← Search

Birong Pan

2 accepted papers

2025

A Survey on Training-free Alignment of Large Language Models

EMNLP 2025

The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely on resource-intensive fine-tuning (FT), which may suffer from knowledge degradation and face challenges in scenarios where t

Cited by 0SourcePDFScholar
2025

Aligning VLM Assistants with Personalized Situated Cognition

ACL 2025long

Vision-language models (VLMs) aligned with general human objectives, such as being harmless and hallucination-free, have become valuable assistants of humans in managing visual tasks. However, people with diversified backgrounds have different cognition even in the same situation. Consequently, they…