activity
20242026
collaborators
Showing cs.CLShow all

5 papers · 1 filter

cs.CL2026

Beyond "I cannot fulfill this request": Alleviating Rigid Rejection in LLMs via Label Enhancement

Ying Zhang, Congyu Qiao, Xin Geng +1

Large Language Models (LLMs) rely on safety alignment to obey safe requests while refusing harmful ones. However, traditional refusal mechanisms often lead to "rigid rejection," wh…

cs.CL2026

VRM: Teaching Reward Models to Understand Authentic Human Preferences

Biao Liu, Ning Xu, Junming Yang +2

Large Language Models (LLMs) have achieved remarkable success across diverse natural language tasks, yet the reward models employed for aligning LLMs often encounter challenges of…

cs.CL2026

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization

Junming Yang, Ning Xu, Biao Liu +2

Preference optimization is crucial for aligning large language models (LLMs) with human values and intentions. A significant challenge in this process is the distribution mismatch…

cs.CL2025

Preference Orchestrator: Prompt-Aware Multi-Objective Alignment for Large Language Models

Biao Liu, Ning Xu, Junming Yang +1

While Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks, aligning these models with varying human preferences…

cs.CL2024

Progressively Label Enhancement for Large Language Model Alignment

Biao Liu, Ning Xu, Xin Geng

Large Language Models (LLM) alignment aims to prevent models from producing content that misaligns with human expectations, which can lead to ethical and legal concerns. In the las…