Understanding and Patching Compositional Reasoning in LLMs Z Li, G Jiang, H Xie, L Song, D Lian, Y Wei ACL 2024 Findings, 2024 | 7 | 2024 |
Learning to Substitute Spans towards Improving Compositional Generalization Z Li, Y Wei, D Lian ACL 2023 1, 2791–2811, 2023 | 6 | 2023 |
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation T Zhong*, Z Li*, Q Wang, L Song, Y Wei, D Lian, Z Mao ACL 2024, co-first authorship, 2024 | 1 | 2024 |
Invariant Representation Learning via Decoupling Style and Spurious Features R Li, Y Pu, Z Li, H Xie, D Lian arXiv preprint arXiv:2312.06226, 2023 | 1 | 2023 |
Interpretable Catastrophic Forgetting of Large Language Model Fine-tuning via Instruction Vector G Jiang, Z Li, C Jiang, S Xue, J Zhou, L Song, D Lian, Y Wei arXiv preprint arXiv:2406.12227, 2024 | | 2024 |