作者位次 #7/9ACL 2026Findings· Findings of ACL
Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
Weixu Zhang · Fanghua Ye · Qiang Gao · Jian Li · Haolun Wu · Yuxing Tian · Sijing Duan · Nan Du · Xiaolong Li
摘要
Large language models (LLMs) often produce content that contradicts or overlooks information provided in the input context, a phenomenon known as faithfulness hallucination. In this paper, we propose Context-Fidelity Boosting (CFB), a lightweight and general decoding-time framework that effective...