20 citations · 38 across the 13 of their papers we have counts for
9 papers · 1 filter
NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models
Weiqi Liu, Yongliang Miao, Haiyan Zhao +2
Neuron-level interpretation in large language models (LLMs) is fundamentally challenged by widespread polysemanticity, where individual neurons respond to multiple distinct semanti…
LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories
Zirui He, Haiyan Zhao, Yingcong Li +2
Large language models (LLMs) are commonly evaluated on challenging benchmarks such as AIME and Math500, where benchmark contamination can make memorized solutions appear as genuine…
Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering
Haiyan Zhao, Xuansheng Wu, Fan Yang +3
Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder…
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…
Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?
Mingyu Jin, Qinkai Yu, Jingyuan Huang +10
Large language models (LLMs) have shown remarkable performances across a wide range of tasks. However, the mechanisms by which these models encode tasks of varying complexities rem…
Towards Uncovering How Large Language Model Works: An Explainability Perspective
Haiyan Zhao, Fan Yang, Bo Shen +2
Large language models (LLMs) have led to breakthroughs in language tasks, yet the internal mechanisms that enable their remarkable generalization and reasoning abilities remain opa…
The Impact of Reasoning Step Length on Large Language Models
Mingyu Jin, Qinkai Yu, Dong Shu +5
Chain of Thought (CoT) is significant in improving the reasoning abilities of large language models (LLMs). However, the correlation between the effectiveness of CoT and the length…
Mitigating Shortcuts in Language Models with Soft Label Encoding
Zirui He, Huiqi Deng, Haiyan Zhao +2
Recent research has shown that large language models rely on spurious correlations in the data for natural language understanding (NLU) tasks. In this work, we aim to answer the fo…
Explainability for Large Language Models: A Survey
Haiyan Zhao, Hanjie Chen, Fan Yang +6
Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transpa…