activity
20232026
collaborators

9 papers

cs.CL2026

Fine-Grained Activation Steering: Steering Less, Achieving More

Zijian Feng, Tianjiao Li, Zixiao Zhu +7

Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering t…

cs.LG2025

Restoring Pruned Large Language Models via Lost Component Compensation

Zijian Feng, Hanzhang Zhou, Zixiao Zhu +5

Pruning is a widely used technique to reduce the size and inference cost of large language models (LLMs), but it often causes performance degradation. To mitigate this, existing re…

cs.CL2025

Domain Lexical Knowledge-based Word Embedding Learning for Text Classification under Small Data

Zixiao Zhu, Kezhi Mao

Pre-trained language models such as BERT have been proved to be powerful in many natural language processing tasks. But in some text classification applications such as emotion rec…

cs.CL2025

Rethinking Prompt Optimizers: From Prompt Merits to Optimization

Zixiao Zhu, Hanzhang Zhou, Zijian Feng +5

Prompt optimization (PO) provides a practical way to improve response quality when users lack the time or expertise to manually craft effective prompts. Existing methods typically…

cs.CL2025

Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction

Junlang Qian, Zixiao Zhu, Hanzhang Zhou +3

Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prom…

cs.CL2024

FreeCtrl: Constructing Control Centers with Feedforward Layers for Learning-Free Controllable Text Generation

Zijian Feng, Hanzhang Zhou, Zixiao Zhu +1

Controllable text generation (CTG) seeks to craft texts adhering to specific attributes, traditionally employing learning-based techniques such as training, fine-tuning, or prefix-…