4 papers
Narcissus: Program Synthesis Using Context-Aware LLM Approximations
Tilman Hinnerichs, Sebastijan Dumancic, Neil Yorke-Smith
Large language models (LLMs) excel at programming, but not when the task fixes the target language: prompted with a grammar rare in their training data, their programs usually brea…
Herb.jl: A Unifying Program Synthesis Library
Tilman Hinnerichs, Reuben Gardos Reid, Jaap de Jong +6
Program synthesis -- the automatic generation of code given a specification -- is one of the most fundamental tasks in artificial intelligence (AI) and the dream of many programmer…
Modelling Program Spaces in Program Synthesis with Constraints
Tilman Hinnerichs, Bart Swinkels, Jaap de Jong +4
A core challenge in program synthesis is taming the large space of possible programs. Since program synthesis is essentially a combinatorial search, the community has sought to lev…
Declarative Design of Neural Predicates in Neuro-Symbolic Systems
Tilman Hinnerichs, Robin Manhaeve, Giuseppe Marra +1
Neuro-symbolic systems (NeSy), which claim to combine the best of both learning and reasoning capabilities of artificial intelligence, are missing a core property of reasoning syst…