6 papers · 1 filter
Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing
Yutong Yin, Mingyu Jin, Jin Pan +12
Test-time scaling improves language-model reasoning, but existing approaches often face a difficult trade-off: long chain-of-thought sampling remains single-threaded, while sentenc…
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…
Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
Mingyu Jin, Yutong Yin, Jingcheng Niu +7
In this work, we investigate how Large Language Models (LLMs) adapt their internal representations when encountering inputs of increasing difficulty, quantified as the degree of ou…
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…
Data-centric NLP Backdoor Defense from the Lens of Memorization
Zhenting Wang, Zhizhi Wang, Mingyu Jin +3
Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample…
Exploring Multilingual Probing in Large Language Models: A Cross-Language Analysis
Daoyang Li, Haiyan Zhao, Qingcheng Zeng +1
Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probin…