7 citations · 7 across the 7 of their papers we have counts for
5 papers · 1 filter
ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
Zirui Wang, Yusen Hou, Shaofeng Liang +4
The explosive growth of large language models (LLMs) has created a heterogeneous and poorly documented ecosystem, making systematic model comparison increasingly important for prov…
When New Generators Arrive: Lifelong Machine-Generated Text Attribution via Ridge Feature Transfer
Zhen Sun, Yifan Liao, Zhicong Huang +4
Machine-generated text (MGT) attribution aims to identify the specific generator responsible for a given text, thereby providing fine-grained evidence for model accountability and…
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
Xi Chen, Mingyu Jin, Jingcheng Niu +7
In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional An…
MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models
Kaichen Huang, Jiahao Huo, Yibo Yan +3
In recent years, multimodal large language models (MLLMs) have significantly advanced, integrating more modalities into diverse applications. However, the lack of explainability re…
MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model
Jiahao Huo, Yibo Yan, Boren Hu +2
Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms…