17 citations · 20 across the 23 of their papers we have counts for
8 papers · 1 filter
RolloutFaith: Auditing Persistent Internal Interventions in Visual World Model
Junchi Yao, Ziyi Wang, Youling Huang +1
Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World models pose a harder requireme…
SharedSAE: One Feature Dictionary Across Language Models
Daniil Ognev, Célian Vasson, Lijie Hu +2
Sparse autoencoders (SAEs) are widely used to interpret language model activations, but SAE training and latent labelling are typically repeated for every model. Here, we show that…
Matryoshka Concept Bottleneck Models
Ziye Chen, Hongbin Lin, Jie Li +1
Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-understandable concepts. However,…
Understanding Generalization and Forgetting in In-Context Continual Learning
Guangyu Li, Meng Ding, Lijie Hu
In-context learning (ICL) derives its power from enabling Large Language Models to adapt to new tasks via prompt-based reasoning alone, entirely bypassing the need for parameter up…
From Instance Selection to Fixed-Pool Data Recipe Search for Supervised Fine-Tuning
Haodong Wu, Jiahao Zhang, Lijie Hu +1
Supervised fine-tuning (SFT) data selection is commonly formulated as instance ranking: score each example and retain a top- subset. However, effective SFT training subsets are…
In-Context Learning Operates as Concept Subspace Learning
Wei Tang, Xinyan Jiang, Fakhri Karray +1
Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directi…
When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection
Zhengyu Hu, Zheyuan Xiao, Linxin Song +10
LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the high…
Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era
Xuansheng Wu, Haiyan Zhao, Yaochen Zhu +9
Explainable AI (XAI) refers to techniques that provide human-understandable insights into the workings of AI models. Recently, the focus of XAI is being extended toward explaining…