The authors create a novel dataset and show that fine-tuned small open-weight LLMs can translate natural language to ATL/ATL* specifications with semantic accuracy (0.84) statistically matching strong few-shot proprietary baselines (0.86).
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Value Coalition Logic reconstructs coalition logic with typed value assignments to states, proves truth-equivalence to the standard logic over coherent valuations, and derives new structural game forms from value projections.
citing papers explorer
-
Translating Natural Language to Strategic Temporal Specifications via LLMs
The authors create a novel dataset and show that fine-tuned small open-weight LLMs can translate natural language to ATL/ATL* specifications with semantic accuracy (0.84) statistically matching strong few-shot proprietary baselines (0.86).