Patat: Human-ai collaborative qualitative coding with explainable interactive rule synthesis

SA Gebreegziabher, Z Zhang, X Tang, Y Meng… - Proceedings of the …, 2023 - dl.acm.org
Over the years, the task of AI-assisted data annotation has seen remarkable advancements.
However, a specific type of annotation task, the qualitative coding performed during thematic …

Hypothesis search: Inductive reasoning with language models

R Wang, E Zelikman, G Poesia, Y Pu, N Haber… - arXiv preprint arXiv …, 2023 - arxiv.org
Inductive reasoning is a core problem-solving capacity: humans can identify underlying
principles from a few examples, which can then be robustly generalized to novel scenarios …

Interactive code generation via test-driven user-intent formalization

SK Lahiri, S Fakhoury, A Naik, G Sakkas… - arXiv preprint arXiv …, 2022 - arxiv.org
Large language models (LLMs) have shown great potential in automating significant
aspects of coding by producing natural code from informal natural language (NL) intent …

Question selection for interactive program synthesis

R Ji, J Liang, Y Xiong, L Zhang, Z Hu - Proceedings of the 41st ACM …, 2020 - dl.acm.org
Interactive program synthesis aims to solve the ambiguity in specifications, and selecting the
proper question to minimize the rounds of interactions is critical to the performance of …

Feedback-driven semi-supervised synthesis of program transformations

X Gao, S Barke, A Radhakrishna, G Soares… - Proceedings of the …, 2020 - dl.acm.org
While editing code, it is common for developers to make multiple related repeated edits that
are all instances of a more general program transformation. Since this process can be …

Perfect is the enemy of good: Best-effort program synthesis

H Peleg, N Polikarpova - 34th European Conference on Object …, 2020 - drops.dagstuhl.de
Program synthesis promises to help software developers with everyday tasks by generating
code snippets automatically from input-output examples and other high-level specifications …

LLM-based Test-driven Interactive Code Generation: User Study and Empirical Evaluation

S Fakhoury, A Naik, G Sakkas, S Chakraborty… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) have shown great potential in automating significant
aspects of coding by producing natural code from informal natural language (NL) intent …

Fast and reliable program synthesis via user interaction

Y Chen, C Wang, X Wang, O Bastani… - 2023 38th IEEE/ACM …, 2023 - ieeexplore.ieee.org
The performance of programming-by-example systems varies significantly across different
tasks and even across different examples in one task. The key issue is that the search space …

Example-guided synthesis of relational queries

A Thakkar, A Naik, N Sands, R Alur, M Naik… - Proceedings of the …, 2021 - dl.acm.org
Program synthesis tasks are commonly specified via input-output examples. Existing
enumerative techniques for such tasks are primarily guided by program syntax and only …

Assuage: Assembly synthesis using a guided exploration

J Hu, P Vaithilingam, S Chong, M Seltzer… - The 34th Annual ACM …, 2021 - dl.acm.org
Assembly programming is challenging, even for experts. Program synthesis, as an
alternative to manual implementation, has the potential to enable both expert and non …