Diversity-Enhanced Reasoning for Subjective Questions
Abstract
A diversity-enhanced framework with multiple role perspectives improves accuracy and diversity in subjective reasoning tasks through unsupervised data construction and reinforcement learning with reward shaping.
Large reasoning models (LRM) with long chain-of-thought (CoT) capabilities have shown strong performance on objective tasks, such as math reasoning and coding. However, their effectiveness on subjective questions that may have different responses from different perspectives is still limited by a tendency towards homogeneous reasoning, introduced by the reliance on a single ground truth in supervised fine-tuning and verifiable reward in reinforcement learning. Motivated by the finding that increasing role perspectives consistently improves performance, we propose MultiRole-R1, a diversity-enhanced framework with multiple role perspectives, to improve the accuracy and diversity in subjective reasoning tasks. MultiRole-R1 features an unsupervised data construction pipeline that generates reasoning chains that incorporate diverse role perspectives. We further employ reinforcement learning via Group Relative Policy Optimization (GRPO) with reward shaping, by taking diversity as a reward signal in addition to the verifiable reward. With specially designed reward functions, we successfully promote perspective diversity and lexical diversity, uncovering a positive relation between reasoning diversity and accuracy. Our experiment on six benchmarks demonstrates MultiRole-R1's effectiveness and generalizability in enhancing both subjective and objective reasoning, showcasing the potential of diversity-enhanced training in LRMs.
Community
This paper found that diversity is a better predictor of model performance than length under test-time scaling. Incorporating diversity as reward shaping into the GRPO training process can further enhance the model's reasoning capability.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Multimodal Mathematical Reasoning with Diverse Solving Perspective (2025)
- Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning (2025)
- ReasonGRM: Enhancing Generative Reward Models through Large Reasoning Models (2025)
- The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs (2025)
- Logit Arithmetic Elicits Long Reasoning Capabilities Without Training (2025)
- Omni-Think: Scaling Cross-Domain Generalization in LLMs via Multi-Task RL with Hybrid Rewards (2025)
- Learning to Reason Across Parallel Samples for LLM Reasoning (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper