# Improving Few-Shot Change Detection Visual Question Answering via Decision-Ambiguity-guided Reinforcement Fine-Tuning

arXiv: https://arxiv.org/abs/2512.24591 · HTML: https://mlsanity.com/paper/2512.24591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 19 references that are in the map.
- First posted on arXiv 31 Dec 2025.

## Builds on (most cited first, 14 of 14)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis](https://mlsanity.com/paper/2403.19646/) (2024)
- [Change Detection Meets Visual Question Answering](https://mlsanity.com/paper/2112.06343/) (2021)
- [Remote Sensing SpatioTemporal Vision-Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02573/) (2024)
- [DynamicEarth: How Far are We from Open-Vocabulary Change Detection?](https://mlsanity.com/paper/2501.12931/) (2025)
- [DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding](https://mlsanity.com/paper/2505.21076/) (2025)
- [Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection](https://mlsanity.com/paper/2410.23828/) (2024)
- [UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models](https://mlsanity.com/paper/2412.20742/) (2024)
- [Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models](https://mlsanity.com/paper/2507.09209/) (2025)

## Abstract (arXiv)

Change detection visual question answering (CDVQA) requires answering text queries by reasoning about semantic changes in bi-temporal remote sensing images. A straightforward approach is to boost CDVQA performance with generic vision-language models via supervised fine-tuning (SFT). Despite recent progress, we observe that a significant portion of failures do not stem from clearly incorrect predictions, but from decision ambiguity, where the model assigns similar confidence to the correct answer and strong distractors. To formalize this challenge, we define Decision-Ambiguous Samples (DAS) as instances with a small probability margin between the ground-truth answer and the most competitive alternative. We argue that explicitly optimizing DAS is crucial for improving the discriminability and robustness of CDVQA models. To this end, we propose DARFT, a Decision-Ambiguity-guided Reinforcement Fine-Tuning framework that first mines DAS using an SFT-trained reference policy and then applies group-relative policy optimization on the mined subset. By leveraging multi-sample decoding and intra-group relative advantages, DARFT suppresses strong distractors and sharpens decision boundaries without additional supervision. Extensive experiments demonstrate consistent gains over SFT baselines, particularly under few-shot settings.