4 papers
The Override Gap: A Magnitude Account of Knowledge Conflict Failure in Hypernetwork-Based Instant LLM Adaptation
Shuaizhi Cheng, Xiang Shi, Zhiwei Zhang +1
Hypernetwork-based methods such as Doc-to-LoRA internalize a document into an LLM's weights in a single forward pass, but they fail systematically on conflicts: when the document c…
Persona Without Substrate: Regime-Dependence and the LLM Individuation Problem
Shuaizhi Cheng
Beckmann & Butlin's (2026) ontological framework for the LLM individuation problem inherits an unargued cross-regime co-reference assumption from the persona-vectors literature: th…
Formalising the Logit Shift Induced by LoRA: A Technical Note
Xiang Shi, Shuaizhi Cheng, Mingwei Li
This technical note provides a first-order formalisation of the logit shift and fact-margin change induced by Low-Rank Adaptation (LoRA). Using a first-order Fréchet approximation…
Data Scaling as Progressive Coverage of a Predictive Contribution Spectrum
Zihui Song, Shihao Ji, Hongxi Li +2
We investigate the hypothesis that real-data scaling laws are governed by progressive coverage of a latent predictive contribution spectrum rather than by token-frequency tails alo…