novel Framework Combining NLP and Reinforcement Learning for SAT Solvingcited by 2
  11. 2026LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detectioncited by 2
  12. 2026VeriTrans: Fine-Tuned LLM-Assisted NL-to-PL Translation via a Deterministic Neuro-Symbolic Pipelinecited by 2
  13. 2026Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Modelscited by 1
  14. 2026sLTN: Structural Logic Tensor Networkscited by 1

Built on by

Not cited yet.