8 papers
ICA Lens: Interpreting Language Models Without Training Another Dictionary
Sida Liu, Feijiang Han
Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (SAEs) have become the standard…
ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models
Delip Rao, Feijiang Han, Chris Callison-Burch
We present ThinknCheck, a 1B-parameter verifier for grounded claim verification that first produces a short, structured rationale and then a binary verdict. We construct LLMAggreFa…
DeepAFL: Deep Analytic Federated Learning
Jianheng Tang, Yajiang Huang, Kejia Fan +8
Federated Learning (FL) is a popular distributed learning paradigm to break down data silo. Traditional FL approaches largely rely on gradient-based updates, facing significant iss…
Can LLMs Handle WebShell Detection? Overcoming Detection Challenges with Behavioral Function-Aware Framework
Feijiang Han, Jiaming Zhang, Chuyi Deng +2
WebShell attacks - where adversaries implant malicious scripts on web servers - remain a persistent threat. Prior machine-learning and deep-learning detectors typically depend on t…
ZeroTuning: Unlocking the Initial Token's Power to Enhance Large Language Models Without Training
Feijiang Han, Xiaodong Yu, Jianheng Tang +3
Token-level attention tuning, a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT), has emerged as a promising approach fo…
Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification
Feijiang Han
Malicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and financ…