Patat: Human-ai collaborative qualitative coding with explainable interactive rule synthesis
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 …
However, a specific type of annotation task, the qualitative coding performed during thematic …
Hypothesis search: Inductive reasoning with language models
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 …
principles from a few examples, which can then be robustly generalized to novel scenarios …
Interactive code generation via test-driven user-intent formalization
Large language models (LLMs) have shown great potential in automating significant
aspects of coding by producing natural code from informal natural language (NL) intent …
aspects of coding by producing natural code from informal natural language (NL) intent …
Question selection for interactive program synthesis
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 …
proper question to minimize the rounds of interactions is critical to the performance of …
Feedback-driven semi-supervised synthesis of program transformations
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 …
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 …
code snippets automatically from input-output examples and other high-level specifications …
LLM-based Test-driven Interactive Code Generation: User Study and Empirical Evaluation
Large language models (LLMs) have shown great potential in automating significant
aspects of coding by producing natural code from informal natural language (NL) intent …
aspects of coding by producing natural code from informal natural language (NL) intent …
Fast and reliable program synthesis via user interaction
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 …
tasks and even across different examples in one task. The key issue is that the search space …
Example-guided synthesis of relational queries
Program synthesis tasks are commonly specified via input-output examples. Existing
enumerative techniques for such tasks are primarily guided by program syntax and only …
enumerative techniques for such tasks are primarily guided by program syntax and only …
Assuage: Assembly synthesis using a guided exploration
Assembly programming is challenging, even for experts. Program synthesis, as an
alternative to manual implementation, has the potential to enable both expert and non …
alternative to manual implementation, has the potential to enable both expert and non …