6 papers
ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences
Bang Nguyen, Dominik Soós, Qian Ma +8
The literature has witnessed an emerging interest in AI agents for automated assessment of scientific papers. Existing benchmarks focus primarily on the computational aspect of thi…
Attacks Meet Interpretability (AmI) Evaluation and Findings
Qian Ma, Ziping Ye, Shagufta Mehnaz
To investigate the effectiveness of the model explanation in detecting adversarial examples, we reproduce the results of two papers, Attacks Meet Interpretability: Attribute-steere…
Learning Password Best Practices Through In-Task Instruction
Qian Ma, Yingfan Zhou, Shubhang Kaushik +6
Users often make security- and privacy-relevant decisions without a clear understanding of the rules that govern safe behavior. We introduce pedagogical friction, a design approach…
How to Backdoor the Knowledge Distillation
Chen Wu, Qian Ma, Prasenjit Mitra +1
Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more e…
Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
Qian Ma, Ruoxiang Xu, Yongqiang Cai
Numerous studies have demonstrated that the Transformer architecture possesses the capability for in-context learning (ICL). In scenarios involving function approximation, context…
Enhancing Adversarial Example Detection Through Model Explanation
Qian Ma, Ziping Ye
Adversarial examples are a major problem for machine learning models, leading to a continuous search for effective defenses. One promising direction is to leverage model explanatio…