Xiaomeng Hu


2025

pdf bib
ALPS: Attention Localization and Pruning Strategy for Efficient Adaptation of Large Language Models
Hao Chen | Haoze Li | Zhiqing Xiao | Lirong Gao | Qi Zhang | Xiaomeng Hu | Ningtao Wang | Xing Fu | Junbo Zhao
Findings of the Association for Computational Linguistics: ACL 2025

Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data training or data-driven activations to identify key attention heads. However, these approaches inherently introduce data dependency, which hinders generalization and reusability. To address this issue and enhance model alignment efficiency, we propose the Attention Localization and Pruning Strategy ALPS, an efficient algorithm that localizes the most task-sensitive attention heads and prunes by restricting attention training updates to these heads, thereby reducing alignment costs. Experimental results demonstrate that our method activates only 10% of attention parameters during fine-tuning while achieving a 2% performance improvement over baselines on three tasks. Moreover, the identified task-specific heads are transferable across datasets and mitigate knowledge forgetting. Our work and findings provide a novel perspective on efficient LLM alignment.

2024

pdf bib
Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection
Xiaomeng Hu | Yiming Zhang | Ru Peng | Haozhe Zhang | Chenwei Wu | Gang Chen | Junbo Zhao
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

In recent years, large language models (LLMs) have achieved remarkable success in the field of natural language generation. Compared to previous small-scale models, they are capable of generating fluent output based on the provided prefix or prompt. However, one critical challenge — the *hallucination* problem — remains to be resolved. Generally, the community refers to the undetected hallucination scenario where the LLMs generate text unrelated to the input text or facts. In this study, we intend to model the distributional distance between the regular conditional output and the unconditional output, which is generated without a given input text. Based upon Taylor Expansion for this distance at the output probability space, our approach manages to leverage the embedding and first-order gradient information. The resulting approach is plug-and-play that can be easily adapted to any autoregressive LLM. On the hallucination benchmarks HADES and other datasets, our approach achieves state-of-the-art performance.