3 articles tagged with #first-order-logic. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers introduce LGMT, a novel testing framework that uses first-order logic to evaluate Large Language Models' reasoning reliability by creating logically equivalent test cases. The study reveals that state-of-the-art LLMs fail consistency checks under semantic transformations, exposing hidden reasoning defects that traditional benchmarks miss.
Researchers have developed a parallel lifted planning algorithm using semi-naive Datalog evaluation that significantly accelerates classical AI planning by combining rule-level and grounding-level parallelism. The approach achieves up to 6-fold speedup on 8 cores and solves more planning tasks than existing baselines, particularly on computationally intensive grounding operations.
Researchers propose RLJP, a new framework for Legal Judgment Prediction that combines first-order logic rules with large language models to improve AI-based legal decision making. The system uses a three-stage approach including Confusion-aware Contrastive Learning to dynamically optimize judgment rules and showed superior performance on public datasets.
