Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

• URL: http://arxiv.org/abs/2607.14682v1
• Date: Thu, 16 Jul 2026 07:43:39 GMT
• Title: Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment
• Abstract summary: We introduce Perception-RFT, a training framework that applies Group Relative Policy Optimization to multimodal document QA.<n>We find that reasoning-enabled models suppress their reasoning traces during training, converging to direct perception-based policies at the 4B parameter scale.<n>We show that an early SFT$rightarrow$RL transition achieves comparable precision with 65% less training data.
• Score: 2.8730465903425877
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Efficient multimodal document question answering with explicit visual grounding, locating the precise document region that supports each answer remains an open challenge. Current approaches bifurcate into Supervised Fine-Tuning (SFT), which requires large annotated datasets and reaches optimization plateaus, and reasoning-centric Reinforcement Learning (RL), which depends on verbose intermediate traces that inflate inference token cost without clear benefit. We introduce Perception-RFT, a training framework that applies Group Relative Policy Optimization (GRPO) to multimodal document QA, bypassing intermediate reasoning tokens to directly align visual features with structured grounding outputs. To rigorously evaluate the necessity of reasoning, we construct a reasoning variant under identical reward settings. We find that reasoning-enabled models suppress their reasoning traces during training, converging to direct perception-based policies at the 4B parameter scale, reducing per-query inference token length by more than 60%, while reasoning-enabled RL underperforms perception-only training. Through a fine-grained analysis of Qwen3-VL-4B optimization dynamics, we confirm that SFT saturation and cold-start RL instability established in text-domain post-training extend to multimodal, and identify a previously uncharacterized Grounding Divergence: a selective trade-off between semantic robustness and geometric precision on two out of distribution (OOD) benchmarks (4,828 samples) under joint RL optimization. We further show that an early SFT$\rightarrow$RL transition achieves comparable precision with 65% less training data.

Related papers

• Is Next-Chunk Reasoning RL Really Better than SFT? Revisiting Training Strategies under no-CoT Data [48.92748013043833]
  We show that Mixed SFT achieves a clearly higher post-RLVR performance ceiling than next-chunk reasoning RL.<n>We also show that higher pre-RLVR accuracy does not necessarily translate into higher post-RLVR accuracy.
  arXiv  Detail & Related papers  (2026-08-24T13:47:45Z)
• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• TARo: Token-level Adaptive Routing for LLM Test-time Alignment [15.824259013420807]
  TARo steers frozen large language models toward structured reasoning entirely at inference time.<n>Extensive experiments show that TARo significantly improves reasoning performance by up to +22.4% over base model.<n> TARo also generalizes from small to large backbones without retraining.
  arXiv  Detail & Related papers  (2026-03-19T02:18:40Z)
• Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learning [7.006180736433431]
  Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry.<n>We propose a novel textbfAnswer-First, Reason Later (AFRL) paradigm.<n>This paradigm requires the model to output the definitive relevance score in the very first token, followed by a structured logical explanation.
  arXiv  Detail & Related papers  (2026-02-10T17:28:12Z)
• Hard Negative Sample-Augmented DPO Post-Training for Small Language Models [4.425580048633862]
  We propose a lightweight and pragmatic post-training pipeline that targets structured errors under realistic compute budgets.<n>We introduce a compact MathVerifier that decomposes a candidate solution into a six-dimensional error profile and aggregates it into interpretable wrongness and absurdity scores.<n> Experiments show that verifier-guided, weighted DPO yields more targeted improvements than vanilla SFT and unweighted DPO.
  arXiv  Detail & Related papers  (2025-12-17T06:15:52Z)
• Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling [90.87033586963828]
  Outcome-reward reinforcement learning (RL) is a common and increasingly significant way to refine the step-by-step reasoning of multimodal large language models (MLLMs)<n>We propose Self-Consistency Sampling (SCS) to correct this issue.<n>Based on Qwen2.5-VL-7B-Instruct, SCS improves accuracy by up to 7.7 percentage points on six multimodal benchmarks with negligible extra computation.
  arXiv  Detail & Related papers  (2025-11-13T18:59:57Z)
• Reinforcing Video Reasoning with Focused Thinking [65.85683941058916]
  We propose TW-GRPO, a novel framework that enhances visual reasoning with focused thinking and dense reward granularity.<n>Specifically, we employ a token weighting mechanism that prioritizes tokens with high informational density.<n>We also reformulate RL training by shifting from single-choice to multi-choice QA tasks.
  arXiv  Detail & Related papers  (2025-05-30T15:42:19Z)
• Interleaved Reasoning for Large Language Models via Reinforcement Learning [22.403928213802036]
  Long chain-of-thought (CoT) enhances large language models' (LLM) reasoning capabilities.<n>We propose a novel training paradigm that uses reinforcement learning (RL) to guide reasoning LLMs to interleave thinking and answering for multi-hop questions.
  arXiv  Detail & Related papers  (2025-05-26T07:58:17Z)
• Token-Efficient RL for LLM Reasoning [0.02488650627593658]
  We propose reinforcement learning strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits.<n>Building on early policy gradient methods with baseline subtraction, we design critic-free methods that operate on a small, informative subset of output tokens.<n>We show that our methods raise accuracy on the SVAMP benchmark from 46% to over 70% and show strong performance on multi-digit multiplication.
  arXiv  Detail & Related papers  (2025-04-29T14:58:43Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning [49.43901716932925]
  We show that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure.<n>Specifically, one first trains a reward model (RM) on some dataset (e.g., human preferences) before using it to provide online feedback.<n>We find the most support for the explanation that on problems with a generation-verification gap, it is relatively easy to learn the relatively simple RM from the preference data.
  arXiv  Detail & Related papers  (2025-03-03T00:15:19Z)

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.