Papers by Xuansheng Wu
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) can disentangle complex features into more interpretable components. |
| Approach: | They propose to use Sparse Autoencoders to disentangle LLM features into more interpretable components. |
| Outcome: | The proposed method disentangles complex features into more interpretable components. |
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning (2024.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved remarkable success in aligning with user intentions. |
| Approach: | They develop local and global explanation methods and a feed-forward-based method for input-output attribution to investigate the impact of instruction tuning on user intentions. |
| Outcome: | The proposed method compares explanations from pre-trained and instruction-tuned models . it empowers LLMs to recognize the instruction parts of user prompts, it encourages response generation . |
InFoBench: Evaluating Instruction Following Ability in Large Language Models (2024.findings-acl)
Copied to clipboard
Yiwei Qin, Kaiqiang Song, Yebowen Hu, Wenlin Yao, Sangwoo Cho, Xiaoyang Wang, Xuansheng Wu, Fei Liu, Pengfei Liu, Dong Yu
| Challenge: | Existing methods for evaluating Large Language Models (LLMs) ability to follow instructions have not been able to provide a detailed analysis of their compliance with instructions. |
| Approach: | They propose a new metric for evaluating Large Language Models' ability to follow instructions and a benchmark for DRFR. |
| Outcome: | The proposed metric and benchmark compared with traditional scoring methods and explores annotation sources including human experts, crowd-sourced workers, and GPT-4. |
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders (2025.emnlp-main)
Copied to clipboard
| Challenge: | Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). |
| Approach: | They propose a method that identifies the most influential latents by incorporating output-side gradient information. |
| Outcome: | The proposed method identifies the most influential latents by incorporating output-side gradient information. |
LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models (2025.findings-naacl)
Copied to clipboard
Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Ninghao Liu, Yih Chung Tham, Xiuzhen Zhang, Qingyu Chen
| Challenge: | Existing benchmarks for large vision-language models (LVLMs) are limited to ophthalmology-specific applications. |
| Approach: | They introduce a large-scale multimodal ophthalmology benchmark consisting of 21,993 instances across five ocular imaging modalities and 13 state-of-the-art LVLM representatives from closed-source, open-source and medical domains. |
| Outcome: | The proposed model shows significant performance drop in ophthalmology compared to other domains. |
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for steering concept vectors suffer from noisy features in diverse datasets that undermine steering robustness. |
| Approach: | They propose a Sparse Autoencoder-Denoised Concept Vector (SDCV) which selectively keeps the most discriminative SAE latents while reconstructing hidden representations. |
| Outcome: | The proposed method improves steering success rates by 4-16% across six challenging concepts while maintaining topic relevance. |