activity
20242026
collaborators
Showing cs.CLShow all

6 papers · 1 filter

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.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

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation

Hanzhang Zhou, Zijian Feng, Zixiao Zhu +2

Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm. However, their effectiveness is often compromi…

cs.CL2024

Logit Separability-Driven Samples and Multiple Class-Related Words Selection for Advancing In-Context Learning

Zhu Zixiao, Feng Zijian, Zhou Hanzhang +2

Effective organization of in-context learning (ICL) demonstrations is key to improving the quality of large language model (LLM) responses. To create better sample-label pairs that…

cs.CL2024

LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction

Hanzhang Zhou, Junlang Qian, Zijian Feng +3

In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We…

cs.CL2024

Unveiling and Manipulating Prompt Influence in Large Language Models

Zijian Feng, Hanzhang Zhou, Zixiao Zhu +2

Prompts play a crucial role in guiding the responses of Large Language Models (LLMs). However, the intricate role of individual tokens in prompts, known as input saliency, in shapi…