7 papers
AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback
Zhitao Gao, Jie Ma, Xuhong Li +5
Large Language Models (LLMs) have achieved significant success in complex reasoning but remain bottlenecked by reliance on expert-annotated data and external verifiers. While exist…
Detecting Training Data of Large Language Models via Expectation Maximization
Gyuwan Kim, Yang Li, Evangelia Spiliopoulou +2
Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as…
From Entity Reliability to Clean Feedback: An Entity-Aware Denoising Framework Beyond Interaction-Level Signals
Ze Liu, Xianquan Wang, Shuochen Liu +5
Implicit feedback is central to modern recommender systems but is inherently noisy, often impairing model training and degrading user experience. At scale, such noise can mislead l…
Faithful and Interpretable Explanations for Complex Ensemble Time Series Forecasts using Surrogate Models and Forecastability Analysis
Yikai Zhao, Jiekai Ma
Modern time series forecasting increasingly relies on complex ensemble models generated by AutoML systems like AutoGluon, delivering superior accuracy but with significant costs to…
Play Favorites: A Statistical Method to Measure Self-Bias in LLM-as-a-Judge
Evangelia Spiliopoulou, Riccardo Fogliato, Hanna Burnsky +4
Large language models (LLMs) can serve as judges that offer rapid and reliable assessments of other LLM outputs. However, models may systematically assign overly favorable ratings…
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models
Qin Liu, Chao Shang, Ling Liu +7
The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phen…