Papers by Shun Shao
Sparse Activation Editing for Reliable Instruction Following in Narratives (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks fail to capture the challenges of instruction following in complex narrative contexts. |
| Approach: | They propose a training-free framework that identifies and edits instruction-relevant neurons using only natural language instructions without requiring labelled data. |
| Outcome: | The proposed framework improves instruction following by identifying and editing instruction-relevant neurons using only natural language instructions, without requiring labelled data. |
Gold Doesn’t Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information (2023.eacl-main)
Copied to clipboard
| Challenge: | Spectral Attribute removaL is a method to remove private or guarded information from neural representations. |
| Approach: | They propose a method to remove guarded or private information from neural representations by matrix decomposition. |
| Outcome: | The proposed method retains better main task performance after removing guarded information compared to previous work. |
SEEK: Segmented Embedding of Knowledge Graphs (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for knowledge graph embedding can not make a proper trade-off between the model complexity and the model expressiveness, which makes them far from satisfactory. |
| Approach: | They propose a lightweight modeling framework that can achieve highly competitive relational expressiveness without increasing the model complexity. |
| Outcome: | The proposed framework can achieve highly competitive relational expressiveness without increasing model complexity. |
Erasure of Unaligned Attributes from Neural Representations (2023.tacl-1)
Copied to clipboard
| Challenge: | Developing a methodology for adjusting neural representations to preserve user privacy and avoid encoding bias in them is an active area of research in recent years. |
| Approach: | They propose an algorithm which erases information from neural representations when the information to be erased is implicit rather than directly aligned to each input example. |
| Outcome: | The proposed algorithm erases information from neural representations when the information to be erased is implicit rather than directly aligned to each input example. |
Iterative Multilingual Spectral Attribute Erasure (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for debiasing are unable to exploit this opportunity because they operate on individual languages. |
| Approach: | They propose to iterate multilingual spectral attribute error (IMSAE) to mitigate joint bias subspaces across multiple languages through iterative SVD-based truncation. |
| Outcome: | The proposed method outperforms monolingual and cross-lingual approaches while maintaining model utility. |