Papers by Xiaolin Hu
Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. |
| Approach: | They propose a methodology that embeds harmful requests within ethical framings to exploit this vulnerability. |
| Outcome: | The proposed framework achieves high success rates by exploiting model's own ethical reasoning to frame harmful actions as morally necessary compromises. |
PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning (2025.coling-main)
Copied to clipboard
| Challenge: | Low-rank adaptation and its variants have been popular due to their ability to avoid excessive inference costs. |
| Approach: | They propose a low-rank adaptation method that enables high-rank updates with low costs while leveraging semantic and linguistic information inherent in pre-trained weight. |
| Outcome: | The proposed method outperforms LoRA and other fine-tuning methods across tasks with less trainable parameters. |
Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to short text clustering are prone to degenerate solutions and noisy data. |
| Approach: | They propose a model to improve robustness against imbalanced and noisy data . they propose self-adaptive optimal transport and class-wise contrastive learning . |
| Outcome: | The proposed model outperforms the state-of-the-art models on eight short text clustering datasets. |