LUKA Lab @ UC Davis & USC

Lattice

[NAACL 2022] Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning.

SuRE

[EMNLP 2022] Summarization as Indirect Supervision for Relation Extraction (SuRE)

lite

This is the repository for the resources in TACL 2022 Paper "Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference".

NLI_as_Indirect_Supervision

Official Implementation for "Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?" ACL 2023

PASTA

This is the code for Parameter-efficient Tuning with Special Token Adaptation.

MrCoD

Multi-hop Evidence Retrieval for Cross-document Relation Extraction

Salience-aware-Learning

[EMNLP 2021] Table-based Fact Verification with Salience-aware Learning.

UniST

[NAACL 2022] Unified Semantic Typing with Meaningful Label Inference

prix-lm

Prix-LM: Pretraining for Multilingual Knowledge Base Construction @ACL 2022

CoIN

READ

[ACL 2023] Robust Natural Language Understanding with Residual Attention Debiasing

PInKS

This is a code repository for PInKS(Preconditioned Commonsense Inference with Minimal Supervision) @AACL-IJCNLP 2022

DDR

Delta-Unlearning

DiagnoseET

Codes for paper "Does Your Model Classify Entities Reasonably? Diagnosing and Mitigating Spurious Correlations in Entity Typing"

Causal-View-of-Entity-Bias

[EMNLP 2023] A Causal View of Entity Bias in (Large) Language Models

CognitiveOverload

Code for our NAACL 2024 Paper "Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking"

DPoE

PaCo

This is a code repository for PaCo (Preconditions Attributed to Commonsense Knowledge) @EMNLP-Findings 2022

SALT

luka-group.github.io

ODDA-Data-Augmentation

Codes and data for the EACL 2024 Findings paper: On-the-fly Denoising for Data Augmentation in Natural Language Understanding.

ViPhy

[EMNLP 2023] VIPHY: Probing “Visible” Physical Commonsense Knowledge