INK Lab @ USC

AlpacaTag

AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging (ACL 2019 Demo)

CommonGen

A Constrained Text Generation Challenge Towards Generative Commonsense Reasoning

CrossFit

Code for paper "CrossFit :weight_lifting:: A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)

DIG

Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)

KagNet

Knowledge-Aware Graph Networks for Commonsense Reasoning (EMNLP-IJCNLP 19)

MHGRN

Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (EMNLP 2020)

RE-Net

Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs (EMNLP 2020)

RICA

TriggerNER

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition (ACL 2020)

USC-DS-RelationExtraction

Distantly Supervised Relation Extraction

INK-USC/TriggerNER

TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition (ACL 2020)

INK-USC/CommonGen

A Constrained Text Generation Challenge Towards Generative Commonsense Reasoning

INK-USC/AlpacaTag

AlpacaTag: An Active Learning-based Crowd Annotation Framework for Sequence Tagging (ACL 2019 Demo)

INK-USC/CPL

Collaborative Policy Learning for Open Knowledge Graph Reasoning (EMNLP 2019)

INK-USC/VisCOLL

Code and data for the project "Visually grounded continual learning of compositional semantics"

INK-USC/NumerSense

The data and code for NumerSense (EMNLP2020)

INK-USC/GMED

Source code for "Gradient Based Memory Editing for Task-Free Continual Learning", 4th Lifelong ML Workshop@ICML 2020

INK-USC/HGN

Learning Contextualized Knowledge Structures for Commonsense Reasoning

INK-USC/SalKG

This is the official PyTorch implementation of our NeurIPS 2021 paper: "SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning"

INK-USC/FiD-ICL

"FiD-ICL: A Fusion-in-Decoder Approach for Efficient In-Context Learning" (ACL 2023)

INK-USC/entity-robustness

Code and data for paper "On the Robustness of Reading Comprehension Models to Entity Renaming" (NAACL'22)

INK-USC/Reflect

Data and Code for Paper "Reflect Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality" (EMNLP 2022)

INK-USC/BITE

Code and data for paper "BITE: Textual Backdoor Attacks with Iterative Trigger Injection"

INK-USC/G-PlanET

INK-USC/RobustLR

A Diagnostic Benchmark for Evaluating Logical Robustness of Deductive Reasoners

INK-USC/XMD

XMD: An End-to-End Framework for Interactive Explanation-Based Debugging of NLP Models

INK-USC/Lifelong-ICL

Code for paper "Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack"

INK-USC/LINK

Code for EMNLP 2024 paper "In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search"

INK-USC/RationaleMultiRewardDistillation

Code and Dataset for preprint titled "Tailoring Self-Rationalizers with Multi-Reward Distillation"

INK-USC/PE2

Code for paper "Prompt Engineering a Prompt Engineer" (https://arxiv.org/abs/2311.05661)

INK-USC/RationaleHumanUtility

Codebase for Human Utility of FTRs at ACL 2023

INK-USC/ER-Test

Code for ER-Test, accepted to the Findings of EMNLP 2022

INK-USC/CrossTaskMoE

Code for paper "Eliciting and Understanding Cross-task Skills with Task-level Mixture-of-Experts" (Findings of EMNLP 2022)

INK-USC/ink-usc.github.io

INK Research Lab Website

INK-USC/predicting-big-bench

Code for paper "How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench"

INK-USC/Controllable-AV-Explanations

INK-USC/lm-forgetting-prediction-code

INK-USC/RICA

INK-USC/llicl-data

Data for Lifelong ICL and Task Haystack (https://arxiv.org/abs/2407.16695)

INK-USC/lm-forgetting-prediction