Papers
Topics
Authors
Recent
Search
2000 character limit reached

Explaining Genetic Programming Trees using Large Language Models

Published 6 Mar 2024 in cs.NE | (2403.03397v1)

Abstract: Genetic programming (GP) has the potential to generate explainable results, especially when used for dimensionality reduction. In this research, we investigate the potential of leveraging eXplainable AI (XAI) and LLMs like ChatGPT to improve the interpretability of GP-based non-linear dimensionality reduction. Our study introduces a novel XAI dashboard named GP4NLDR, the first approach to combine state-of-the-art GP with an LLM-powered chatbot to provide comprehensive, user-centred explanations. We showcase the system's ability to provide intuitive and insightful narratives on high-dimensional data reduction processes through case studies. Our study highlights the importance of prompt engineering in eliciting accurate and pertinent responses from LLMs. We also address important considerations around data privacy, hallucinatory outputs, and the rapid advancements in generative AI. Our findings demonstrate its potential in advancing the explainability of GP algorithms. This opens the door for future research into explaining GP models with LLMs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Y. Mei, Q. Chen, A. Lensen, B. Xue, and M. Zhang, “Explainable artificial intelligence by genetic programming: A survey,” IEEE Transactions on Evolutionary Computation, vol. 27, no. 3, pp. 621–641, 2023.
  2. T. P. Quinn, S. Jacobs, M. Senadeera, V. Le, and S. Coghlan, “The three ghosts of medical AI: Can the black-box present deliver?” Artificial Intelligence in Medicine, vol. 124, p. 102158, 2022.
  3. Z. Salahuddin, H. C. Woodruff, A. Chatterjee, and P. Lambin, “Transparency of deep neural networks for medical image analysis: A review of interpretability methods,” Computers in Biology and Medicine, vol. 140, p. 105111, 2022.
  4. O. Kuiper, M. van den Berg, J. van der Burgt, and S. Leijnen, “Exploring explainable AI in the financial sector: Perspectives of banks and supervisory authorities,” in Artificial Intelligence and Machine Learning, L. A. Leiva, C. Pruski, R. Markovich, A. Najjar, and C. Schommer, Eds.   Cham: Springer International Publishing, 2022, pp. 105–119.
  5. M. Ribera and A. Lapedriza, “Can we do better explanations? A proposal of user-centered explainable AI,” in Intelligent User Interfaces (IUI) Workshops, 2019.
  6. T. Miller, “Explanation in artificial intelligence: Insights from the social sciences,” Artificial Intelligence, vol. 267, pp. 1–38, 2019.
  7. P. Maddigan and T. Susnjak, “Chat2vis: Fine-tuning data visualisations using multilingual natural language text and pre-trained large language models,” arXiv preprint arXiv:2303.14292, 2023.
  8. ——, “Chat2vis: Generating data visualizations via natural language using chatgpt, codex and gpt-3 large language models,” IEEE Access, vol. 11, pp. 45 181–45 193, 2023.
  9. S. Nguyen, D. Thiruvady, Y. Sun, and M. Zhang, “Genetic-based constraint programming for resource constrained job scheduling,” arXiv preprint arXiv:2402.00459, 2024.
  10. Q. Fan, Y. Bi, B. Xue, and M. Zhang, “A genetic programming-based method for image classification with small training data,” Knowledge-Based Systems, vol. 283, p. 111188, 2024.
  11. Q. U. Ain, B. Xue, H. Al-Sahaf, and M. Zhang, “Skin cancer detection with multimodal data: A feature selection approach using genetic programming,” in Data Science and Machine Learning, D. Benavides-Prado, S. Erfani, P. Fournier-Viger, Y. L. Boo, and Y. S. Koh, Eds.   Singapore: Springer Nature Singapore, 2024, pp. 254–269.
  12. L. Wu, L. Yuan, G. Zhao, H. Lin, and S. Z. Li, “Deep clustering and visualization for end-to-end high-dimensional data analysis,” IEEE Transactions on Neural Networks and Learning Systems, pp. 1–12, 2022.
  13. Q. V. Nguyen, M. Lin Huang, and S. Simoff, “Enhancing scatter-plots with start-plots for visualising multi-dimensional data,” in 2020 24th International Conference Information Visualisation (IV), 2020, pp. 80–85.
  14. S. J. Fernstad, A. Macquisten, J. Berrington, N. Embleton, and C. Stewart, “Quality Metrics to Guide Visual Analysis of High Dimensional Genomics Data,” in EuroVis Workshop on Visual Analytics (EuroVA), C. Turkay and K. Vrotsou, Eds.   The Eurographics Association, 2020.
  15. A. Agrawal and C. McComb, “Comparing strategies for visualizing the high-dimensional exploration behavior of cps design agents,” in 2022 IEEE Workshop on Design Automation for CPS and IoT (DESTION), 2022, pp. 64–69.
  16. A. Lensen, B. Xue, and M. Zhang, “Genetic programming for evolving a front of interpretable models for data visualization,” IEEE Transactions on Cybernetics, vol. 51, no. 11, pp. 5468–5482, 2021.
  17. T. Uriot, M. Virgolin, T. Alderliesten, and P. A. N. Bosman, “On genetic programming representations and fitness functions for interpretable dimensionality reduction,” in Proceedings of the Genetic and Evolutionary Computation Conference.   ACM, 2022.
  18. A. Lensen, B. Xue, and M. Zhang, “Can genetic programming do manifold learning too?” in Proceedings of the European Conference on Genetic Programming (EuroGP), Lecture Notes in Computer Science.   Springer International Publishing, 2019, vol. 11451, pp. 114–130.
  19. A. Lensen, M. Zhang, and B. Xue, “Multi-objective genetic programming for manifold learning: balancing quality and dimensionality,” Genetic Programming and Evolvable Machines, vol. 21, no. 3, pp. 399–431, feb 2020.
  20. F. Schofield and A. Lensen, “Using genetic programming to find functional mappings for umap embeddings,” in 2021 IEEE Congress on Evolutionary Computation (CEC), 2021, pp. 704–711.
  21. L. Longo, M. Brcic, F. Cabitza, J. Choi, R. Confalonieri, J. D. Ser, R. Guidotti, Y. Hayashi, F. Herrera, A. Holzinger, R. Jiang, H. Khosravi, F. Lecue, G. Malgieri, A. Páez, W. Samek, J. Schneider, T. Speith, and S. Stumpf, “Explainable artificial intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions,” Information Fusion, vol. 106, p. 102301, 2024.
  22. S. Ali, T. Abuhmed, S. El-Sappagh, K. Muhammad, J. M. Alonso-Moral, R. Confalonieri, R. Guidotti, J. Del Ser, N. Díaz-Rodríguez, and F. Herrera, “Explainable artificial intelligence (XAI): What we know and what is left to attain trustworthy artificial intelligence,” Information Fusion, vol. 99, p. 101805, 2023.
  23. S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, ser. NIPS’17.   Curran Associates, 2017, p. 4768–4777.
  24. M. T. Ribeiro, S. Singh, and C. Guestrin, “”Why should i trust you?” explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.   Association for Computing Machinery, 2016, pp. 1135–1144.
  25. J. Klaise, A. V. Looveren, G. Vacanti, and A. Coca, “Alibi explain: Algorithms for explaining machine learning models,” Journal of Machine Learning Research, vol. 22, no. 181, pp. 1–7, 2021.
  26. R. K. Mothilal, A. Sharma, and C. Tan, “Explaining machine learning classifiers through diverse counterfactual explanations,” in Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 2020, pp. 607–617.
  27. M. Venturini, I. Van Keilegom, W. De Corte, and C. Vens, “Predicting time-to-intubation after critical care admission using machine learning and cured fraction information,” Artificial Intelligence in Medicine, vol. 150, p. 102817, 2024.
  28. P. Maddigan and T. Susnjak, “Forecasting patient demand at urgent care clinics using machine learning,” arXiv preprint arXiv:2205.13067, 2022.
  29. I. Hussain and R. Jany, “Interpreting stroke-impaired electromyography patterns through explainable artificial intelligence,” Sensors, vol. 24, no. 5, 2024.
  30. F. Afrin, M. Hamilton, and C. Thevathyan, “Exploring counterfactual explanations for predicting student success,” in Computational Science – ICCS 2023, J. Mikyška, C. de Mulatier, M. Paszynski, V. V. Krzhizhanovskaya, J. J. Dongarra, and P. M. Sloot, Eds.   Cham: Springer, 2023, pp. 413–420.
  31. N. R. Raji, R. M. S. Kumar, and C. L. Biji, “Explainable machine learning prediction for the academic performance of deaf scholars,” IEEE Access, vol. 12, pp. 23 595–23 612, 2024.
  32. M. Kuźba and P. Biecek, “What would you ask the machine learning model? identification of user needs for model explanations based on human-model conversations,” in ECML PKDD 2020 Workshops.   Springer International Publishing, 2020, pp. 447–459.
  33. M. Guimaraes, J. Baptista, and M. Sousa, “A conversational interface for interacting with machine learning models,” 2022.
  34. V. B. Nguyen, J. Schlötterer, and C. Seifert, “Explaining machine learning models in natural conversations: Towards a conversational XAI agent,” arXiv preprint arXiv:2209.02552, 2022.
  35. S. Luke and L. Panait, “A comparison of bloat control methods for genetic programming,” Evolutionary Computation, vol. 14, no. 3, pp. 309–344, 2006.
  36. B. Tran, B. Xue, and M. Zhang, “Genetic programming for feature construction and selection in classification on high-dimensional data,” Memetic Computing, vol. 8, no. 1, pp. 3–15, 2016.
  37. E. Cambria, L. Malandri, F. Mercorio, M. Mezzanzanica, and N. Nobani, “A survey on XAI and natural language explanations,” Information Processing & Management, vol. 60, no. 1, p. 103111, 2023.
  38. C. Singh, J. P. Inala, M. Galley, R. Caruana, and J. Gao, “Rethinking interpretability in the era of large language models,” arXiv preprint arXiv:2402.01761, 2024.
  39. C. C. Sartori, C. Blum, and G. Ochoa, “Large language models for the automated analysis of optimization algorithms,” arXiv preprint arXiv:2402.08472, 2024.
  40. C. Chacón Sartori, C. Blum, and G. Ochoa, “Stnweb: A new visualization tool for analyzing optimization algorithms,” Software Impacts, vol. 17, p. 100558, 2023.
  41. Y. Lappalainen and N. Narayanan, “Aisha: A custom AI library chatbot using the ChatGPT API,” Journal of Web Librarianship, vol. 17, no. 3, pp. 37–58, 2023.
  42. A. Rau, S. Rau, D. Zöller, A. Fink, H. Tran, C. Wilpert, J. Nattenmüller, J. Neubauer, F. Bamberg, M. Reisert, and M. F. Russe, “A context-based chatbot surpasses radiologists and generic ChatGPT in following the ACR appropriateness guidelines,” Radiology, vol. 308, no. 1, p. e230970, 2023.
  43. M. Zaib, W. E. Zhang, Q. Z. Sheng, A. Mahmood, and Y. Zhang, “Conversational question answering: a survey,” Knowledge and Information Systems, vol. 64, pp. 3151–3195, 2022.
  44. H. Chase, “LangChain,” Oct. 2022. [Online]. Available: https://github.com/hwchase17/langchain
  45. S. Luke and L. Panait, “Lexicographic parsimony pressure,” in Proceedings of the 4th Annual Conference on Genetic and Evolutionary Computation, 2002, pp. 829–836.
  46. ——, “Fighting bloat with nonparametric parsimony pressure,” in Parallel Problem Solving from Nature — PPSN VII.   Springer, 2002, pp. 411–421.
  47. R. Poli, “A simple but theoretically-motivated method to control bloat in genetic programming,” in Genetic Programming.   Springer, 2003, pp. 204–217.
  48. L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
  49. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
  50. P. Lewis, E. Perez, A. Piktus, F. Petroni, V. Karpukhin, N. Goyal, H. Küttler, M. Lewis, W.-t. Yih, T. Rocktäschel, S. Riedel, and D. Kiela, “Retrieval-augmented generation for knowledge-intensive nlp tasks,” in Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, Eds., vol. 33.   Curran Associates, Inc., 2020, pp. 9459–9474.
  51. J. Johnson, M. Douze, and H. Jégou, “Billion-scale similarity search with GPUs,” IEEE Transactions on Big Data, vol. 7, no. 3, pp. 535–547, 2019.
  52. S. Aeberhard and M. Forina, “Wine,” UCI Machine Learning Repository, 1991.
  53. N. Ilter and H. Guvenir, “Dermatology,” UCI Machine Learning Repository, 1998.
  54. S. A. Nene, S. K. Nayar, and H. Murase, “Columbia object image library (coil-20),” Department of Computer Science, Columbia University, Tech. Rep. CUCS-005-96, February 1996. [Online]. Available: https://www.bibsonomy.org/bibtex/2e21afb22e024792723fc3b9f659c522e/jabreftest
  55. A. Zhou, B. Li, and H. Wang, “Robust prompt optimization for defending language models against jailbreaking attacks,” arXiv preprint arXiv:2401.17263, 2024.
  56. T. R. McIntosh, T. Susnjak, T. Liu, P. Watters, and M. N. Halgamuge, “Inadequacies of large language model benchmarks in the era of generative artificial intelligence,” arXiv preprint arXiv:2402.09880, 2024.
  57. C. van der Lee, A. Gatt, E. van Miltenburg, S. Wubben, and E. Krahmer, “Best practices for the human evaluation of automatically generated text,” in Proceedings of the 12th International Conference on Natural Language Generation, K. van Deemter, C. Lin, and H. Takamura, Eds.   Tokyo, Japan: Association for Computational Linguistics, 2019, pp. 355–368.
Citations (3)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

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

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

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

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free