Explaining Hitori Puzzles: Neurosymbolic Proof Staging for Sequential Decisions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913998178353152 |
|---|---|
| author | Pacheco, Maria Leonor Somenzi, Fabio Srinivas, Dananjay Trivedi, Ashutosh |
| author_facet | Pacheco, Maria Leonor Somenzi, Fabio Srinivas, Dananjay Trivedi, Ashutosh |
| contents | We propose a neurosymbolic approach to the explanation of complex sequences of decisions that combines the strengths of decision procedures and Large Language Models (LLMs). We demonstrate this approach by producing explanations for the solutions of Hitori puzzles. The rules of Hitori include local constraints that are effectively explained by short resolution proofs. However, they also include a connectivity constraint that is more suitable for visual explanations. Hence, Hitori provides an excellent testing ground for a flexible combination of SAT solvers and LLMs. We have implemented a tool that assists humans in solving Hitori puzzles, and we present experimental evidence of its effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14294 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explaining Hitori Puzzles: Neurosymbolic Proof Staging for Sequential Decisions Pacheco, Maria Leonor Somenzi, Fabio Srinivas, Dananjay Trivedi, Ashutosh Artificial Intelligence We propose a neurosymbolic approach to the explanation of complex sequences of decisions that combines the strengths of decision procedures and Large Language Models (LLMs). We demonstrate this approach by producing explanations for the solutions of Hitori puzzles. The rules of Hitori include local constraints that are effectively explained by short resolution proofs. However, they also include a connectivity constraint that is more suitable for visual explanations. Hence, Hitori provides an excellent testing ground for a flexible combination of SAT solvers and LLMs. We have implemented a tool that assists humans in solving Hitori puzzles, and we present experimental evidence of its effectiveness. |
| title | Explaining Hitori Puzzles: Neurosymbolic Proof Staging for Sequential Decisions |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.14294 |