6 papers
OBJECTION! Lawyer Agents Mitigate Guilty Bias in Legal Judgment Prediction
Jaehoon Jeong, Jay-Yoon Lee
Legal Judgment Prediction (LJP) models are typically trained on documents that describe facts from a prosecutorial perspective. Existing datasets further exhibit severe label imbal…
Scoring a Set, Not Summing Passage Scores: Effective and Efficient Set Retrieval
Mooho Song, Jay-Yoon Lee
Multi-hop question answering requires retrieving multiple evidence passages whose usefulness often depends on one another. Conventional retrievers either rank passages independentl…
SEAL-pose: Enhancing 3D Human Pose Estimation via a Learned Loss for Structural Consistency
Yeonsung Kim, Junggeun Do, Seunguk Do +3
3D human pose estimation (HPE) is characterized by intricate local and global dependencies among joints. Conventional supervised losses are limited in capturing these correlations…
Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks
Mooho Song, Hyeryung Son, Jay-Yoon Lee
Examining logical inconsistencies among multiple statements (such as collections of sentences or question-answer pairs) is a crucial challenge in machine learning, particularly for…
GraphCheck: Multipath Fact-Checking with Entity-Relationship Graphs
Hyewon Jeon, Jay-Yoon Lee
Automated fact-checking aims to assess the truthfulness of textual claims based on relevant evidence. However, verifying complex claims that require multi-hop reasoning remains a s…
An Analysis under a Unified Fomulation of Learning Algorithms with Output Constraints
Mooho Song, Jay-Yoon Lee
Neural networks (NN) perform well in diverse tasks, but sometimes produce nonsensical results to humans. Most NN models "solely" learn from (input, output) pairs, occasionally conf…