Compositional generalization for multi-label text classification: A data-augmentation approach

Y Chai, Z Li, J Liu, L Chen, F Li, D Ji… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Despite significant advancements in multi-label text classification, the ability of existing
models to generalize to novel and seldom-encountered complex concepts, which are …

Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models

S Liu, H Dai, Y Zhao, P Liu - arXiv preprint arXiv:2406.02066, 2024 - arxiv.org
Molecule synthesis through machine learning is one of the fundamental problems in drug
discovery. Current data-driven strategies employ one-step retrosynthesis models and search …

Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach

Z Li, L Haroutunian, R Tumuluri, P Cohen… - arXiv preprint arXiv …, 2024 - arxiv.org
Post-editing has proven effective in improving the quality of text generated by large
language models (LLMs) such as GPT-3.5 or GPT-4, particularly when direct updating of …