Papers by Haichao Zhang
Generate First, Then Sample: Enhancing Fake News Detection with LLM-Augmented Reinforced Sampling (2025.acl-long)
Copied to clipboard
| Challenge: | Existing models have a performance gap of 20% between classifying fake news and real news, making them less suitable for practical deployment. |
| Approach: | They propose to adopt an LLM to generate fake news in three different styles, which are later incorporated into the training set to augment the representation of fake news. |
| Outcome: | The proposed model achieves state-of-the-art performance on two benchmark datasets and improves detection accuracy by 24.02% and 11.06% respectively. |
Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game (P18-1)
Copied to clipboard
| Challenge: | supervised language learning is limited by the ability of capturing mainly the statistics of training data. |
| Approach: | They propose to use conversational games to train agents to use new knowledge . they propose to mimic and reinforce conversational game and use it in one-shot fashion . |
| Outcome: | The proposed approach is able to acquire information by asking questions about novel objects and use the just-learned knowledge in subsequent conversations in a one-shot fashion. |
Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain adaptation paradigms for reading comprehension require large amounts of annotation data to achieve the desired task performance. |
| Approach: | They propose a few-shot domain adaptation paradigm for reading comprehension . they introduce self-attention attribution to weigh parameters and refine the lottery subnetwork . |
| Outcome: | The proposed model outperforms the full model fine-tuning adaptation on four out of five domains with a small amount of data available for adaptation. |
RLShield: Dynamic Jailbreak Detection for LLMs via Reinforced Adaptive Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to detect jailbreak prompts rely on static model components or fixed decision thresholds. |
| Approach: | They propose a dynamic jailbreak detection framework that employs reinforcement learning for adaptive threshold selection. |
| Outcome: | Experimental results show that the framework outperforms baselines in detection performance while maintaining high computational efficiency. |