11 papers
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…
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…
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…
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…
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…
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…