GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification

• URL: http://arxiv.org/abs/2604.08879v1
• Date: Fri, 10 Apr 2026 02:38:14 GMT
• Title: GRASP: Grounded CoT Reasoning with Dual-Stage Optimization for Multimodal Sarcasm Target Identification
• Abstract summary: GRASP is a framework that integrates visual grounding with explicit Chain-of-Thought (CoT) reasoning to move beyond black-box MSTI.<n>We introduce Grounded CoT reasoning, which explicitly anchors sarcasm-related visual regions within the reasoning trajectory.<n>Our dataset and source code will be released on GitHub.
• Score: 26.21876180083083
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Moving beyond the traditional binary classification paradigm of Multimodal Sarcasm Detection, Multimodal Sarcasm Target Identification (MSTI) presents a more formidable challenge, requiring precise localization of fine-grained targets such as textual phrases and visual regions. Existing approaches predominantly rely on implicit cross-modal alignment, offering limited interpretability and suboptimal fine-grained localization. To address these limitations, we propose GRASP, Grounded Chain-of-Thought ReAsoning with Dual-Stage Optimization for Multimodal Sarcasm Prediction and Target Identification, a framework that integrates visual grounding with explicit Chain-of-Thought (CoT) reasoning to move beyond black-box MSTI. Specifically, we curate MSTI-MAX, a refined dataset that mitigates class imbalance and enriches multimodal sarcasm cues. We introduce Grounded CoT reasoning, which explicitly anchors sarcasm-related visual regions within the reasoning trajectory and prompts the model to articulate rationales before predicting the final classification labels and sarcasm targets. Furthermore, we employ a dual-stage outcome-supervised joint optimization strategy: Supervised Fine-Tuning with a coordinate-aware weighted loss, followed by Fine-Grained Target Policy Optimization. Extensive experiments demonstrate that GRASP outperforms existing baselines in fine-grained sarcasm target identification across modalities, and an LLM-as-a-Judge evaluation quantitatively measures the quality of internal reasoning chains. Our dataset and source code will be released on GitHub.

Related papers

• Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Multimodal Sarcasm Detection [8.747820204756566]
  Multimodal sarcasm detection aims to identify sarcastic intent from multimodal content.<n>New framework integrates Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization.
  arXiv  Detail & Related papers  (2026-08-20T12:02:06Z)
• ExACT: Exemplar-Driven Calibrated Refinement for Training-Free Visual Grounding in Remote Sensing Images [51.53960096934913]
  Remote sensing visual grounding (RSVG) aims to locate specific objects in high-resolution RS imagery using free-form natural language descriptions.<n>Recent advances in multimodal large language models (MLLMs) show great potential for such open-vocabulary RSVG.<n>We propose Exemplar-driven Calibrated Refinement (ExACT), a training-free framework driven by a one-shot visual prompting mechanism.
  arXiv  Detail & Related papers  (2026-06-27T13:50:39Z)
• CFMS: Towards Explainable and Fine-Grained Chinese Multimodal Sarcasm Detection Benchmark [11.646782931569026]
  We construct CFMS, the first fine-grained multimodal sarcasm dataset tailored for Chinese social media.<n>We find that the fine-grained explanation annotations effectively guide AI in generating images with explicit sarcastic intent.<n>To overcome the constraints of traditional retrieval methods, we propose a Reinforcement Learning-augmented In-Context Learning strategy.
  arXiv  Detail & Related papers  (2026-03-23T15:55:14Z)
• Perception-Aware Multimodal Spatial Reasoning from Monocular Images [57.42071289037214]
  spatial reasoning from monocular images is essential for autonomous driving.<n>Current Vision-Language Models (VLMs) still struggle with fine-grained geometric perception.<n>We propose a perception-aware multimodal reasoning framework that equipsVLMs with explicit object-centric grounding ability.
  arXiv  Detail & Related papers  (2026-03-07T02:05:12Z)
• OmniVL-Guard: Towards Unified Vision-Language Forgery Detection and Grounding via Balanced RL [63.388513841293616]
  Existing forgery detection methods fail to handle the interleaved text, images, and videos prevalent in real-world misinformation.<n>To bridge this gap, this paper targets to develop a unified framework for omnibus vision-language forgery detection and grounding.<n>We propose textbf OmniVL-Guard, a balanced reinforcement learning framework for omnibus vision-language forgery detection and grounding.
  arXiv  Detail & Related papers  (2026-02-11T09:41:36Z)
• MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization [56.074760766965085]
  Group-Relative Policy Optimization has emerged as an efficient paradigm for aligning Large Language Models (LLMs)<n>We propose MAESTRO, which treats reward scalarization as a dynamic latent policy, leveraging the model's terminal hidden states as a semantic bottleneck.<n>We formulate this as a contextual bandit problem within a bi-level optimization framework, where a lightweight Conductor network co-evolves with the policy by utilizing group-relative advantages as a meta-reward signal.
  arXiv  Detail & Related papers  (2026-01-12T05:02:48Z)
• Generalized Trajectory Scoring for End-to-end Multimodal Planning [42.38746285135693]
  Generalized Trajectory Scoring (GTRS) is a unified framework for end-to-end multi-modal planning.<n>GTRS consists of three complementary innovations: (1) a diffusion-based trajectory generator that produces diverse fine-grained proposals; (2) a vocabulary generalization technique that trains a scorer on super-dense trajectory sets with dropout regularization; and (3) a sensor augmentation strategy that enhances out-of-domain generalization.<n>As the winning solution of the Navsim v2 Challenge, GTRS demonstrates superior performance even with sub-optimal sensor inputs.
  arXiv  Detail & Related papers  (2025-06-07T05:06:05Z)
• 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)
• RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning [60.84707424369494]
  Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models (LLMs) on complex tasks.<n>We introduce the Reasoning Boundary Framework++ (RBF++), a framework for evaluating and optimizing measurable boundaries of CoT capability.
  arXiv  Detail & Related papers  (2025-05-19T16:25:55Z)
• CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models [14.453131020178564]
  This paper proposes a versatile MSTI framework with a coarse-to-fine paradigm, by augmenting sarcasm explainability with reasoning and pre-training knowledge. Inspired by the powerful capacity of Large Multimodal Models (LMMs) on multimodal reasoning, we first engage LMMs to generate competing rationales for coarser-grained pre-training of a small language model on multimodal sarcasm detection. We then propose fine-tuning the model for finer-grained sarcasm target identification. Our framework is thus empowered to adeptly unveil the intricate targets within multimodal sarcasm and mitigate the negative impact posed by potential noise inherently in LMMs.
  arXiv  Detail & Related papers  (2024-05-01T08:44:44Z)
• TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection [18.015012133043093]
  We propose TOT: a topology-aware optimal transport framework to decipher the implicit harm in memes scenario. Specifically, we leverage an optimal transport kernel method to capture complementary information from multiple modalities. The newly achieved state-of-the-art performance on two publicly available benchmark datasets, together with further visual analysis, demonstrate the superiority of TOT.
  arXiv  Detail & Related papers  (2023-02-27T06:58:19Z)

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.