ResearchTrend.AI
Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples
v1v2 (latest)

Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples

Chun-Yi Kuan
Hung-yi Lee
ArXiv (abs)PDFHTML

Papers citing "Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples"

3 / 3 papers shown
Title
From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
Chun-Yi Kuan
Hung-yi Lee
AuLLM
65
0
0
26 May 2025
DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data
Ke-Han Lu
Zhehuai Chen
Szu-Wei Fu
Chao-Han Huck Yang
Jagadeesh Balam
Boris Ginsburg
Yu-Te Wang
Hung-yi Lee
AuLLMSyDa
170
16
0
28 Jan 2025
Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning
Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning
Chun-Yi Kuan
Hung-yi Lee
AuLLMLRM
172
7
0
03 Jan 2025