REVIEW 6 cited by
Boosting MLLM Reasoning with Text-Debiased Hint-GRPO
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
MLLM reasoning has drawn widespread research for its excellent problem-solving capability. Current reasoning methods fall into two types: PRM, which supervises the intermediate reasoning steps, and ORM, which supervises the final results. Recently, DeepSeek-R1 has challenged the traditional view that PRM outperforms ORM, which demonstrates strong generalization performance using an ORM method (i.e., GRPO). However, current MLLM's GRPO algorithms still struggle to handle challenging and complex multimodal reasoning tasks (e.g., mathematical reasoning). In this work, we reveal two problems that impede the performance of GRPO on the MLLM: Low data utilization and Text-bias. Low data utilization refers to that GRPO cannot acquire positive rewards to update the MLLM on difficult samples, and text-bias is a phenomenon that the MLLM bypasses image condition and solely relies on text condition for generation after GRPO training. To tackle these problems, this work proposes Hint-GRPO that improves data utilization by adaptively providing hints for samples of varying difficulty, and text-bias calibration that mitigates text-bias by calibrating the token prediction logits with image condition in test-time. Experiment results on three base MLLMs across eleven datasets demonstrate that our proposed methods advance the reasoning capability of original MLLM by a large margin, exhibiting superior performance to existing MLLM reasoning methods. Our code is available at https://github.com/hqhQAQ/Hint-GRPO.
Forward citations
Cited by 6 Pith papers
-
Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems
AdaPrefix-GRPO treats solution-prefix length as a feedback controller targeting 50% rollout success rate during GRPO training, then anneals to zero prefix, yielding 1.6–2.1× accuracy gains over vanilla GRPO at matched...
-
Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
RL-trained VLMs generalize compositionally far better than SFT-trained ones on synthetic geometry and spatial tasks, but cross-modal combination remains weak, and a caption-before-thinking plus progress-reward recipe ...
-
RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning
RePrompt uses RL-trained reasoning traces to enhance text-to-image prompts, boosting spatial composition and counting scores across FLUX, SD3, and PixArt-Σ while keeping image generators fixed.
-
Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning
A GRPO framework that treats thinking as a tool call and uses dual-level regulation so multimodal models learn when to reason versus answer directly.
-
EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models
EMO-R3, which combines a three-step emotional reasoning prompt with a reward for the model agreeing with its own image–emotion judgments, raises visual emotion-recognition accuracy by about one point over plain GRPO.
-
Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle
A survey that maps reinforcement learning methods, datasets, benchmarks, and open-source tools across the full training lifecycle of large language models, focusing on verifiable-reward reasoning.
Discussion (0). Continue with ORCID to comment.