Papers by Meiqi Guo
Inflating Topic Relevance with Ideology: A Case Study of Political Ideology Bias in Social Topic Detection Models (2020.coling-main)
Copied to clipboard
| Challenge: | a study examines the impact of political ideology biases in training data . topic detection methods may contain or propagate certain biase resulting in a skewed data collection . |
| Approach: | They propose to learn a text representation that is invariant to political ideology while still judging topic relevance. |
| Outcome: | The proposed model can be invariant to political ideology while still judging topic relevance. |
MoDE: Effective Multi-task Parameter Efficient Fine-Tuning with a Mixture of Dyadic Experts (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent efforts have explored mixtures of LoRA modules for multi-task settings, but this study reveals redundancy in the down-projection matrix of these architectures. |
| Approach: | They propose a method to share down-projection matrix across tasks and employ atomic rank-one adapters coupled with routers that allow more sophisticated task-level specialization. |
| Outcome: | The proposed method outperforms state-of-the-art models on a SNI benchmark and provides a practical solution for deploying lightweight models. |
Decoding Symbolism in Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing language models can be used to decode symbolism, but they are biased in pre-trained corpora. |
| Approach: | They propose to use language models to decode symbols by re-ranking pre-trained models. |
| Outcome: | The proposed framework shows that pre-trained models can mitigate the bias and improve performance to be on par with human models. |