Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction
Not on the map. Why?
Abstract (arXiv)
Historical linguists have long written "programs" that convert reconstructed words in an ancestor language into their attested descendants via ordered string rewrite functions (called sound laws) However, writing these programs is time-consuming, motivating the development of automated Sound Law Induction (SLI) which we formulate as Programming by Examples (PBE) with Large Language Models (LLMs) in this paper. While LLMs have been effective for code generation, recent work has shown that PBE is challenging but improvable by fine-tuning, especially with training data drawn from the same distribution as evaluation data. In this paper, we create a conceptual framework of what constitutes a "similar distribution" for SLI and propose four kinds of synthetic data generation methods with varying amounts of inductive bias to investigate what leads to the best performance. Based on the results we create a SOTA open-source model for SLI as PBE (+6% pass rate with a third of the parameters of the second-best LLM) and also highlight exciting future directions for PBE research.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 27 Jan 2025.
Builds on
16 of 45 references.
References · 16
- 2023GPT-4 Technical Reportcited by 18,132
- 2021Evaluating Large Language Models Trained on Codecited by 8,053
- 2021Program Synthesis with Large Language Modelscited by 3,509
- 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
- 2024Qwen2.5-Coder Technical Reportcited by 1,151
- 2023Magicoder: Empowering Code Generation with OSS-Instructcited by 251
- 2021Jigsaw: Large Language Models meet Program Synthesiscited by 103
- 2022Interactive Code Generation via Test-Driven User-Intent Formalizationcited by 50
- 2024Is Programming by Example solved by LLMs?cited by 27
- 2023ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesiscited by 17
- 2020Optimal Neural Program Synthesis from Multimodal Specificationscited by 15
- 2024Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasonscited by 13
4 more
- 2024The First Prompt Counts the Most! An Evaluation of Large Language Models on Iterative Example-Based Code Generationcited by 7
- 2024Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMscited by 5
- 2021Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problemscited by 4
- 2024Automating Sound Change Prediction for Phylogenetic Inference: A Tukanoan Case Studycited by 4
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.