Search Results for author:
Found 6 papers, 4 papers with code
Case-Based or Rule-Based: How Do Transformers Do the Math?
Through carefully designed intervention experiments on five math tasks, we confirm that transformers are performing case-based reasoning, no matter whether scratchpad is used, which aligns with the previous observations that transformers use subgraph matching/shortcut learning to reason.
Chain of Images for Intuitively Reasoning
The human brain is naturally equipped to comprehend and interpret visual information rapidly.
Parrot Mind: Towards Explaining the Complex Task Reasoning of Pretrained Large Language Models with Template-Content Structure
Furthermore, by generalizing this structure to the hierarchical case, we demonstrate that models can achieve task composition, further reducing the space needed to learn from linear to logarithmic, thereby effectively learning on complex reasoning involving multiple steps.
Code Prompting: a Neural Symbolic Method for Complex Reasoning in Large Language Models
We also consider the ensemble of code prompting and CoT prompting to combine the strengths of both.
Neural Common Neighbor with Completion for Link Prediction
Despite its outstanding performance in various graph tasks, vanilla Message Passing Neural Network (MPNN) usually fails in link prediction tasks, as it only uses representations of two individual target nodes and ignores the pairwise relation between them.
Ranked #1 on
Link Property Prediction
on ogbl-ddi
Rethinking Knowledge Graph Evaluation Under the Open-World Assumption
However, evaluation of knowledge graph completion (KGC) models often ignores the incompleteness -- facts in the test set are ranked against all unknown triplets which may contain a large number of missing facts not included in the KG yet.
