6 papers
ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation
Yiru Dong, Richong Zhang, Fanshuang Kong +1
Large language models (LLMs) have made notable progress in code generation, but they still struggle on challenging tasks that require sophisticated algorithms or complex implementa…
inversedMixup: Data Augmentation via Inverting Mixed Embeddings
Fanshuang Kong, Richong Zhang, Qiyu Sun +3
Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio. However, since it operates at the latent embedding level, the resulting sam…
Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation
Junhao Zhang, Richong Zhang, Fanshuang Kong +3
Existing long-text generation methods produce lengthy outputs from short inputs, leaving long-input-to-long-output generation underexplored. As input length increases, LLMs increas…
LH-Mix: Local Hierarchy Correlation Guided Mixup over Hierarchical Prompt Tuning
Fanshuang Kong, Richong Zhang, Ziqiao Wang
Hierarchical text classification (HTC) aims to assign one or more labels in the hierarchy for each text. Many methods represent this structure as a global hierarchy, leading to red…
MOMA: Masked Orthogonal Matrix Alignment for Zero-Additional-Parameter Model Merging
Fanshuang Kong, Richong Zhang, Zhijie Nie +4
Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric mis…
Activated Parameter Locating via Causal Intervention for Model Merging
Fanshuang Kong, Richong Zhang, Ziqiao Wang
Model merging combines multiple homologous models into one model, achieving convincing generalization without the necessity of additional training. A key challenge in this problem…