CoChat
Sign Up
Cited by 1Logic, Reasoning, and KnowledgeNatural Language Processing TechniquesSoftware Engineering Research

Predicate Renaming via Large Language Models

Open access
Gentili, Elisabetta, Ribeiro, Tony, Riguzzi, Fabrizio, Inoue, Katsumi·2026·Machine Learning
DOI 10.1007/s10994-026-07075-1
Open this paper in CoChat — free accountOpen PDF

Abstract

In this paper, we address the problem of giving names to predicates in logic rules using Large Language Models (LLMs). In the context of Inductive Logic Programming, various rule generation methods produce rules containing unnamed predicates, with Predicate Invention being a key example. This hinders the readability, interpretability, and reusability of the logic theory. Leveraging recent advancements in LLMs development, we explore their ability to process natural language and code to provide semantically meaningful suggestions for giving a name to unnamed predicates. The evaluation of our approach on some hand-crafted logic rules indicates that LLMs hold potential for this task.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s10994-026-07075-1

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Existing PI methods operate through purely syntactic symbol manipulation and lack conceptual understanding of what they invent.

    “Second, existing PI methods operate through purely syntactic symbol manipulation and lack conceptual understanding of what they invent [4].”

    From ADVENT: LLM-Driven Automatic Predicate Invention for ILP (2026) · cites this paper as [4]

    Section 2.1 (page unavailable) says invented predicates can have placeholder names that obscure their intended meaning. Section 3 (page unavailable) describes an approach that generates syntactically valid predicates without automatically determining their semantic names. These passages support a limitation in semantic naming, but not the broader claim that existing PI methods operate purely through syntactic manipulation or lack conceptual understanding. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Existing PI methods produce semantically opaque predicates.

    “Existing methods rely on domain expertise and produce semantically opaque predicates, hindering adaptation to unfamiliar domains and cross-task reuse.”

    From ADVENT: LLM-Driven Automatic Predicate Invention for ILP (2026) · cites this paper as [4]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 57 · Cited by 1

Research works printed but not linked: 64

  1. Abiteboul, S., Hull, R., & Vianu, V. (1995). Foundations of databases. Addison-Wesley.
  2. Alammar, J., & Grootendorst, M. (2024). Hands-On Large Language Models. O'Reilly, Sebastopol, CA, USA, https://www .oreilly.co m/library/v iew/hand s-on-large-language/9781098150952/. 135 Page 36 of 39 Machine Learning (2026) 115:135
  3. Bommasani, R., Hudson, D. A., & Adeli, E. (2021). On the opportunities and risks of foundation models. arXiv:2108.07258 · arXiv
  4. Bordes, A., Usunier, N., & Garcia-Duran, A. (2013). Translating embeddings for modeling multi-relational data. Advances in Neural Information Processing Systems 26.
  5. Brown, T., Mann, B., & Ryder, N. (2020). Language models are few-shot learners. In: H. Larochelle, M. Ran- zato, & R. Hadsell (Eds.), Advances in neural information processing systems (Vol. 33, pp. 1877-1901).
  6. Chen, M., Tworek, J., & Jun, H. (2021). Evaluating large language models trained on code. arXiv:2107.03374 · arXiv
  7. Cobbe, K., Kosaraju, V., & Bavarian, M. (2021). Training verifiers to solve math word problems. arXiv:2110.14168 · arXiv
  8. Cohere For AI (2024) c4ai-command-r-plus-08-2024. https://doi.org/10.57967/hf/3135, h t / / -- · DOI
  9. Colmerauer, A., & Roussel, P. (1996). The birth of Prolog, Association for Computing Machinery, New York, NY, USA, pp. 331-367. https://doi.org/10.1145/234286.1057820. · DOI
  10. Creswell, A., Shanahan, M., & Higgins, I. (2022). Selection-inference: Exploiting large language models for interpretable logical reasoning. arXiv:2205.09712 · arXiv
  11. Cropper, A., & Morel, R. (2021b). Predicate invention by learning from failures. arXiv:2104.14426 · arXiv
  12. Cunnington, D., Law, M., Lobo, J., & Russo, A. (2024). The role of foundation models in neuro symbolic learning and reasoning. In: T. R. Besold, A. d'Avila Garcez, & E. Jimenez-Ruiz (Eds.), Neural-symbolic learning and reasoning (pp. 84-100). Springer.
  13. Dash, A., Mathur, B., & Patil, P. (2024). Enhancing carbon emission tracking with gemini: An ai solution for sustainable development. https://doi.org/10.13140/RG.2.2.26165.90089 · DOI
  14. De Giorgis, S., Gangemi, A., & Russo, A. (2024). Neurosymbolic graph enrichment for grounded world models. arXiv:2411.12671 · arXiv
  15. Fadja, A. N., Lamma, E., & Riguzzi, F. (2017). Deep probabilistic logic programming. Plp@ Ilp (pp. 3-14)
  16. Gandarela, J. P., Carvalho, D. S., & Freitas, A. (2024). Inductive learning of logical theories with LLMs: A complexity-graded analysis. arXiv:2408.16779 · arXiv
  17. Gu, A., & Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv:2312.00752 · arXiv
  18. Gulwani, S. (2011). Automating string processing in spreadsheets using input-output examples. ACM Sigplan Notices, 46(1), 317-330.
  19. Han, S.J., Ransom, K.J., Perfors, A. & Kemp, C. (2024). Inductive reasoning in humans and large language models. Cognitive Systems Research, 83, Article 101155. https://doi.org/10.1016/j.cogsys.2023.101155 · DOI
  20. Hinton, G. (2015). Distilling the knowledge in a neural network. arXiv:1503.02531 · arXiv
  21. Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2024). Large language models for software engineering: A systematic literature review. ACM Transactions on Soft- ware Engineering and Methodology, 33(8), 1-79.
  22. Inoue, K., Doncescu, A., & Nabeshima, H. (2013). Completing causal networks by meta-level abduction. Machine Learning, 91(2), 239-277.
  23. Inoue, K., Furukawa, K., Kobayashi, I., & Nabeshima, H. (2010). Discovering rules by meta-level abduc- tion. In: Inductive logic programming: 19th international conference, ILP 2009, Leuven, Belgium, July 02-04, 2009. Revised Papers 19, Springer, pp. 49-64.
  24. Jiang, J., Wang, F., & Shen, J. (2024). A survey on large language models for code generation. arXiv:2406.00515 · arXiv
  25. Kaddour, J., Harris, J., & Mozes, M. (2023). Challenges and applications of large language models. arXiv:2307.10169 · arXiv
  26. Kakas, A. C., Kowalski, R. A., & Toni, F. (1992). Abductive logic programming. Journal of Logic and Com- putation, 2(6), 719-770.
  27. Kareem, I., Gallagher, K., Borroto, M., Ricca, F., & Russo, A. (2025). Using learning from answer sets for robust question answering with llm. In C. Dodaro, G. Gupta, & M. V. Martinez (Eds.), Logic program- ming and nonmonotonic reasoning (pp. 112-125). Springer.
  28. Kim, J., Lee, J. H., Kim, S., Park, J., Yoo, K. M., Kwon, S. J., & Lee, D. (2023). Memory-efficient fine- tuning of compressed large language models via sub-4-bit integer quantization. In A. Oh, T. Naumann, & A. Globerson (Eds.), Advances in neural information processing systems (Vol. 36, pp. 36187-36207).
  29. Kojima, T., Gu, S. S., & Reid, M. (2022). Large language models are zero-shot reasoners. In: S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, & A. Oh (Eds.), Advances in Neural Information Process- ing Systems, vol 35. Curran Associates, Inc., Red Hook, NY, USA, pp. 22199-22213, h Kok, S., & Domingos, P. (2005). Learning the structure of markov logic networks. Proceedings of the 22nd international conference on Machine learning (pp. 441-448).
  30. Koubaa, A., Boulila, W., & Ghouti, L. (2023). Exploring ChatGPT capabilities and limitations: A survey. IEEE Access. https://doi.org/10.1109/access.2023.3326474 · DOI
  31. Kowalski, R. A. (1988). The early years of logic programming. Communications of the ACM, 31, 38-43.
  32. Law, M., Russo, A., & Broda, K. (2020). The ilasp system for inductive learning of answer set programs. arXiv:2005.00904 · arXiv
  33. Li, Z., Cao, Y., & Xu, X. (2024). Llms for relational reasoning: How far are we? Proceedings of the 1st Inter- national Workshop on Large Language Models for Code (pp. 119-126).
  34. Liu, Y., He, H., & Han, T. (2024b). Understanding llms: A comprehensive overview from training to infer- ence. arXiv:2401.02038 · arXiv
  35. Magdy, S. M., Alwajih, F., Kwon, S. Y., Abdel-Salam, R., & Abdul-Mageed, M. (2024). Gazelle: An instruc- tion dataset for Arabic writing assistance. https://arxiv.org/abs/2410.18163 · arXiv
  36. Mooney, R. J. (1996). Inductive logic programming for natural language processing. International confer- ence on inductive logic programming (pp. 1-22). Springer.
  37. Moradi Dakhel, A., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., & Jiang, Z. M. J. (2023). GitHub Copilot AI pair programmer: Asset or liability? Journal of Systems and Software, 203, Article 111734. https://doi.org/10.1016/j.jss.2023.111734 · DOI · Paper page
  38. Muggleton, S., & Buntine, W. (1988). Machine invention of first-order predicates by inverting resolution. Machine Learning Proceedings 1988 (pp. 339-352). Elsevier. 135 Page 38 of 39 Machine Learning (2026) 115:135
  39. Nguembang Fadja, A., Riguzzi, F., & Lamma, E. (2021). Learning hierarchical probabilistic logic programs. Machine Learning, 110(7), 1637-1693.
  40. Pearce, H., Tan, B., Ahmad, B., Karri, R., & Dolan-Gavitt, B. (2023). Examining zero-shot vulnerability repair with large language models. In: 2023 IEEE Symposium on Security and Privacy (SP), pp. 2339- 2356, https://doi .org/10.110 9/SP46215.2 023.1017 9324 · DOI
  41. Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of Machine Learning Research, 21(140), 1-67.
  42. Rao, A., Pang, M., Kim, J., Kamineni, M., Lie, W., Prasad, A. K., Landman, A., Dreyer, K., & Succi, M. D. (2023). Assessing the utility of ChatGPT throughout the entire clinical workflow: Development and usability study. Journal of Medical Internet Research, 25, Article e48659.
  43. Rezayi, S., Liu, Z., & Wu, Z. (2022). Agribert: Knowledge-infused agricultural language models for match- ing food and nutrition. IJCAI, 5150-5156.
  44. Ribeiro, T., Folschette, M., Magnin, M., & Inoue, K. (2021). Learning any memory-less discrete semantics for dynamical systems represented by logic programs. Machine Learning. h t t p s : / / d o i . o r g / 1 0 . 1 0 0 7 / s 1 0 9 9 4 -0 2 1 -0 6 1 0 5 -4 · DOI
  45. Riguzzi, F. (2023). Foundations of probabilistic logic programming: Languages, semantics, inference and learning (2nd ed.). River Publishers.
  46. Sato, T., Inoue, K., & Sakama, C. (2018). Abducing relations in continuous spaces. IJCAI (pp. 1956-1962).
  47. Srinivasan, A., King, R. D., & Muggleton, S. H. (1997). Carcinogenesis predictions using ilp. International Conference on Inductive Logic Programming (pp. 273-287). Springer.
  48. Srinivasan, A., Muggleton, S. H., Sternberg, M. J., & King, R. D. (1996). Theories for mutagenicity: A study in first-order and feature-based induction. Artificial Intelligence, 85(1-2), 277-299.
  49. Srivastava, A., Rastogi, A., & Rao, A. (2022). Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv:2206.04615 · arXiv
  50. Stahl, I. (1993). Predicate invention in ilp-an overview. European conference on machine learning (pp. 311- 322). Springer.
  51. Talmor, A., Herzig, J., & Lourie, N. (2018). Commonsenseqa: A question answering challenge targeting com- monsense knowledge. arXiv:1811.00937 · arXiv
  52. Tarau, P. (2025). On llm-generated logic programs and their inference execution methods. arXiv:2502.09209 · arXiv
  53. Touvron, H., Lavril, T., & Izacard, G. (2023). Llama: Open and efficient foundation language models. arXiv:2302.13971 · arXiv
  54. Valmeekam, K., Olmo, A., & Sreedharan, S. (2022). Large language models still can't plan (a benchmark for llms on planning and reasoning about change). NeurIPS 2022 Foundation Models for Decision Making Workshop.
  55. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. U., & Polosukhin, I. (2017). Attention is all you need. In: Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., & Garnett, R. (Eds.), Advances in Neural Information Processing Systems, vol 30.
  56. Vennekens, J., Verbaeten, S., & Bruynooghe, M. (2004). Logic programs with annotated disjunctions. In: Logic Programming: 20th International Conference, ICLP 2004, Saint-Malo, France, September 6-10, 2004. Proceedings 20, Springer, pp. 431-445.
  57. Wang, R., Zelikman, E., & Poesia, G. (2023). Hypothesis search: Inductive reasoning with language models. arXiv:2309.05660 · arXiv
  58. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtow- icz, M., Davison, J., Shleifer, S., Platen, P., Ma, C., Jernite, Y., Plu, J., Xu, C., Scao, T. L., Gugger, S., Drame, M., Lhoest, Q., & Rush, A. M. (2020). Transformers: State-of-the-art natural language process- ing. In: Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations. Association for Computational Linguistics, Online, pp. 38-45, h t t p s : / / w w w . a c l . o /
  59. Wu, Z., Zhang, L., Cao, C., Yu, X., Liu, Z., Zhao, L., Li, Y., Dai, H., Ma, C., Li, G., Liu, W., Li, Q., Shen, D., Li, X., Zhu, D., & Liu, T. (2025). Exploring the trade-offs: Unified large language models vs local fine-tuned models for highly-specific radiology NLI task. IEEE Transactions on Big Data, 11(3), 1027- 1041. https://doi.org/10.1109/TBDATA.2025.3536928 · DOI
  60. Yang, Z., Dong, L., Du, X., Cheng, H., Cambria, E., Liu, X., Gao, J., & Wei, F. (2020). On the sub-layer functionalities of transformer decoder. In: Cohn T, He Y, Liu Y (Eds.), Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, Online, pp. 4799-4811. https://acl anthology.o rg/2020.fin dings-em nlp.432/
  61. Yang, Y., Wang, L., Shi, S., Tadepalli, P., Lee, S., & Tu, Z. (2024). On the sub-layer function-alities of trans- former decoder. In: Cohn, T., He, Y., Liu, Y (Eds.), Language models as inductive reasoners. In: Graham Y, Purver M (Eds.), Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, St. Julian's, Malta, pp 209-225, https://aclanthology.org/2024.eacl-long.13/
  62. Zhang, Z., Yilmaz, L., & Liu, B. (2024). A critical review of inductive logic programming techniques for explainable AI. IEEE Transactions on Neural Networks and Learning Systems, 35(8), 10220-10236. https://doi.org/10.1109/TNNLS.2023.3246980 · DOI · Paper page
  63. Zheng, L., Chiang, W., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li,D., Xing, E.P., Zhang, H., Gonzalez, J.E., Stoica, I.(2023). Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36, 46595-46623.
  64. Zuo, J., Velikanov, M., Rhaiem, D.E., Chahed, I., Belkada, Y., Kunsch, G., Hacid, H.: Falcon Mamba: The First Competitive Attention-free 7B Language Model (2024). https://arxiv.org/abs/2410.05355 · arXiv

Authors
Gentili, E., Ribeiro, T., Riguzzi, F., & Inoue, K.
Affiliations
  • National Institute of Informatics (JP)
  • École Centrale de Nantes (FR)
  • University of Ferrara (IT)
Corresponding author
  • Gentili, Elisabetta
  • Ribeiro, Tony
  • Riguzzi, Fabrizio
  • Inoue, Katsumi
ORCID
Venue
Machine Learning
Publisher
Springer Science and Business Media LLC
Published
2026-05-23
Volume
115
Issue
6
ISSN
  • 0885-6125 (ISSN-L)
  • 1573-0565
DOI
10.1007/s10994-026-07075-1
OpenAlex
W7162215952
Cited by
1
References
57
Citations by year
2026: 1
FWCI
3.42
Type
journal article
Language
en
Open access
Licence
Locations
  • Machine Learning (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • Institutional Research Information System University of Ferrara (University of Ferrara) (submittedVersion, cc-by)
Funders
Università degli Studi di Ferrara
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Logic, Reasoning, and Knowledge
  • Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
  • Physical Sciences › Computer Science › Information Systems › Software Engineering Research
Keywords
predicate invention, large language models, inductive logic programming

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review