FSA-GRPO: Teaching Auditory LLMs to Use Few-Shot Demonstrations

arXiv:2606.02615 · eess.AS, cs.AI, cs.SD · Submitted 2026-05-26 · Read on arXiv

eess.AS, cs.AI, cs.SD

Submitted: 2026-05-26

Updated: 2026-08-29

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 66× in this paper · explained in 6 episodes
• Adaptation — 30× in this paper · explained in 1 episode
• Speech Translation — 16× in this paper
• Ablation — 12× in this paper · explained in 1 episode
• In-Context Learning — 12× in this paper · explained in 4 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Alignment — 8× in this paper · explained in 1 episode
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• GRPO Objective — 5× in this paper · explained in 2 episodes
• Low-Resource Languages — 4× in this paper · explained in 4 episodes
• Domain Adaptation — 3× in this paper · explained in 5 episodes
• Semantic Alignment — 3× in this paper · explained in 3 episodes
• Transferability — 3× in this paper · explained in 4 episodes
• Catastrophic Forgetting — 2× in this paper · explained in 5 episodes
• Domain Shift — 2× in this paper · explained in 4 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• In-Context Learning (ICL) — 2× in this paper · explained in 5 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Meta-learning — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Personalization — 1× in this paper · explained in 2 episodes
• Redmond Sentence Recall — 1× in this paper
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• Advancing Speech Understanding in Speech-Aware Language Models with GRPO
• Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models
• Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
• Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
• Multimodal In-context Learning for ASR of Low-resource Languages
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition
• COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning
• Qwen2.5-Omni Technical Report
• Omnilingual ASR: Open-Source Multilingual Speech Recognition for 1600+ Languages
• Proximal Policy Optimization Algorithms
• TICL+: A Case Study On Speech In-Context Learning for Children's Speech Recognition
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• TICL: Text-Embedding KNN For Speech In-Context Learning Unlocks Speech Recognition Abilities of Large Multimodal Models
• Group Relative Policy Optimization for Speech Recognition
• Towards General Auditory Intelligence: Large Multimodal Models for Machine Listening and Speaking
• MetaSICL: Globalizing Auditory LLMs for Underserved Speakers and Languages via Meta Speech In-Context Learning

Related papers

• X-VC: Zero-shot Streaming Voice Conversion in Codec Space
• Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization
• Towards Audio Token Compression in Large Audio Language Models
• WaveScat: Wavelet Scattering Front-Ends with Self-Supervised Features for Speech Deepfake Detection
• ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions