Papers by Shaojie Wang
Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | federated learning (FL) fine-tunes large language models with local data, but organizations are reluctant to share local data. |
| Approach: | They propose a framework for fine-tuning large language models with local data . they propose centralized fine- tuning with local datasets is a good idea . |
| Outcome: | The proposed framework allows clients to retain local data while sharing only model parameters for training. |
A Lifelong Multilingual Multi-granularity Semantic Alignment Approach via Maximum Co-occurrence Probability (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to mask and predict tokens in multilingual text limit multilingual interaction . |
| Approach: | They propose a lifelong multilingual multi-granularity semantic alignment approach which continuously extracts massive aligned linguistic units from noisy data via a maximum co-occurrence probability algorithm. |
| Outcome: | The proposed approach improves translation performance on WMT14 18 benchmarks in twelve directions. |
From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent studies reveal large language models lack logical reasoning abilities . logical relationship understanding is a core capability underlying genuine logical thinking . |
| Approach: | They propose a lightweight training framework targeting logical relationship understanding . they propose logical relation understanding framework that provides explicit supervision . |
| Outcome: | The proposed framework outperforms CoT-SFT training frameworks in logical relationship understanding tasks. |