collaborators

11 papers

cs.CL2026

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…

cs.CL2026

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…

cs.LG2025

Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders

Dong Shu, Xuansheng Wu, Haiyan Zhao +2

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional…

cs.LG2025

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models

Dong Shu, Xuansheng Wu, Haiyan Zhao +4

Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted…

cs.CV2025

Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability

Dong Shu, Haiyan Zhao, Jingyu Hu +4

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment betwe…

cs.AI2025

ContractEval: Benchmarking LLMs for Clause-Level Legal Risk Identification in Commercial Contracts

Shuang Liu, Zelong Li, Ruoyun Ma +2

The potential of large language models (LLMs) in specialized domains such as legal risk analysis remains underexplored. In response to growing interest in locally deploying open-so…