1 citations · 2 across the 3 of their papers we have counts for
4 papers
One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering
Xudong Zhu, Zhihui Zhu
Prompting guides language model behavior through the initial context, whereas activation steering often intervenes throughout generation. A natural question is whether steering can…
AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
Xudong Zhu, Mohammad Mahdi Khalili, Zhihui Zhu
Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic feat…
From Emergence to Control: Probing and Modulating Self-Reflection in Language Models
Xudong Zhu, Jiachen Jiang, Mohammad Mahdi Khalili +1
Self-reflection -- the ability of a large language model (LLM) to revisit, evaluate, and revise its own reasoning -- has recently emerged as a powerful behavior enabled by reinforc…
FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extraction
Xudong Zhu, Zhao Kang, Bei Hui
Document-level Relation Extraction (DocRE) aims to identify relation labels between entities within a single document. It requires handling several sentences and reasoning over the…