EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration

• URL: http://arxiv.org/abs/2512.15528v1
• Date: Wed, 17 Dec 2025 15:30:50 GMT
• Title: EmoCaliber: Advancing Reliable Visual Emotion Comprehension via Confidence Verbalization and Calibration
• Authors: Daiqing Wu, Dongbao Yang, Can Ma. Yu Zhou,
• Abstract summary: Visual EmotionBench (VEC) aims to infer sentiment polarities or emotion categories from affective cues embedded in images.<n>We introduce a three-stage training framework that progressively endows with structured reasoning, teaches to verbalize confidence, and calibrates confidence expression.<n>EmoCaliber demonstrates overall superiority against existing methods in both emotion prediction and confidence estimation.
• Score: 8.485394614072028
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Visual Emotion Comprehension (VEC) aims to infer sentiment polarities or emotion categories from affective cues embedded in images. In recent years, Multimodal Large Language Models (MLLMs) have established a popular paradigm in VEC, leveraging their generalizability to unify VEC tasks defined under diverse emotion taxonomies. While this paradigm achieves notable success, it typically formulates VEC as a deterministic task, requiring the model to output a single, definitive emotion label for each image. Such a formulation insufficiently accounts for the inherent subjectivity of emotion perception, overlooking alternative interpretations that may be equally plausible to different viewers. To address this limitation, we propose equipping MLLMs with capabilities to verbalize their confidence in emotion predictions. This additional signal provides users with an estimate of both the plausibility of alternative interpretations and the MLLMs' self-assessed competence, thereby enhancing reliability in practice. Building on this insight, we introduce a three-stage training framework that progressively endows with structured reasoning, teaches to verbalize confidence, and calibrates confidence expression, culminating in EmoCaliber, a confidence-aware MLLM for VEC. Through fair and comprehensive evaluations on the unified benchmark VECBench, EmoCaliber demonstrates overall superiority against existing methods in both emotion prediction and confidence estimation. These results validate the effectiveness of our approach and mark a feasible step toward more reliable VEC systems. Project page: https://github.com/wdqqdw/EmoCaliber.

Related papers

• ADEPT: RL-Aligned Agentic Decoding of Emotion via Evidence Probing Tools -- From Consensus Learning to Ambiguity-Driven Emotion Reasoning [67.22219034602514]
  We introduce ADEPT (Agentic Decoding of Emotion via Evidence Probing Tools), a framework that reframes emotion recognition as a multi-turn inquiry process.<n> ADEPT transforms an SLLM into an agent that maintains an evolving candidate emotion set and adaptively invokes dedicated semantic and acoustic probing tools.<n>We show that ADEPT improves primary emotion accuracy in most settings while substantially improving minor emotion characterization.
  arXiv  Detail & Related papers  (2026-02-13T08:33:37Z)
• E^2-LLM: Bridging Neural Signals and Interpretable Affective Analysis [54.763420895859035]
  We present ELLM2-EEG-to-Emotion Large Language Model, first MLLM framework for interpretable emotion analysis from EEG.<n>ELLM integrates a pretrained EEG encoder with Q-based LLMs through learnable projection layers, employing a multi-stage training pipeline.<n>Experiments on the dataset across seven emotion categories demonstrate that ELLM2-EEG-to-Emotion Large Language Model achieves excellent performance on emotion classification.
  arXiv  Detail & Related papers  (2026-01-11T13:21:20Z)
• Emotion-Enhanced Multi-Task Learning with LLMs for Aspect Category Sentiment Analysis [3.605122187208041]
  We introduce a novel emotion-enhanced ACSA framework that learns sentiment polarity and category-specific emotions.<n>Our approach enables the model to produce emotional descriptions for each aspect category.<n>We also introduce an emotion refinement mechanism based on the Valence-Arousal-Dominance (VAD) dimensional framework.
  arXiv  Detail & Related papers  (2025-11-24T13:52:42Z)
• Cognitive Inception: Agentic Reasoning against Visual Deceptions by Injecting Skepticism [81.39177645864757]
  We propose textbfInception, a fully reasoning-based agentic reasoning framework to conduct authenticity verification by injecting skepticism.<n>To the best of our knowledge, this is the first fully reasoning-based framework against AIGC visual deceptions.
  arXiv  Detail & Related papers  (2025-11-21T05:13:30Z)
• TiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition [31.4260327895046]
  Multimodal Emotion Recognition aims to accurately identify human emotional states by integrating heterogeneous modalities such as visual, auditory, and textual data.<n>Existing approaches predominantly rely on unified emotion labels to supervise model training, often overlooking a critical challenge: inter-modal emotion conflicts.<n>We propose Typicality-based Consistent-aware Multimodal Emotion Recognition (TiCAL), inspired by the stage-wise nature of human emotion perception.
  arXiv  Detail & Related papers  (2025-11-19T03:49:22Z)
• Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier [53.55996102181836]
  We propose the Emotional Rationale Verifier (ERV) and an Explanation Reward.<n>Our method guides the model to produce reasoning that is explicitly consistent with the target emotion.<n>We show that our approach not only enhances alignment between explanation and prediction but also empowers MLLMs to deliver emotionally coherent, trustworthy interactions.
  arXiv  Detail & Related papers  (2025-10-27T16:40:17Z)
• Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach [29.502292089901825]
  We argue that this inconsistency stems partly from constraints in existing evaluation methods.<n>We propose an Emotion Statement Judgment task that overcomes these constraints.<n>We devise an automated pipeline that efficiently constructs emotion-centric statements with minimal human effort.
  arXiv  Detail & Related papers  (2025-09-26T06:30:39Z)
• Enhancing Multi-Agent Debate System Performance via Confidence Expression [55.34012400580016]
  Multi-Agent Debate (MAD) systems simulate human debate and thereby improve task performance.<n>Some Large Language Models (LLMs) possess superior knowledge or reasoning capabilities for specific tasks, but struggle to clearly communicate this advantage during debates.<n>Inappropriate confidence expression can cause agents in MAD systems to either stubbornly maintain incorrect beliefs or converge prematurely on suboptimal answers.<n>We develop ConfMAD, a MAD framework that integrates confidence expression throughout the debate process.
  arXiv  Detail & Related papers  (2025-09-17T14:34:27Z)
• MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models [108.61337743051483]
  We present MME-Emotion, a systematic benchmark that assesses both emotional understanding and reasoning capabilities of MLLMs.<n>MME-Emotion contains over 6,000 curated video clips with task-specific questioning-answering (QA) pairs, spanning broad scenarios to formulate eight emotional tasks.<n>It incorporates a holistic evaluation suite with hybrid metrics for emotion recognition and reasoning, analyzed through a multi-agent system framework.
  arXiv  Detail & Related papers  (2025-08-11T03:14:55Z)
• Leveraging Label Potential for Enhanced Multimodal Emotion Recognition [6.725011823614421]
  Multimodal emotion recognition (MER) seeks to integrate various modalities to predict emotional states accurately.<n>We introduce a novel model called Label Signal-Guided Multimodal Emotion Recognition (LSGMER) to overcome this limitation.
  arXiv  Detail & Related papers  (2025-04-07T15:00:34Z)
• MR-GSM8K: A Meta-Reasoning Benchmark for Large Language Model Evaluation [60.65820977963331]
  We introduce a novel evaluation paradigm for Large Language Models (LLMs) This paradigm shifts the emphasis from result-oriented assessments, which often neglect the reasoning process, to a more comprehensive evaluation. By applying this paradigm in the GSM8K dataset, we have developed the MR-GSM8K benchmark.
  arXiv  Detail & Related papers  (2023-12-28T15:49:43Z)
• MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition [118.73025093045652]
  We propose a pre-training model textbfMEmoBERT for multimodal emotion recognition. Unlike the conventional "pre-train, finetune" paradigm, we propose a prompt-based method that reformulates the downstream emotion classification task as a masked text prediction. Our proposed MEmoBERT significantly enhances emotion recognition performance.
  arXiv  Detail & Related papers  (2021-10-27T09:57:00Z)

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.