INK Lab @ USC's repositories
TriggerNER
TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition (ACL 2020)
NumerSense
The data and code for NumerSense (EMNLP2020)
sparse-distillation
Code for "Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models"
entity-robustness
Code and data for paper "On the Robustness of Reading Comprehension Models to Entity Renaming" (NAACL'22)
RationaleHumanUtility
Codebase for Human Utility of FTRs at ACL 2023
RationaleMultiRewardDistillation
Code and Dataset for preprint titled "Tailoring Self-Rationalizers with Multi-Reward Distillation"
CrossTaskMoE
Code for paper "Eliciting and Understanding Cross-task Skills with Task-level Mixture-of-Experts" (Findings of EMNLP 2022)
ink-usc.github.io
INK Research Lab Website
predicting-big-bench
Code for paper "How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench"