ZonglinY/PrimeNet_nouns

MOOSE

Official implementation for <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>, accepted by ACL 2024.

LRNL-bench

The Logical Reasoning over Natural Language as Knowledge Representation Benchmark (LRNL-bench) is a collaborative benchmark intended to promote a comprehensive evaluation on the three sub-reasoning aspects of logical reasoning (the three aspects are deductive reasoning, inductive reasoning, and abductive reasoning).

Inductive_Reasoning

Official implementation for <Language Models as Inductive Reasoners>, accepted by EACL 2024.

ECBRF_Case_Based_Reasoning_with_PLM

Official implementation for <End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion>, accepted by EACL 2023 (oral).

Improving-Event-Duration-Prediction-via-Time-aware-Pre-training