Papers
Topics
Authors
Recent
Search
2000 character limit reached

Prompt2DeModel: Declarative Neuro-Symbolic Modeling with Natural Language

Published 30 Jul 2024 in cs.CL, cs.AI, and cs.HC | (2407.20513v1)

Abstract: This paper presents a conversational pipeline for crafting domain knowledge for complex neuro-symbolic models through natural language prompts. It leverages LLMs to generate declarative programs in the DomiKnowS framework. The programs in this framework express concepts and their relationships as a graph in addition to logical constraints between them. The graph, later, can be connected to trainable neural models according to those specifications. Our proposed pipeline utilizes techniques like dynamic in-context demonstration retrieval, model refinement based on feedback from a symbolic parser, visualization, and user interaction to generate the tasks' structure and formal knowledge representation. This approach empowers domain experts, even those not well-versed in ML/AI, to formally declare their knowledge to be incorporated in customized neural models in the DomiKnowS framework.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Pylon: A pytorch framework for learning with constraints. In NeurIPS 2021 Competitions and Demonstrations Track, pages 319–324. PMLR, 2022.
  2. Program synthesis with large language models. arXiv preprint arXiv:2108.07732, 2021.
  3. A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 632–642, 2015.
  4. Codet: Code generation with generated tests. arXiv preprint arXiv:2207.10397, 2022.
  5. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374, 2021.
  6. Palm: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311, 2022.
  7. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021.
  8. H. R. Faghihi and P. Kordjamshidi. Time-stamped language model: Teaching language models to understand the flow of events. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4560–4570, 2021.
  9. DomiKnowS: A library for integration of symbolic domain knowledge in deep learning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 231–241, 2021.
  10. The role of semantic parsing in understanding procedural text. In Findings of the Association for Computational Linguistics: EACL 2023, pages 1792–1804, 2023.
  11. M. Freitag and Y. Al-Onaizan. Beam search strategies for neural machine translation. ACL 2017, page 56, 2017.
  12. Inference-masked loss for deep structured output learning. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pages 2754–2761, 2021.
  13. Folio: Natural language reasoning with first-order logic. arXiv preprint arXiv:2209.00840, 2022.
  14. Multiplexnet: Towards fully satisfied logical constraints in neural networks. In Proceedings of the AAAI conference on artificial intelligence, volume 36, pages 5700–5709, 2022.
  15. Harnessing deep neural networks with logic rules. In 54th ACL, pages 2410–2420, 2016.
  16. Scallop: From probabilistic deductive databases to scalable differentiable reasoning. Advances in Neural Information Processing Systems, 34:25134–25145, 2021.
  17. Large language models can self-improve. arXiv preprint arXiv:2210.11610, 2022.
  18. Cladder: Assessing causal reasoning in language models. In Thirty-seventh conference on neural information processing systems.
  19. Chatgpt: Jack of all trades, master of none. Information Fusion, page 101861, 2023.
  20. Saul: towards declarative learning based programming. In Proceedings of the 24th International Conference on Artificial Intelligence, IJCAI’15, page 1844–1851. AAAI Press, 2015. ISBN 9781577357384.
  21. Systems ai: A declarative learning based programming perspective. In International Joint Conference on Artificial Intelligence, 2018. URL https://api.semanticscholar.org/CorpusID:44080347.
  22. Declarative learning-based programming as an interface to ai systems. Frontiers in artificial intelligence, 5:755361, 2022.
  23. Cifar-100 (canadian institute for advanced research). URL http://www.cs.toronto.edu/~kriz/cifar.html.
  24. J. Lloyd. Practical advantages of declarative programming. In Unknown, pages 3 – 17, 1994. Conference Proceedings/Title of Journal: Joint Conference on Declarative Programming.
  25. Deepproblog: Neural probabilistic logic programming. Advances in neural information processing systems, 31, 2018.
  26. R. Mirzaee and P. Kordjamshidi. Disentangling extraction and reasoning in multi-hop spatial reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 3379–3397, 2023.
  27. Probabilistic reasoning in generative large language models. arXiv preprint arXiv:2402.09614, 2024.
  28. A primal dual formulation for deep learning with constraints. In Advances in Neural Information Processing Systems, pages 12157–12168, 2019.
  29. Lever: Learning to verify language-to-code generation with execution. In International Conference on Machine Learning, pages 26106–26128. PMLR, 2023.
  30. Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:2203.13474, 2022.
  31. Logic-lm: Empowering large language models with symbolic solvers for faithful logical reasoning. arXiv preprint arXiv:2305.12295, 2023.
  32. Certified reasoning with language models. arXiv preprint arXiv:2306.04031, 2023.
  33. H. Rajaby Faghihi and P. Kordjamshidi. Consistent joint decision-making with heterogeneous learning models. In Y. Graham and M. Purver, editors, Findings of the Association for Computational Linguistics: EACL 2024, pages 803–813, St. Julian’s, Malta, Mar. 2024. Association for Computational Linguistics. URL https://aclanthology.org/2024.findings-eacl.53.
  34. Gluecons: A generic benchmark for learning under constraints. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8):9552–9561, Jun. 2023. doi: 10.1609/aaai.v37i8.26143.
  35. D. Roth. Learning Based Programming. Technical Report UIUCDCS-R-99-2127, 10 1999. URL http://cogcomp.org/papers/Roth99c.pdf.
  36. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950, 2023.
  37. Picard: Parsing incrementally for constrained auto-regressive decoding from language models. In EMNLP, pages 9895–9901, 2021.
  38. Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580, 2023.
  39. WIQA: A dataset for “what if…” reasoning over procedural text. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6076–6085, Hong Kong, China, Nov. 2019. Association for Computational Linguistics. doi: 10.18653/v1/D19-1629. URL https://aclanthology.org/D19-1629.
  40. Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition. In Proceedings of the Seventh Conference on Natural Language Learning at HLT-NAACL 2003, pages 142–147, 2003. URL https://aclanthology.org/W03-0419.
  41. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  42. Prompt2model: Generating deployable models from natural language instructions. arXiv preprint arXiv:2308.12261, 2023.
  43. Exploring the trade-offs: Unified large language models vs local fine-tuned models for highly-specific radiology nli task. arXiv preprint arXiv:2304.09138, 2023.
  44. A semantic loss function for deep learning with symbolic knowledge. In ICML, pages 5502–5511. PMLR, 2018.
  45. Coupling large language models with logic programming for robust and general reasoning from text. arXiv preprint arXiv:2307.07696, 2023.
  46. P. Yu and S. Bach. Alfred: A system for prompted weak supervision. arXiv preprint arXiv:2305.18623, 2023.
  47. Coder reviewer reranking for code generation. In International Conference on Machine Learning, pages 41832–41846. PMLR, 2023.
  48. A survey of large language models. arXiv preprint arXiv:2303.18223, 2023.

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up