4 papers · 1 filter
Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs
Jingcheng Niu, Xingdi Yuan, Tong Wang +2
We observe a novel phenomenon, contextual entrainment, across a wide range of language models (LMs) and prompt settings, providing a new mechanistic perspective on how LMs become d…
Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity
Lei Yu, Jingcheng Niu, Zining Zhu +2
In this paper, we introduce DiscoGP, a novel framework for extracting self-contained modular units, or sheaves, within neural language models (LMs). Sheaves extend the concept of f…
What does the Knowledge Neuron Thesis Have to do with Knowledge?
Jingcheng Niu, Andrew Liu, Zining Zhu +1
We reassess the Knowledge Neuron (KN) Thesis: an interpretation of the mechanism underlying the ability of large language models to recall facts from a training corpus. This nascen…
Bringing the State-of-the-Art to Customers: A Neural Agent Assistant Framework for Customer Service Support
Stephen Obadinma, Faiza Khan Khattak, Shirley Wang +23
Building Agent Assistants that can help improve customer service support requires inputs from industry users and their customers, as well as knowledge about state-of-the-art Natura…