FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding

• URL: http://arxiv.org/abs/2608.10764v1
• Date: Tue, 11 Aug 2026 10:22:08 GMT
• Title: FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding
• Abstract summary: Existing multiple-choice question (MCQ) benchmarks inadvertently leak target events through their questions and candidate options.<n>We present FADE, an effective training framework for counterfactual discovery and explanation.<n>FADE achieves state-of-the-art strict paired scores across all three tasks on DualityVidQA-test and IPV-Bench, outperforming GPT-5.6.
• Score: 19.559643217912114
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ) benchmarks inadvertently leak target events through their questions and candidate options. This reduces the core challenge from active discovery to text-guided verification. In this paper, we present FADE, an effective training framework for counterfactual discovery and explanation. Our method is built on an evidence-first, two-stage training paradigm. First, evidence-internalized supervised fine-tuning grounds the model's predictions in decisive visual anomalies. Second, we apply a fading-anchor reinforcement learning strategy that progressively removes textual guidance, compelling the model to independently discover and explain evidence. To rigorously evaluate this capability, we also introduce an effective pipeline that converts existing MCQ datasets into aligned MCQ, open-ended question answering (OQA), and captioning tasks without requiring additional data curation. Our simple approach yields strong results. Using Qwen3-VL-8B as the baseline, FADE achieves state-of-the-art strict paired scores across all three tasks on DualityVidQA-test and IPV-Bench, outperforming GPT-5.6. In specific, when transitioning from constrained MCQs to unconstrained OQA and captioning, our model demonstrates remarkable robustness. Its performance retention is 90.4% and 67.4% on DualityVidQA-test-substantially higher than the 48.1% and 30.7% retained by GPT-5.6. We hope this simple framework can serve as a solid baseline for future research in unconstrained counterfactual video understanding.

Related papers

• Counterfactual Reasoning for Robust Visual Question Answering [5.8572830941696985]
  We propose a novel training framework that enhances counterfactual contrastive learning for Visual Question Answering (VQA) models.<n>Our framework introduces three key contributions: (1) a three-stage curriculum for stable multi-objective optimization, (2) an enhanced Batch-Contrastive loss for more discriminative feature learning, and (3) two novel regularizers.<n>Our model achieves a competitive accuracy of 61.64% on the bias-sensitive VQA-CP v2 benchmark while maintaining 62.80% on the standard VQA v2 dataset, yielding a small generalization gap of 1.16%.
  arXiv  Detail & Related papers  (2026-09-15T03:06:11Z)
• Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements [78.87065404966002]
  Existing benchmarks predominantly curate questions at the question level.<n>We propose Encyclo-K, a statement-based benchmark that rethinks benchmark construction from the ground up.
  arXiv  Detail & Related papers  (2025-12-31T13:55:54Z)
• Look As You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning [55.232400251303794]
  Look As You Think (LAT) is a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution.<n>LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5.
  arXiv  Detail & Related papers  (2025-11-15T02:50:23Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA [37.679936989592996]
  We introduce a framework to synthesize richer supervisory signals.<n>We propose two complementary strategies: Question-Based Paraphrasing (QBP) and Question-Based Captioning (QBC)
  arXiv  Detail & Related papers  (2025-09-29T08:28:44Z)
• From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs [58.02809208460186]
  We revisit this paradox using high-quality traces from DeepSeek-R1 as demonstrations.<n>We find that adding more exemplars consistently degrades accuracy, even when demonstrations are optimal.<n>We introduce Insight-to-solve (I2S), a sequential test-time procedure that turns demonstrations into explicit, reusable insights.
  arXiv  Detail & Related papers  (2025-09-27T08:59:31Z)
• Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models [77.96693360763925]
  Video SimpleQA is the first comprehensive benchmark tailored for factuality evaluation in video contexts.<n>Our work differs from existing video benchmarks through the following key features: Knowledge required: demanding integration of external knowledge beyond the video's explicit narrative.<n>Short-form definitive answer: Answers are crafted as unambiguous and definitively correct in a short format with minimal scoring variance.
  arXiv  Detail & Related papers  (2025-03-24T17:46:09Z)
• Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology [0.34530027457862006]
  Previous research has shown that existing models, when trained on EQA datasets that include unanswerable questions, demonstrate a significant lack of robustness. Our proposed training method includes a novel loss function for the EQA problem and challenges an implicit assumption present in numerous EQA datasets. Our models exhibit significantly enhanced robustness against two types of adversarial attacks, with a performance decrease of only about a third compared to the default models.
  arXiv  Detail & Related papers  (2024-09-29T20:35:57Z)
• Chain of Evidences and Evidence to Generate: Prompting for Context Grounded and Retrieval Augmented Reasoning [3.117335706912261]
  Chain of Evidences (CoE) and Evidence to Generate (E2G) are built upon two unique strategies.<n>Instead of unverified reasoning claims, our innovative approaches leverage the power of "evidence for decision making"<n>Our framework consistently achieves remarkable results across various knowledge-intensive reasoning and generation tasks.
  arXiv  Detail & Related papers  (2024-01-11T09:49:15Z)
• Answering from Sure to Uncertain: Uncertainty-Aware Curriculum Learning for Video Question Answering [63.12469700986452]
  We introduce the concept of uncertainty-aware curriculum learning (CL) Here, uncertainty serves as the guiding principle for dynamically adjusting the difficulty. In practice, we seamlessly integrate the VideoQA model into our framework and conduct comprehensive experiments.
  arXiv  Detail & Related papers  (2024-01-03T02:29:34Z)

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.