2 papers
cs.SD2026
TAD: Token-Adaptive Contrastive Decoding with Confidence-Guided Gating for Hallucination Mitigation in Large Audio-Language Models
Heyu Chang, Nianwen Si, Hao Zhang +2
Large audio-language models (LALMs) can hallucinate audio objects, answering "yes" to absent sound events, thus undermining reliability in audio question answering. We propose Toke…
cs.CL2023
Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges
Nianwen Si, Hao Zhang, Heyu Chang +3
In recent years, large language models (LLMs) have spurred a new research paradigm in natural language processing. Despite their excellent capability in knowledge-based question an…