Pith. sign in

REVIEW 4 cited by

Image Captioning Evaluation in the Age of Multimodal LLMs: Challenges and Future Perspectives

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.14604 v2 pith:EE245KRE submitted 2025-03-18 cs.CV cs.AIcs.CL

classification cs.CVcs.AIcs.CL
keywords evaluationimagecaptioningmetricscaptionschallengesfuturelimitations
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable evaluation metrics. This survey provides a comprehensive overview of advancements in image captioning evaluation, analyzing the evolution, strengths, and limitations of existing metrics. We assess these metrics across multiple dimensions, including correlation with human judgment, ranking accuracy, and sensitivity to hallucinations. Additionally, we explore the challenges posed by the longer and more detailed captions generated by MLLMs and examine the adaptability of current metrics to these stylistic variations. Our analysis highlights some limitations of standard evaluation approaches and suggests promising directions for future research in image captioning assessment.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Existing MLLM unlearning methods reduce private-attribute leakage on entangled images but substantially harm co-occurring public figures and landmarks, with private knowledge often re-emerging after public finetuning.

  2. A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions

    cs.CV 2026-07 conditional novelty 5.0 of 10

    Reference-free caption quality is scored by the downstream vision-language accuracy of a caption-conditioned reconstructed image, via a new CTTD benchmark.

  3. LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning

    cs.AI 2026-07 conditional novelty 5.0 of 10

    LenGuard-GPC adds a token-level KL consistency reward between standard and guided prompts, plus a staged length bonus, to GRPO training of Qwen3-VL-8B and reports better accuracy with shorter responses on multi-view s...

  4. Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment

    cs.CV 2025-05 conditional novelty 5.0 of 10

    FOA-Attack aligns global and clustered local features via optimal transport with dynamic ensemble weighting to create targeted adversarial images that transfer to closed-source multimodal LLMs.

Pith tools