Papers by Mooho Song
An Analysis under a Unified Formulation of Learning Algorithms with Output Constraints (2024.acl-srw)
Copied to clipboard
| Challenge: | Existing work on NN models with output constraints has not been able to categorize them in a unified manner. |
| Approach: | They propose new algorithms to integrate the information of main task and constraint injection . they use the H-score as a metric for considering main task metric and constrain infringement simultaneously . |
| Outcome: | The proposed algorithms integrate the information of main task and constraint injection, inspired by continual-learning algorithms. |
Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks (2025.acl-long)
Copied to clipboard
| Challenge: | Traditional methods that rely on 1:1 pairwise comparisons fail to capture inconsistencies . few studies have addressed related problems in the domain of factual inconsistenency detection . |
| Approach: | They propose a set-consistency verification task that assesses logical coherence of entire sets . they propose 'set-consistent energy network' that employs a margin-based loss to learn the compatibility among a collection of statements . |
| Outcome: | The proposed model outperforms existing methods and significantly outperformed existing models. |