Challenge: Existing MLLMs rely on commercial models such as GPT-4o for evaluations, but they are not universally accessible.
Approach: They propose a task decomposition evaluation framework based on GPT-4o to automatically construct a specialized training dataset to break down the multifaceted evaluation process into simpler sub-tasks.
Outcome: The proposed framework outperforms the current state-of-the-art GPT-4o evaluation framework with over 4.6% improvement in Spearman and Kendall correlations with human judgments.

Similar Papers

GPTScore: Evaluate as You Desire (2024.naacl-long)

Copied to clipboard

Challenge: Existing evaluation frameworks for text generation are not adequate to assess the quality of the generated outputs.
Approach: They propose a framework that utilizes emergent abilities of generative pre-trained models to evaluate generated texts.
Outcome: The proposed evaluation framework can achieve what one desires to evaluate for texts simply by natural language instructions.
Holistic Evaluation for Interleaved Text-and-Image Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation benchmarks do not support arbitrarily interleaved images and text for both inputs and outputs.
Approach: They propose to use a benchmark to evaluate interleaved text-and-image generation . they define five evaluation aspects for InterleavatedEval, a reference-free metric .
Outcome: The proposed benchmarks cover a limited number of domains and use cases and lack comparableity-based metrics.
Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks (2023.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape . established automatic evaluation metrics are poor surrogates, correlating weakly with human judgement.
Approach: They propose to use both automatic and human evaluation to evaluate generative LLMs on three NLP benchmarks: text summarisation, text simplification and grammatical error correction.
Outcome: The proposed model outperforms many popular models according to human reviewers on the majority of metrics, while scoring much worse when using classic automatic evaluation metrics.
AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models (2025.emnlp-main)

Copied to clipboard

Challenge: Text-to-Image (T2I) models have been successful in generating images from textual descriptions, but they struggle to capture nuanced and implicit attributes inherent in action depiction.
Approach: They propose a benchmark to evaluate the performance of T2I models in generating images from action-centric prompts.
Outcome: The proposed model achieves an increase of 72% on AcT2I.
VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation (2024.acl-long)

Copied to clipboard

Challenge: Existing metrics for conditional image generation are opaque and lack explainability . evaluators of these metrics have limited ability to evaluate image synthesis tasks .
Approach: They propose a Visual Instruction-guided Explainable metric for evaluating conditional image models.
Outcome: The proposed model achieves a high Spearman correlation with human evaluations, but is weaker than GPT-4o and GPT-v in evaluating synthetic images.
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes (2023.acl-long)

Copied to clipboard

Challenge: Existing learned metrics perform unsatisfactory across text generation tasks or require human annotations for training on specific tasks.
Approach: They propose a self-supervised approach to train a model-based metric for text generation evaluation using sentences retrieved from a corpus.
Outcome: The proposed model outperforms all prior unsupervised metrics on four text generation evaluation benchmarks, with an average Kendall improvement of 0.158.
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods assess only one aspect of the task, misalign with human judgments or rely on costly API-based evaluation.
Approach: RefVNLI evaluates textual alignment and subject preservation in a single run.
Outcome: RefVNLI outperforms or matches existing baselines across multiple benchmarks and subject categories.
DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering (2023.acl-long)

Copied to clipboard

Challenge: Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability.
Approach: They propose a metric that evaluates natural language generation tasks as an instruction-style question answering task and utilizes instruction-tuned pre-trained language models without training on evaluation datasets.
Outcome: The proposed metric achieves state-of-the-art performance in untrained metrics for evaluating text summarization and dialogue generation, which exhibits strong dimension-level / task-level generalization ability and interpretability.
VizSeq: a visual analysis toolkit for text generation tasks (D19-3)

Copied to clipboard

Challenge: Several softwares for text evaluation are available that do not provide detailed examples.
Approach: They propose a visual analysis toolkit for instance-level and corpus-level system evaluation on a wide variety of text generation tasks.
Outcome: The proposed toolkit covers most common n-gram metrics and latest embedding-based metrics such as BERTScore.
MEGA: Multilingual Evaluation of Generative AI (2023.emnlp-main)

Copied to clipboard

Challenge: Large Large Models (LLMs) have shown impressive performance on many natural language processing tasks such as language understanding, reasoning, and language generation.
Approach: They present a framework for evaluating generative LLMs in the multilingual setting and provide directions for future progress in the field.
Outcome: The proposed framework evaluates generative models on 16 NLP datasets across 70 typologically diverse languages and compares them to state-of-the-art non-autoregressive models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations