- The rise of large language models (LLMs) has sparked interest in coding assistants. While general purpose programming languages are well supported, generating code for domain-specific languages remains a challenging problem for LLMs. In this paper, we focus on the LLM-based generation of Answer Set Programming (ASP) code, a particularly effective approach for finding solutions to combinatorial search problems. However, the effectiveness of LLMs in ASP code generation is hindered by the limited number of examples seen during their initial pre-training phase. In this paper, we introduce a novel approach for solver-guided instruction-tuning of LLMs for addressing the highly complex semantic parsing task inherent in ASP code generation. We sample ASP statements for program continuations proposed by LLMs for unriddling logic puzzles and categorize them into chosen and rejected instances based on solver feedback. We then apply supervised fine-tuning to train LLMs on the curated data, andThe rise of large language models (LLMs) has sparked interest in coding assistants. While general purpose programming languages are well supported, generating code for domain-specific languages remains a challenging problem for LLMs. In this paper, we focus on the LLM-based generation of Answer Set Programming (ASP) code, a particularly effective approach for finding solutions to combinatorial search problems. However, the effectiveness of LLMs in ASP code generation is hindered by the limited number of examples seen during their initial pre-training phase. In this paper, we introduce a novel approach for solver-guided instruction-tuning of LLMs for addressing the highly complex semantic parsing task inherent in ASP code generation. We sample ASP statements for program continuations proposed by LLMs for unriddling logic puzzles and categorize them into chosen and rejected instances based on solver feedback. We then apply supervised fine-tuning to train LLMs on the curated data, and further improve robustness using a solver-guided search that includes best-of-N sampling. Our experiments demonstrate consistent improvements in two distinct prompting settings on different datasets.…
