# Towards Faithful Sentimental Image Captioning via Evidence-Aware Multi-Agent Reasoning

arXiv: https://arxiv.org/abs/2607.25789 · HTML: https://mlsanity.com/paper/2607.25789/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 25 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Object Hallucination in Image Captioning](https://mlsanity.com/paper/1809.02156/) (2018)
- [Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs](https://mlsanity.com/paper/2003.00387/) (2020)
- [SentiCap: Generating Image Descriptions with Sentiments](https://mlsanity.com/paper/1510.01431/) (2015)
- [Length-Controllable Image Captioning](https://mlsanity.com/paper/2007.09580/) (2020)
- [ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing](https://mlsanity.com/paper/2303.02437/) (2023)
- [SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text](https://mlsanity.com/paper/1805.07030/) (2018)
- [Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage](https://mlsanity.com/paper/2412.15484/) (2024)
- [Controllable Image Captioning via Prompting](https://mlsanity.com/paper/2212.01803/) (2022)
- [Zero-Shot Strategies for Length-Controllable Summarization](https://mlsanity.com/paper/2501.00233/) (2024)
- [PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness](https://mlsanity.com/paper/2410.07035/) (2024)
- [The Power of Many: Multi-Agent Multimodal Models for Cultural Image Captioning](https://mlsanity.com/paper/2411.11758/) (2024)
- [Length Controlled Generation for Black-box LLMs](https://mlsanity.com/paper/2412.14656/) (2024)

## Abstract (arXiv)

Sentimental Image Captioning (SIC) requires balancing emotional expression with visual fidelity. Existing methods often struggle with this trade-off, leading to hallucinations due to insufficient local grounding and the lack of sentimental verification mechanisms. To address these limitations, we propose SEA-Cap, a Sentiment-Evidence-Aware Multi-Agent System for faithful and evidence-grounded sentimental image captioning. SEA-Cap incorporates a Sentiment Evidence Miner that extracts structured, local affective cues to shift sentiment control from global attributes to verifiable object-level evidence. Leveraging this evidence, our framework orchestrates a collaborative workflow where a Generator, Hallucination Checker, and Arbitrator iteratively refine captions via a shared blackboard. By explicitly auditing generated content against mined visual evidence, SEA-Cap ensures both sentiment accuracy and factual consistency. Extensive experiments on two benchmark datasets demonstrate that SEA-Cap effectively mitigates hallucinations and achieves state-of-the-art performance.