Backend
CoTTAGE: An Explainable Judge for Text-to-Audio Generation
arXiv cs.SD0 views
arXiv:2611.17644v1 Announce Type: new Abstract: Rapid progress in text-to-audio (TTA) generation demands reliable and explainable automatic evaluation. However, existing metrics fail to simultaneously deliver high correlation with human judgments and meaningful, audio-grounded explanations, forcing reliance on labor-intensive human evaluation that bottlenecks model development iteration. To address this, we propose CoTTAGE, a reasoning-based evaluator for text relevance (REL) and audio quality (OVL). Following a reason-then-predict paradigm, CoTTAGE first generates an audio-grounded rationale to diagnose errors before predicting scores. Supported by over 10K newly collected human OVL annotations, CoTTAGE is first trained via supervised fine-tuning and then refined with reinforcement learning using a Thurstone-based preference objective that converts sampled score distributions into pairwise preference probabilities and rewards agreement with rankings derived from human judgments. Across six benchmarks spanning REL and OVL, CoTTAGE achieves state-of-the-art correlation with human judgments while producing human-preferred explanations to accelerate TTA development.
Source:https://arxiv.org/abs/2611.17644PreviousLazyWeights: Decode-on-Demand Edge LLMsNextAny Channel Count, One Token Stream: Incorporating Spatial Audio Understanding and Reasoning into Large Audio-Language Models
Related posts
What I Learned Managing Instagram for Local Brands in Kerala
0dev.to

Shamir Secret Sharing in Python from Scratch: GF(256), Vault Compatibility, and Where MPC Wallets Go Further
0dev.to
You asked the agent to improve a screen. It started over.
0dev.to
FBI's ARTEX AI Warning: What It Means for SMB Defenses
0dev.to
Every deletion in your diff had a reason to exist. AI doesn't know what it was.
0dev.to

Where does my site rank in 114 Google markets?
0dev.to