mlsanityData to 7 Oct 2026

Leveraging Language to Learn Program Abstractions and Search Heuristics

arXiv 2106.11053 ↗First posted 18 Jun 2021cs.LG cs.AI cs.CLcited by 44

Not on the map. Why?

Abstract (arXiv)

Inductive program synthesis, or inferring programs from examples of desired behavior, offers a general paradigm for building interpretable, robust, and generalizable machine learning systems. Effective program synthesis depends on two key ingredients: a strong library of functions from which to build programs, and an efficient search strategy for finding programs that solve a given task. We introduce LAPS (Language for Abstraction and Program Search), a technique for using natural language annotations to guide joint learning of libraries and neurally-guided search models for synthesis. When integrated into a state-of-the-art library learning system (DreamCoder), LAPS produces higher-quality libraries and improves search efficiency and generalization on three domains -- string editing, image composition, and abstract reasoning about scenes -- even when no natural language hints are available at test time.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). Builds on 35 of its 80 references that are in the map. First posted on arXiv 18 Jun 2021.

Builds on

35 of 80 references.

References · 35

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  4. 2019The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervisioncited by 369
  5. 2018Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understandingcited by 304
  6. 2020DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learningcited by 159
  7. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  8. 2016DeepCoder: Learning to Write Programscited by 145
  9. 2017Inferring and Executing Programs for Visual Reasoningcited by 130
  10. 2017RobustFill: Neural Program Learning under Noisy I/Ocited by 124
  11. 2016Data Recombination for Neural Semantic Parsingcited by 111
  12. 2017Building machines that adapt and compute like brainscited by 99
23 more
  1. 2018Tree-to-tree Neural Networks for Program Translationcited by 93
  2. 2019Write, Execute, Assess: Program Synthesis with a REPLcited by 92
  3. 2016Neuro-Symbolic Program Synthesiscited by 84
  4. 2019Compound Probabilistic Context-Free Grammars for Grammar Inductioncited by 76
  5. 2017Learning with Latent Languagecited by 75
  6. 2017Learning to Infer Graphics Programs from Hand-Drawn Imagescited by 73
  7. 2018Synthesizing Programs for Images using Reinforced Adversarial Learningcited by 72
  8. 2018Learning Neural Templates for Text Generationcited by 61
  9. 2019Human few-shot learning of compositional instructionscited by 47
  10. 2019Learning to Infer Program Sketchescited by 44
  11. 2015Program Synthesis using Natural Languagecited by 41
  12. 2020ALICE: Active Learning with Contrastive Natural Language Explanationscited by 36
  13. 2019Program Synthesis and Semantic Parsing with Learned Code Idiomscited by 34
  14. 2019Few-Shot Bayesian Imitation Learning with Logical Program Policiescited by 30
  15. 2020PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewardscited by 30
  16. 2019Shaping Visual Representations with Language for Few-shot Classificationcited by 27
  17. 2018Neural Program Synthesis with Priority Queue Trainingcited by 24
  18. 2020Learning abstract structure for drawing by efficient motor program inductioncited by 23
  19. 2016Learning Executable Semantic Parsers for Natural Language Understandingcited by 21
  20. 2018Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programscited by 21
  21. 2020Optimal Neural Program Synthesis from Multimodal Specificationscited by 15
  22. 2017Macro Grammars and Holistic Triggering for Efficient Semantic Parsingcited by 10
  23. 2020Benchmarking Multimodal Regex Synthesis with Complex Structurescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 14; 2023: 8; 2024: 10; 2025: 3; 2026: 5.

44 papers.

Sort:

By area:

  1. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  2. 2021Skill Induction and Planning with Latent Languagecited by 99
  3. 2024Symbolic Regression with a Learned Concept Librarycited by 76
  4. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 70
  5. 2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
  6. 2022Top-Down Synthesis for Library Learningcited by 57
  7. 2022Structured, flexible, and robust: benchmarking and improving large language models towards more human-like behavior in out-of-distribution reasoning taskscited by 56
  8. 2024What Are Tools Anyway? A Survey from the Language Model Perspectivecited by 53
  9. 2023LILO: Learning Interpretable Libraries by Compressing and Documenting Codecited by 46
  10. 2023Learning adaptive planning representations with natural language guidancecited by 36
  11. 2021Program Transfer for Answering Complex Questions over Knowledge Basescited by 34
  12. 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractionscited by 32
32 more
  1. 2024Is Programming by Example solved by LLMs?cited by 27
  2. 2022How to talk so AI will learn: Instructions, descriptions, and autonomycited by 22
  3. 2023Human-like Few-Shot Learning via Bayesian Reasoning over Natural Languagecited by 21
  4. 2022Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machinescited by 20
  5. 2022Language and Culture Internalisation for Human-Like Autotelic AIcited by 14
  6. 2023ANPL: Towards Natural Programming with Interactive Decompositioncited by 13
  7. 2024Loose LIPS Sink Ships: Asking Questions in Battleship with Language-Informed Program Samplingcited by 12
  8. 2022Identifying concept libraries from language about object structurecited by 8
  9. 2022Neurosymbolic Programming for Sciencecited by 7
  10. 2021Using Program Synthesis and Inductive Logic Programming to solve Bongard Problemscited by 6
  11. 2022LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractionscited by 5
  12. 2023Generating Language Corrections for Teaching Physical Control Taskscited by 4
  13. 2024Policy Learning with a Language Bottleneckcited by 4
  14. 2024TurtleBench: A Visual Programming Benchmark in Turtle Geometrycited by 4
  15. 2025Refactoring Codebases through Library Designcited by 4
  16. 2026Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agentscited by 4
  17. 2022lilGym: Natural Language Visual Reasoning with Reinforcement Learningcited by 3
  18. 2022SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalizationcited by 2
  19. 2023Bayesian Program Learning by Decompiling Amortized Knowledgecited by 2
  20. 2023VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answeringcited by 2
  21. 2024Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spacescited by 2
  22. 2025Self-Evolving Visual Concept Library using Vision-Language Criticscited by 2
  23. 2022ObSynth: An Interactive Synthesis System for Generating Object Models from Natural Language Specificationscited by 1
  24. 2023Learning a Hierarchical Planner from Humans in Multiple Generationscited by 1
  25. 2025Language and Experience: A Computational Model of Social Learning in Complex Taskscited by 1
  26. 2022Language-Based Causal Representation Learningcited by 0
  27. 2022Programming by Example and Text-to-Code Translation for Conversational Code Generationcited by 0
  28. 2024MathDSL: A Domain-Specific Language for Concise Mathematical Solutions Via Program Synthesiscited by 0
  29. 2026Cascaded Transfer: Learning Many Tasks under Budget Constraintscited by 0
  30. 2026Think Through a Bottleneck: Hourglass Reasoning for Rigorous Inductioncited by 0
  31. 2026SkillComposer: Learning Reusable Skills for Natural-Language Robot Programmingcited by 0
  32. 2026MatLoom: Layered Text-to-Material Generation in a Compact Program Spacecited by 0