A meta-level neuro-symbolic layer uses LLMs to synthesize, consolidate, and verify minimal necessary-and-sufficient first-order causal rules from human-specified goals and principles, demonstrated in two autonomous-driving proof-of-concept scenarios.
InProceedings of the IEEE/ACM 15th International Symposium on Software Engineering for Adaptive and Self-Managing Systems(Seoul, Republic of Korea) (SEAMS ’20)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LO 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Towards Neuro-symbolic Causal Rule Synthesis, Verification, and Evaluation Grounded in Legal and Safety Principles
A meta-level neuro-symbolic layer uses LLMs to synthesize, consolidate, and verify minimal necessary-and-sufficient first-order causal rules from human-specified goals and principles, demonstrated in two autonomous-driving proof-of-concept scenarios.