Elamur Research⌕
☰
home / papers / 2023 / Large Language Models as General Pattern Machines

Large Language Models as General Pattern Machines

Paper · 2023 · Suvir Mirchandani, Fei Xia, Pete Florence et al.

Summary

The paper asks whether pre-trained LLMs, used with no fine-tuning, can act as generic engines for recognizing and continuing abstract, non-linguistic patterns, and whether this skill transfers to low-level robot control. The authors cast problems as in-context completion of token sequences in three families. In sequence transformation, the model maps inputs to outputs for PCFG-generated strings and ARC grid puzzles written as ASCII-like text. In sequence completion, it extrapolates simple functions such as sinusoids, for example to continue a wiping motion from kinesthetic demonstrations. In sequence improvement, reward-labelled trajectories are fed back into the prompt so the model proposes better ones during online interaction. On ARC, prompted models solve a meaningful share of puzzles. They keep part of this ability even when digits are replaced by random vocabulary tokens, which suggests largely token-invariant pattern reasoning. The method also discovers a CartPole controller and lets a human steer a robot with binary feedback. This is evidence that language pre-training provides priors usable for actions. However, latency, cost and context length currently limit real deployment.

Key points

  • On ARC, LLMs answer up to 85 of 800 problems correctly with no training. This beats several program-synthesis systems that rely on hand-designed DSLs, and some accuracy remains when symbols are mapped to random tokens.
  • In the Grid navigation task, the prompt lists the best past trajectories sorted by return, then requests a higher return than any seen so far. Model d3 reliably solves the task within 50 episodes (averaged over 5 trials), whereas smaller models sometimes keep repeating suboptimal behavior from the context.
  • For CartPole, observations are pole angle and velocity scaled to 0–100, actions are 1 (left) and 2 (right), and the horizon is 200. Returns rise over 100 LLM-driven episodes that follow 100 random ones, and d3 learns oscillating actions that keep the pole up.
  • A "clicker training" setup lets a human guide a robot end-effector to push an object. The robot acts every 2 s, episodes last 30 s, and the human gives only sparse binary rewards.
  • Stated limitations include one LLM query per predicted token, bounds set by context length, the need for consistent tokenization, and missing visual/physical grounding. For these reasons the approach is restricted to lab settings for now.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Stanford UniversityStanford · United States506 works · 330,052 citations🏢Google DeepMindLondon · United Kingdom72 works · 84,326 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,894 works

Cite

Cite as Suvir Mirchandani, Fei Xia, Pete Florence, Brian Ichter, Danny Driess, Montserrat Gonzalez Arenas, Kanishka Rao, Dorsa Sadigh and Andy Zeng. 2023. Large Language Models as General Pattern Machines. arXiv:2307.04721.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2307.04721 · arXiv 2307.04721

@misc{mirchandani2023large,
  title = {{Large Language Models as General Pattern Machines}},
  author = {Suvir Mirchandani, Fei Xia, Pete Florence, Brian Ichter, Danny Driess, Montserrat Gonzalez Arenas, Kanishka Rao, Dorsa Sadigh and Andy Zeng},
  year = {2023},
  doi = {10.48550/arxiv.2307.04721},
  eprint = {2307.04721},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2307.04721}
}

References

90 references, 38 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. J. Wei, X. Wang, D. Schuurmans, M. Bosma, E. Chi, Q. Le, and D. Zhou. Chain of thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems (NeurIPS), 2022. — Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  2. T. Kojima, S. S. Gu, M. Reid, Y. Matsuo, and Y. Iwasawa. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
  3. M. Suzgun, N. Scales, N. Schärli, S. Gehrmann, Y. Tay, H. W. Chung, A. Chowdhery, Q. V. Le, E. H. Chi, D. Zhou, et al. Challenging BIG-Bench tasks and whether chain-of-thought can solve them. arXiv:2210.09261, 2022.
  4. A. Creswell, M. Shanahan, and I. Higgins. Selection-Inference: Exploiting large language models for interpretable logical reasoning. arXiv:2205.09712, 2022. find
  5. A. Lewkowycz, A. Andreassen, D. Dohan, E. Dyer, H. Michalewski, V. Ramasesh, A. Slone, C. Anil, I. Schlag, T. Gutman-Solo, et al. Solving quantitative reasoning problems with language models. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
  6. M. Ahn, A. Brohan, N. Brown, Y. Chebotar, O. Cortes, B. David, C. Finn, K. Gopalakrishnan, K. Hausman, A. Herzog, et al. Do as I can, not as I say: Grounding language in robotic affordances. In Conference on Robot Learning (CoRL), 2022.
  7. W. Huang, P. Abbeel, D. Pathak, and I. Mordatch. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. arXiv:2201.07207, 2022.
  8. Y. Xie, C. Yu, T. Zhu, J. Bai, Z. Gong, and H. Soh. Translating natural language to planning goals with large-language models. arXiv:2302.05128, 2023. — [arXiv:2302.05128](https://arxiv.org/abs/2302.05128) find
  9. Y. Ding, X. Zhang, C. Paxton, and S. Zhang. Task and motion planning with large language models for object rearrangement. arXiv:2303.06247, 2023. — [arXiv:2303.06247](https://arxiv.org/abs/2303.06247) find
  10. B. Liu, Y. Jiang, X. Zhang, Q. Liu, S. Zhang, J. Biswas, and P. Stone. LLM+P: Empowering large language models with optimal planning proficiency. arXiv:2304.11477, 2023.
  11. E. Zelikman, Q. Huang, G. Poesia, N. D. Goodman, and N. Haber. Parsel: A (de-) compositional framework for algorithmic reasoning with language models. arXiv:2212.10561, 2023.
  12. K. Lin, C. Agia, T. Migimatsu, M. Pavone, and J. Bohg. Text2Motion: From natural language instructions to feasible plans. arXiv:2303.12153, 2023. — [arXiv:2303.12153](https://arxiv.org/abs/2303.12153) find
  13. J. Liang, W. Huang, F. Xia, P. Xu, K. Hausman, B. Ichter, P. Florence, and A. Zeng. Code as Policies: Language model programs for embodied control. In International Conference on Robotics and Automation (ICRA), 2023. find
  14. I. Singh, V. Blukis, A. Mousavian, A. Goyal, D. Xu, J. Tremblay, D. Fox, J. Thomason, and A. Garg. ProgPrompt: Generating Situated Robot Task Plans using Large Language Models. In International Conference on Robotics and Automation (ICRA), 2023.
  15. M. Kwon, S. M. Xie, K. Bullard, and D. Sadigh. Reward Design with Language Models. In International Conference on Learning Representations (ICLR), 2023.
  16. H. Hu and D. Sadigh. Language Instructed Reinforcement Learning for Human-AI Coordination. In International Conference on Machine Learning (ICML), 2023. find
  17. J. Wu, R. Antonova, A. Kan, M. Lepert, A. Zeng, S. Song, J. Bohg, S. Rusinkiewicz, and T. Funkhouser. TidyBot: Personalized Robot Assistance with Large Language Models. In International Conference on Intelligent Robots and Systems (IROS), 2023. find
  18. J. Liu, D. Shen, Y. Zhang, B. Dolan, L. Carin, and W. Chen. What Makes Good In-Context Examples for GPT-3. In Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, 2021.
  19. Z. Zhao, E. Wallace, S. Feng, D. Klein, and S. Singh. Calibrate before use: Improving few-shot performance of language models. In International Conference on Machine Learning (ICML), 2021.
  20. F. Chollet. On the measure of intelligence. arXiv:1911.01547, 2019. find
  21. S. Ferré. First Steps of an Approach to the ARC Challenge based on Descriptive Grid Models and the Minimum Description Length Principle. arXiv:2112.00848, 2021. — [arXiv:2112.00848](https://arxiv.org/abs/2112.00848) find
  22. Y. Xu, E. B. Khalil, and S. Sanner. Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus. In AAAI Conference on Artificial Intelligence, 2022. find
  23. J. Ainooson, D. Sanyal, J. P. Michelson, Y. Yang, and M. Kunda. An approach for solving tasks on the Abstract Reasoning Corpus. arXiv:2302.09425, 2023. — [arXiv:2302.09425](https://arxiv.org/abs/2302.09425) find
  24. S. Alford. A Neurosymbolic Approach to Abstraction and Reasoning. PhD thesis, Massachusetts Institute of Technology, 2021. find
  25. R. Assouel, P. Rodriguez, P. Taslakian, D. Vazquez, and Y. Bengio. Object-centric Compositional Imagination for Visual Abstract Reasoning. In ICLR Workshop on the Elements of Reasoning: Objects, Structure and Causality, 2022. find
  26. A. Moskvichev, V. V. Odouard, and M. Mitchell. The ConceptARC Benchmark: Evaluating Understanding and Generalization in the ARC Domain. arXiv:2305.07141, 2023. find
  27. V. Kolev, B. Georgiev, and S. Penkov. Neural abstract reasoner. In 4th Knowledge Representation and Reasoning Meets Machine Learning Workshop (KR2ML) at NeurIPS, 2020. find
  28. T. Paparaju. ARC Competition : EDA + PyTorch CNN. https://www.kaggle.com/code/tarunpaparaju/ arc-competition-eda-pytorch-cnn, 2022. Accessed: 2023-05-30. ↗
  29. S. Min, X. Lyu, A. Holtzman, M. Artetxe, M. Lewis, H. Hajishirzi, and L. Zettlemoyer. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? In Conference on Empirical Methods in Natural Language Processing, 2022.
  30. J. Pan, T. Gao, H. Chen, and D. Chen. What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning. In Findings of the Association for Computational Linguistics, 2023. — What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning
  31. K. Lu, A. Grover, P. Abbeel, and I. Mordatch. Pretrained transformers as universal computation engines. In AAAI Conference on Artificial Intelligence, 2022. find
  32. M. Reid, Y. Yamada, and S. S. Gu. Can wikipedia help offline reinforcement learning? In International Conference on Learning Representations (ICLR), 2023. find
  33. A. Brohan, N. Brown, J. Carbajal, Y. Chebotar, J. Dabis, C. Finn, K. Gopalakrishnan, K. Hausman, A. Herzog, J. Hsu, et al. RT-1: Robotics transformer for real-world control at scale. In Proceedings of Robotics: Science and Systems (RSS), 2022. find
  34. R. Bommasani, D. A. Hudson, E. Adeli, R. Altman, S. Arora, S. von Arx, M. S. Bernstein, J. Bohg, A. Bosselut, E. Brunskill, et al. On the opportunities and risks of foundation models. arXiv:2108.07258, 2021.
  35. S. Nair, A. Rajeswaran, V. Kumar, C. Finn, and A. Gupta. R3M: A universal visual representation for robot manipulation. In Conference on Robot Learning (CoRL), 2022. find
  36. I. Radosavovic, T. Xiao, S. James, P. Abbeel, J. Malik, and T. Darrell. Real-world robot learning with masked visual pre-training. In Conference on Robot Learning (CoRL), 2023. find
  37. S. Karamcheti, S. Nair, A. S. Chen, T. Kollar, C. Finn, D. Sadigh, and P. Liang. Language-Driven Representation Learning for Robotics. In Proceedings of Robotics: Science and Systems (RSS), 2023. find
  38. A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019. find
  39. T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, et al. Language models are few-shot learners. In Advances in Neural Information Processing Systems (NeurIPS), 2020.
  40. C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research (JMLR), 21(1):5485–5551, 2020.
  41. D. Hendrycks, X. Liu, E. Wallace, A. Dziedzic, R. Krishnan, and D. Song. Pretrained transformers improve out-of-distribution robustness. In Annual Meeting of the Association for Computational Linguistics, 2020.
  42. T. Dinh, Y. Zeng, R. Zhang, Z. Lin, M. Gira, S. Rajput, J.-y. Sohn, D. Papailiopoulos, and K. Lee. LIFT: Language-interfaced fine-tuning for non-language machine learning tasks. In Advances in Neural Information Processing Systems (NeurIPS), 2022. find
  43. S. Chan, A. Santoro, A. Lampinen, J. Wang, A. Singh, P. Richemond, J. McClelland, and F. Hill. Data distributional properties drive emergent in-context learning in transformers. In Advances in Neural Information Processing Systems (NeurIPS), 2022. find
  44. S. Garg, D. Tsipras, P. S. Liang, and G. Valiant. What can transformers learn in-context? a case study of simple function classes. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
  45. E. Akyürek, D. Schuurmans, J. Andreas, T. Ma, and D. Zhou. What learning algorithm is in-context learning? investigations with linear models. In International Conference on Learning Representations (ICLR), 2022.
  46. J. Von Oswald, E. Niklasson, E. Randazzo, J. Sacramento, A. Mordvintsev, A. Zhmoginov, and M. Vladymyrov. Transformers learn in-context by gradient descent. In International Conference on Machine Learning (ICML), 2023.
  47. L. Kirsch, J. Harrison, J. Sohl-Dickstein, and L. Metz. General-purpose in-context learning by meta-learning transformers. In Workshop on Meta-Learning at NeurIPS, 2022. find
  48. S. M. Xie, A. Raghunathan, P. Liang, and T. Ma. An explanation of in-context learning as implicit bayesian inference. In International Conference on Learning Representations (ICLR), 2022.
  49. X. Wang, W. Zhu, and W. Y. Wang. Large language models are implicitly topic models: Explaining and finding good demonstrations for in-context learning. arXiv:2301.11916, 2023.
  50. S. C. Chan, I. Dasgupta, J. Kim, D. Kumaran, A. K. Lampinen, and F. Hill. Transformers generalize differently from information stored in context vs in weights. arXiv:2210.05675, 2022. — [arXiv:2210.05675](https://arxiv.org/abs/2210.05675) find
  51. R. N. Shepard and J.-J. Chang. Stimulus generalization in the learning of classifications. Journal of Experimental Psychology, 65(1):94, 1963. find
  52. F. G. Ashby and J. T. Townsend. Varieties of perceptual independence. Psychological Review, 93(2):154, 1986. find
  53. L. Ouyang, J. Wu, X. Jiang, D. Almeida, C. Wainwright, P. Mishkin, C. Zhang, S. Agarwal, K. Slama, A. Ray, et al. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
  54. M. Chen, J. Tworek, H. Jun, Q. Yuan, H. P. d. O. Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman, et al. Evaluating large language models trained on code. arXiv:2107.03374, 2021.
  55. A. Chowdhery, S. Narang, J. Devlin, M. Bosma, G. Mishra, A. Roberts, P. Barham, H. W. Chung, C. Sutton, S. Gehrmann, et al. PaLM: Scaling language modeling with pathways. arXiv:2204.02311, 2022.
  56. R. Anil, A. M. Dai, O. Firat, M. Johnson, D. Lepikhin, A. Passos, S. Shakeri, E. Taropa, P. Bailey, Z. Chen, et al. PaLM 2 Technical Report. arXiv:2305.10403, 2023.
  57. W. Huang, F. Xia, T. Xiao, H. Chan, J. Liang, P. Florence, A. Zeng, J. Tompson, I. Mordatch, Y. Chebotar, P. Sermanet, N. Brown, T. Jackson, L. Luu, S. Levine, K. Hausman, and B. Ichter. Inner Monologue: Embodied Reasoning through Planning with Language Models. In Conference on Robot Learning (CoRL)… find
  58. A. Zeng, A. Wong, S. Welker, K. Choromanski, F. Tombari, A. Purohit, M. Ryoo, V. Sindhwani, J. Lee, V. Vanhoucke, et al. Socratic Models: Composing zero-shot multimodal reasoning with language. In International Conference on Learning Representations (ICLR), 2023.
  59. C. H. Song, J. Wu, C. Washington, B. M. Sadler, W.-L. Chao, and Y. Su. LLM-Planner: Few-shot grounded planning for embodied agents with large language models. arXiv:2212.04088, 2022.
  60. W. Huang, F. Xia, D. Shah, D. Driess, A. Zeng, Y. Lu, P. Florence, I. Mordatch, S. Levine, K. Hausman, et al. Grounded Decoding: Guiding text generation with grounded models for robot control. arXiv:2303.00855, 2023. — [arXiv:2303.00855](https://arxiv.org/abs/2303.00855) find
  61. G. Wang, Y. Xie, Y. Jiang, A. Mandlekar, C. Xiao, Y. Zhu, L. Fan, and A. Anandkumar. Voyager: An Open-Ended Embodied Agent with Large Language Models. arXiv:2305.16291, 2023. find
  62. M. Laskin, L. Wang, J. Oh, E. Parisotto, S. Spencer, R. Steigerwald, D. Strouse, S. Hansen, A. Filos, E. Brooks, et al. In-context reinforcement learning with algorithm distillation. In International Conference on Learning Representations (ICLR), 2023. find
  63. M. Xu, Y. Shen, S. Zhang, Y. Lu, D. Zhao, J. Tenenbaum, and C. Gan. Prompting decision transformer for few-shot policy generalization. In International Conference on Machine Learning (ICML), 2022. find
  64. Y. Zhang, D. Huang, B. Liu, S. Tang, Y. Lu, L. Chen, L. Bai, Q. Chu, N. Yu, and W. Ouyang. MotionGPT: Finetuned LLMs are General-Purpose Motion Generators. arXiv:2306.10900, 2023. — [arXiv:2306.10900](https://arxiv.org/abs/2306.10900) find
  65. J. N. Lee, A. Xie, A. Pacchiano, Y. Chandak, C. Finn, O. Nachum, and E. Brunskill. Supervised Pretraining Can Learn In-Context Reinforcemenet Learning. arXiv:2306.14892, 2023. — [arXiv:2306.14892](https://arxiv.org/abs/2306.14892) find
  66. T. Webb, K. J. Holyoak, and H. Lu. Emergent analogical reasoning in large language models. Nature Human Behaviour, pages 1–16, 2023. find
  67. E. Brooks, L. Walls, R. L. Lewis, and S. Singh. In-Context Policy Iteration. arXiv:2210.03821, 2022. — [arXiv:2210.03821](https://arxiv.org/abs/2210.03821) find
  68. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin. Attention is all you need. In Advances in Neural Information Processing Systems (NeurIPS), 2017.
  69. D. Zhou, N. Schärli, L. Hou, J. Wei, N. Scales, X. Wang, D. Schuurmans, O. Bousquet, Q. Le, and E. Chi. Least-to-Most Prompting Enables Complex Reasoning in Large Language Models. In International Conference on Learning Representations (ICLR), 2023.
  70. Abstraction and Rasoning Challenge 1st place solution. abstraction-and-reasoning-challenge/discussion/154597, 2020. https://www.kaggle.com/competitions/ ↗
  71. J. Su, Y. Lu, S. Pan, A. Murtadha, B. Wen, and Y. Liu. RoFormer: Enhanced Transformer with Rotary Position Embedding. arXiv:2104.09864, 2021.
  72. Y. Xu, W. Li, P. Vaezipoor, S. Sanner, and E. B. Khalil. Llms and the abstraction and reasoning corpus: Successes, failures, and the importance of object-based representations. arXiv:2305.18354, 2023.
  73. R. Wang, E. Zelikman, G. Poesia, Y. Pu, N. Haber, and N. D. Goodman. Hypothesis search: Inductive reasoning with language models. arXiv:2309.05660, 2023. find
  74. A. Srivastava, A. Rastogi, A. Rao, A. A. M. Shoeb, A. Abid, A. Fisch, A. R. Brown, A. Santoro, A. Gupta, A. Garriga-Alonso, et al. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. Transactions on Machine Learning Research (TMLR), 2022.
  75. R. Sennrich, B. Haddow, and A. Birch. Neural machine translation of rare words with subword units. In Annual Meeting of the Association for Computational Linguistics, 2015.
  76. T. Kudo and J. Richardson. SentencePiece: A simple and language independent subword tokenizer and detokenizer for neural text processing. In Conference on Empirical Methods in Natural Language Processing, 2018.
  77. D. Hupkes, V. Dankers, M. Mul, and E. Bruni. Compositionality decomposed: How do neural networks generalise? Journal of Artificial Intelligence Research (JAIR), 2020.
  78. Z. Allen-Zhu and Y. Li. Physics of Language Models: Part 1, Context-Free Grammar. arXiv:2305.13673, 2023. find
  79. E. Jang. Just Ask for Generalization. In https://evjang.com/2021/10/23/generalization.html, 2022. ↗
  80. L. Chen, K. Lu, A. Rajeswaran, K. Lee, A. Grover, M. Laskin, P. Abbeel, A. Srinivas, and I. Mordatch. Decision transformer: Reinforcement learning via sequence modeling. In Advances in Neural Information Processing Systems (NeurIPS), 2021. find
  81. F. Kaplan, P.-Y. Oudeyer, E. Kubinyi, and A. Miklósi. Robotic clicker training. Robotics and Autonomous Systems, 38(3-4):197–206, 2002. find
  82. C. Chiandetti, S. Avella, E. Fongaro, and F. Cerri. Can clicker training facilitate conditioning in dogs? Applied Animal Behaviour Science, 184:109–116, 2016. find
  83. S. Li, X. Puig, C. Paxton, Y. Du, C. Wang, L. Fan, T. Chen, D.-A. Huang, E. Akyürek, A. Anandkumar, et al. Pre-trained language models for interactive decision-making. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
  84. D. Driess, F. Xia, M. S. Sajjadi, C. Lynch, A. Chowdhery, B. Ichter, A. Wahid, J. Tompson, Q. Vuong, T. Yu, et al. PaLM-E: An embodied multimodal language model. arXiv:2303.03378, 2023. find
  85. O. Zafrir, G. Boudoukh, P. Izsak, and M. Wasserblat. Q8bert: Quantized 8bit bert. In Fifth Workshop on Energy Efficient Machine Learning and Cognitive Computing-NeurIPS Edition (EMC2-NIPS), pages 36–39. IEEE, 2019. find
  86. T. Dao, D. Fu, S. Ermon, A. Rudra, and C. Ré. Flashattention: Fast and memory-efficient exact attention with io-awareness. In Advances in Neural Information Processing Systems (NeurIPS), 2022. find
  87. F. Paischer, T. Adler, V. Patil, A. Bitto-Nemling, M. Holzleitner, S. Lehner, H. Eghbal-Zadeh, and S. Hochreiter. History compression via language models in reinforcement learning. In International Conference on Machine Learning (ICML), 2022. find
  88. K. Ellis, C. Wong, M. Nye, M. Sablé-Meyer, L. Morales, L. Hewitt, L. Cary, A. Solar-Lezama, and J. B. Tenenbaum. DreamCoder: Bootstrapping Inductive Program Synthesis with Wake-Sleep Library Learning. In ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI),… find
  89. K. Ellis, L. Morales, M. Sablé-Meyer, A. Solar-Lezama, and J. Tenenbaum. Learning libraries of subroutines for neurally–guided bayesian program induction. In Advances in Neural Information Processing Systems (NeurIPS), 2022. find
  90. M. F. Cusumano-Towner, F. A. Saad, A. K. Lew, and V. K. Mansinghka. Gen: A General-Purpose Probabilistic Programming System with Programmable Inference. In ACM SIGPLAN International Conference on Programming Language Design and Implementation (PLDI), 2019. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/mirchandani-2023-large-language-models-general-pattern/