mlsanityData to 14 Oct 2026

Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models

arXiv 2509.21874 ↗First posted 26 Sep 2025cs.LGcited by 3

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

We propose ILP-CoT, a method that bridges Inductive Logic Programming (ILP) and Multimodal Large Language Models (MLLMs) for abductive logical rule induction. The task involves both discovering logical facts and inducing logical rules from a small number of unstructured textual or visual inputs, which still remain challenging when solely relying on ILP, due to the requirement of specified background knowledge and high computational cost, or MLLMs, due to the appearance of perceptual hallucinations. Based on the key observation that MLLMs could propose structure-correct rules even under hallucinations, our approach automatically builds ILP tasks with pruned search spaces based on the rule structure proposals from MLLMs, and utilizes ILP system to output rules built upon rectified logical facts and formal inductive reasoning. Its effectiveness is verified through challenging logical induction benchmarks, as well as a potential application of our approach, namely text-to-image customized generation with rule induction. Our code and data are released at https://github.com/future-item/ILP-CoT.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 45 of its 56 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

45 of 56 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Compositional Chain-of-Thought Prompting for Large Multimodal Models27 Nov
  2. 2023What's Left? Concept Grounding with Logic-Enhanced Foundation Models24 Oct
  3. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond24 Aug

Other references · 42

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 2023Visual Instruction Tuningcited by 7,869
  7. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  8. 2023Qwen Technical Reportcited by 3,344
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  10. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,457
  11. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  12. 2020Object-Centric Learning with Slot Attentioncited by 876
30 more
  1. 2023Multimodal Chain-of-Thought Reasoning in Language Modelscited by 752
  2. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 708
  3. 2022PAL: Program-aided Language Modelscited by 652
  4. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 394
  5. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  6. 2022Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thoughtcited by 337
  7. 2023Faithful Chain-of-Thought Reasoningcited by 288
  8. 2022Autoformalization with Large Language Modelscited by 263
  9. 2023Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Modelscited by 261
  10. 2017Learning Explanatory Rules from Noisy Datacited by 211
  11. 2022Language models show human-like content effects on reasoning taskscited by 173
  12. 2023Solving Math Word Problems by Combining Language Models With Symbolic Solverscited by 124
  13. 2023Deductive Verification of Chain-of-Thought Reasoningcited by 124
  14. 2023Chain of Code: Reasoning with a Language Model-Augmented Code Emulatorcited by 123
  15. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 120
  16. 2023SatLM: Satisfiability-Aided Language Models Using Declarative Promptingcited by 102
  17. 2023Cones 2: Customizable Image Synthesis with Multiple Subjectscited by 101
  18. 2024Faithful Logical Reasoning via Symbolic Chain-of-Thoughtcited by 100
  19. 2020Inductive logic programming at 30: a new introductioncited by 85
  20. 2023LLMs and the Abstraction and Reasoning Corpus: Successes, Failures, and the Importance of Object-based Representationscited by 82
  21. 2020Learning programs by learning from failurescited by 73
  22. 2024Visual Prompting in Multimodal Large Language Models: A Surveycited by 54
  23. 2020Abductive Knowledge Induction From Raw Datacited by 38
  24. 2024A Survey on Personalized Content Synthesis with Diffusion Modelscited by 29
  25. 2024LeanReasoner: Boosting Complex Logical Reasoning with Leancited by 28
  26. 2024Language Models as Compilers: Simulating Pseudocode Execution Improves Algorithmic Reasoning in Language Modelscited by 20
  27. 2021FF-NSL: Feed-Forward Neural-Symbolic Learnercited by 15
  28. 2024Non-confusing Generation of Customized Concepts in Diffusion Modelscited by 15
  29. 2024NeSyCoCo: A Neuro-Symbolic Concept Composer for Compositional Generalizationcited by 13
  30. 2023Learning Differentiable Logic Programs for Abstract Visual Reasoningcited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026A Foundation Model for Zero-Shot Logical Rule Inductioncited by 1
  2. 2026ADVENT: LLM-Driven Automatic Predicate Invention for ILPcited by 0
  3. 2026When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Efficient rule induction by ignoring pointless rules
  2. 2025Honey, I shrunk the hypothesis space (through logical preprocessing)
  3. 2025Hypothesis Generation via LLM-Automated Language Bias for ILP
  4. 2026Visual Perceptual to Conceptual First-Order Rule Learning Networks
  5. 2024IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction
  6. 2024Program Synthesis using Inductive Logic Programming for the Abstraction and Reasoning Corpus
  7. 2025Logic Unseen: Revealing the Logical Blindspots of Vision-Language Models
  8. 2025A Survey of Inductive Reasoning for Large Language Models