Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

• URL: http://arxiv.org/abs/2503.11197v3
• Date: Wed, 19 Mar 2025 16:33:16 GMT
• Title: Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
• Authors: Gang Li, Jizhong Liu, Heinrich Dinkel, Yadong Niu, Junbo Zhang, Jian Luan,
• Abstract summary: reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs)<n>We conduct a series of RL explorations in audio understanding and reasoning, specifically focusing on the audio question answering (AQA) task.<n>Our experiments demonstrated state-of-the-art performance on the MMAU Test-mini benchmark, achieving an accuracy rate of 64.5%.
• Score: 22.88876323500893
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio modality has largely been overlooked in these developments. Thus, we conduct a series of RL explorations in audio understanding and reasoning, specifically focusing on the audio question answering (AQA) task. We leverage the group relative policy optimization (GRPO) algorithm to Qwen2-Audio-7B-Instruct, and our experiments demonstrated state-of-the-art performance on the MMAU Test-mini benchmark, achieving an accuracy rate of 64.5%. The main findings in this technical report are as follows: 1) The GRPO algorithm can be effectively applied to large audio language models (LALMs), even when the model has only 8.2B parameters; 2) With only 38k post-training samples, RL significantly outperforms supervised fine-tuning (SFT), indicating that RL-based approaches can be effective without large datasets; 3) The explicit reasoning process has not shown significant benefits for AQA tasks, and how to efficiently utilize deep thinking remains an open question for further research; 4) LALMs still lag far behind humans auditory-language reasoning, suggesting that the RL-based approaches warrant further exploration. Our project is available at https://github.com/xiaomi-research/r1-aqa and https://huggingface.co/mispeech/r1-aqa.

Related papers

• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding. It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions. Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT) Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning [50.419872452397684]
  Search-R1 is an extension of reinforcement learning for reasoning frameworks. It generates search queries during step-by-step reasoning with real-time retrieval. It improves performance by 41% (Qwen2.5-7B) and 20% (Qwen2.5-3B) over various RAG baselines.
  arXiv  Detail & Related papers  (2025-03-12T16:26:39Z)
• MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning [56.97799347091435]
  We present MM-Eureka, a multimodal reasoning model that successfully extends large-scale rule-based reinforcement learning (RL) to multimodal reasoning.<n>Our work reproduces key characteristics of text-based RL systems like DeepSeek-R1 in the multimodal space.<n>We demonstrate that both instruction-tuned and pre-trained models can develop strong multimodal reasoning capabilities through rule-based RL without supervised fine-tuning.
  arXiv  Detail & Related papers  (2025-03-10T14:23:12Z)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models.<n>Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start.<n>Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models [95.45204813682885]
  We introduce Audio-Reasoner, a large-scale audio language model for deep reasoning in audio tasks.<n>We train Audio-Reasoner on CoTA, enabling it to achieve great logical capabilities in audio reasoning.<n>Our findings stress the core of structured CoT training in advancing audio reasoning.
  arXiv  Detail & Related papers  (2025-03-04T06:18:34Z)
• On the Emergence of Thinking in LLMs I: Searching for the Right Intuition [34.32871896067864]
  We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP)<n> RLSP involves three steps: supervised fine-tuning with human or synthetic demonstrations of the reasoning process, using an exploration reward signal to encourage diverse and efficient reasoning behaviors, and RL training with an outcome verifier to ensure correctness while preventing reward hacking.<n> Empirical studies in the math domain show that RLSP improves reasoning.
  arXiv  Detail & Related papers  (2025-02-10T18:52:04Z)
• Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling [52.34735382627312]
  Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks.<n>Existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling.<n>We present T1 to scale reinforcement learning by encouraging exploration and understand inference scaling.
  arXiv  Detail & Related papers  (2025-01-20T18:33:33Z)
• ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback [13.154512864498912]
  We propose a two-stage algorithm ARES that Alternates REinforcement Learning (RL) and Supervised Fine-Tuning (SFT) First, we request the Teacher to score how much each sentence contributes to solving the problem in a Chain-of-Thought (CoT) Second, we ask the Teacher to correct the wrong reasoning after the RL stage. With the correction feedback, we stabilize the RL fine-tuned model through SFT.
  arXiv  Detail & Related papers  (2024-06-25T07:20:11Z)
• Teaching Large Language Models to Reason with Reinforcement Learning [38.17625148525193]
  Reinforcement Learning from Human Feedback (textbfRLHF) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from feedback.
  arXiv  Detail & Related papers  (2024-03-07T16:36:29Z)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [80.10358123795946]
  We develop a framework for building multi-turn RL algorithms for fine-tuning large language models. Our framework adopts a hierarchical RL approach and runs two RL algorithms in parallel. Empirically, we find that ArCHer significantly improves efficiency and performance on agent tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:45:56Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• A Light Weight Model for Active Speaker Detection [7.253335671577093]
  We construct a lightweight active speaker detection architecture by reducing input candidates, splitting 2D and 3D convolutions for audio-visual feature extraction, and applying gated recurrent unit (GRU) with low computational complexity for cross-modal modeling. Experimental results on the AVA-ActiveSpeaker dataset show that our framework achieves competitive mAP performance (94.1% vs. 94.2%). Our framework also performs well on the Columbia dataset showing good robustness.
  arXiv  Detail & Related papers  (2023-03-08T08:40:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.