Shuoran Jiang
2024
Linguistic Rule Induction Improves Adversarial and OOD Robustness in Large Language Models
Shuoran Jiang
|
Qingcai Chen
|
Yang Xiang
|
Youcheng Pan
|
Yukang Lin
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Ensuring robustness is especially important when AI is deployed in responsible or safety-critical environments. ChatGPT can perform brilliantly in both adversarial and out-of-distribution (OOD) robustness, while other popular large language models (LLMs), like LLaMA-2, ERNIE and ChatGLM, do not perform satisfactorily in this regard. Therefore, it is valuable to study what efforts play essential roles in ChatGPT, and how to transfer these efforts to other LLMs. This paper experimentally finds that linguistic rule induction is the foundation for identifying the cause-effect relationships in LLMs. For LLMs, accurately processing the cause-effect relationships improves its adversarial and OOD robustness. Furthermore, we explore a low-cost way for aligning LLMs with linguistic rules. Specifically, we constructed a linguistic rule instruction dataset to fine-tune LLMs. To further energize LLMs for reasoning step-by-step with the linguistic rule, we construct the task-relevant LingR-based chain-of-thoughts. Experiments showed that LingR-induced LLaMA-13B achieves comparable or better results with GPT-3.5 and GPT-4 on various adversarial and OOD robustness evaluations.
2021
Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning
Shuoran Jiang
|
Qingcai Chen
|
Xin Liu
|
Baotian Hu
|
Lisai Zhang
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Graph convolutional network (GCN) has become popular in various natural language processing (NLP) tasks with its superiority in long-term and non-consecutive word interactions. However, existing single-hop graph reasoning in GCN may miss some important non-consecutive dependencies. In this study, we define the spectral graph convolutional network with the high-order dynamic Chebyshev approximation (HDGCN), which augments the multi-hop graph reasoning by fusing messages aggregated from direct and long-term dependencies into one convolutional layer. To alleviate the over-smoothing in high-order Chebyshev approximation, a multi-vote-based cross-attention (MVCAttn) with linear computation complexity is also proposed. The empirical results on four transductive and inductive NLP tasks and the ablation study verify the efficacy of the proposed model.
Search
Co-authors
- Qingcai Chen 2
- Yang Xiang 1
- Youcheng Pan 1
- Yukang Lin 1
- Xin Liu 1
- show all...