40 citations · 120 across the 25 of their papers we have counts for
5 papers · 2 filters
SAGE: An Agentic Explainer Framework for Interpreting SAE Features in Language Models
Jiaojiao Han, Wujiang Xu, Mingyu Jin +1
Large language models (LLMs) have achieved remarkable progress, yet their internal mechanisms remain largely opaque, posing a significant challenge to their safe and reliable deplo…
Rep2Text: Decoding Full Text from a Single LLM Token Representation
Haiyan Zhao, Zirui He, Yiming Tang +4
Large language models represent text as hidden numerical patterns, but what information these representations actually contain remains a mystery. Can we recover the original text f…
LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
Zirui He, Haiyan Zhao, Yingcong Li +2
Large language models (LLMs) are commonly evaluated on challenging benchmarks such as AIME and Math500, where benchmark contamination can make memorized solutions appear as genuine…
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
Haiyan Zhao, Xuansheng Wu, Fan Yang +3
Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder…
Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding
Mingyu Jin, Kai Mei, Wujiang Xu +5
Large language models (LLMs) have achieved remarkable success in contextual knowledge understanding. In this paper, we show that these concentrated massive values consistently emer…