English
Related papers

Related papers: Why We Need New Evaluation Metrics for NLG

200 papers

Text generation is an important Natural Language Processing task with various applications. Although several metrics have already been introduced to evaluate the text generation methods, each of them has its own shortcomings. The most…

Machine Learning · Computer Science 2019-05-22 Ehsan Montahaei , Danial Alihosseini , Mahdieh Soleymani Baghshah

Behavioral testing in NLP allows fine-grained evaluation of systems by examining their linguistic capabilities through the analysis of input-output behavior. Unfortunately, existing work on behavioral testing in Machine Translation (MT) is…

Computation and Language · Computer Science 2023-11-06 Javier Ferrando , Matthias Sperber , Hendra Setiawan , Dominic Telaar , Saša Hasan

The state-of-the-art language model-based automatic metrics, e.g. BARTScore, benefiting from large-scale contextualized pre-training, have been successfully used in a wide range of natural language generation (NLG) tasks, including machine…

Computation and Language · Computer Science 2022-12-21 Qingyu Lu , Liang Ding , Liping Xie , Kanjian Zhang , Derek F. Wong , Dacheng Tao

We present FLUKE (Framework for LingUistically-driven and tasK-agnostic robustness Evaluation), a framework for assessing model robustness through systematic minimal variations of test data. FLUKE introduces controlled variations across…

Computation and Language · Computer Science 2026-02-23 Yulia Otmakhova , Hung Thinh Truong , Rahmad Mahendra , Zenan Zhai , Rongxin Zhu , Daniel Beck , Jey Han Lau

Natural language processing researchers have identified limitations of evaluation methodology for generation tasks, with new questions raised about the validity of automatic metrics and of crowdworker judgments. Meanwhile, efforts to…

Computation and Language · Computer Science 2022-05-20 Jungo Kasai , Keisuke Sakaguchi , Ronan Le Bras , Lavinia Dunagan , Jacob Morrison , Alexander R. Fabbri , Yejin Choi , Noah A. Smith

Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is…

Computation and Language · Computer Science 2024-09-19 Gaurav Maheshwari , Dmitry Ivanov , Kevin El Haddad

Fast and reliable evaluation metrics are key to R&D progress. While traditional natural language generation metrics are fast, they are not very reliable. Conversely, new metrics based on large pretrained language models are much more…

Computation and Language · Computer Science 2021-10-19 Moussa Kamal Eddine , Guokan Shang , Antoine J. -P. Tixier , Michalis Vazirgiannis

Performance of NLP systems is typically evaluated by collecting a large-scale dataset by means of crowd-sourcing to train a data-driven model and evaluate it on a held-out portion of the data. This approach has been shown to suffer from…

Computation and Language · Computer Science 2024-08-12 Viktor Schlegel , Goran Nenadic , Riza Batista-Navarro

Most research about natural language generation (NLG) relies on evaluation benchmarks with limited references for a sample, which may result in poor correlations with human judgements. The underlying reason is that one semantic meaning can…

Computation and Language · Computer Science 2024-05-28 Tianyi Tang , Hongyuan Lu , Yuchen Eleanor Jiang , Haoyang Huang , Dongdong Zhang , Wayne Xin Zhao , Tom Kocmi , Furu Wei

Meta-analyses statistically aggregate the findings of different randomized controlled trials (RCTs) to assess treatment effectiveness. Because this yields robust estimates of treatment effectiveness, results from meta-analyses are…

Computation and Language · Computer Science 2024-07-26 Hye Sun Yun , David Pogrebitskiy , Iain J. Marshall , Byron C. Wallace

We introduce a simple approach that uses a large language model (LLM) to automatically implement a fully interpretable rule-based data-to-text system in pure Python. Experimental evaluation on the WebNLG dataset showed that such a…

Computation and Language · Computer Science 2025-03-03 Jędrzej Warczyński , Mateusz Lango , Ondrej Dusek

Commit messages are natural language descriptions of code changes, which are important for program understanding and maintenance. However, writing commit messages manually is time-consuming and laborious, especially when the code is updated…

Software Engineering · Computer Science 2021-07-27 Wei Tao , Yanlin Wang , Ensheng Shi , Lun Du , Shi Han , Hongyu Zhang , Dongmei Zhang , Wenqiang Zhang

Large language model (LLM) evaluation is increasingly costly, prompting interest in methods that speed up evaluation by shrinking benchmark datasets. Benchmark prediction (also called efficient LLM evaluation) aims to select a small subset…

Machine Learning · Computer Science 2025-06-10 Guanhua Zhang , Florian E. Dorner , Moritz Hardt

Business processes are fundamental to organizational operations, yet their optimization remains challenging due to the timeconsuming nature of manual process analysis. Our paper harnesses Large Language Models (LLMs) to automate value-added…

Computation and Language · Computer Science 2025-04-10 William De Michele , Abel Armas Cervantes , Lea Frermann

Regulatory efforts to govern large language model (LLM) development have predominantly focused on restricting access to high-performance computational resources. This study evaluates the efficacy of such measures by examining whether LLM…

Machine Learning · Computer Science 2025-06-06 Jack Sanderson , Teddy Foley , Spencer Guo , Anqi Qu , Henry Josephson

In Machine Learning, a benchmark refers to an ensemble of datasets associated with one or multiple metrics together with a way to aggregate different systems performances. They are instrumental in (i) assessing the progress of new methods…

Computation and Language · Computer Science 2022-10-10 Pierre Colombo , Nathan Noiry , Ekhine Irurozki , Stephan Clemencon

Large language models (LLMs) enable rapid and consistent automated evaluation of open-ended exam responses, including dimensions of content and argumentation that have traditionally required human judgment. This is particularly important in…

Computation and Language · Computer Science 2026-01-26 Andres Karjus , Kais Allkivi , Silvia Maine , Katarin Leppik , Krister Kruusmaa , Merilin Aruvee

Model-based, reference-free evaluation metrics have been proposed as a fast and cost-effective approach to evaluate Natural Language Generation (NLG) systems. Despite promising recent results, we find evidence that reference-free evaluation…

Computation and Language · Computer Science 2022-04-22 Esin Durmus , Faisal Ladhak , Tatsunori Hashimoto

LLM applications are AI systems whose nondeterministic outputs and evolving model behavior make traditional testing insufficient for release governance. We present an automated self-testing framework that introduces quality gates with…

Software Engineering · Computer Science 2026-05-22 Alexandre Cristovão Maiorano

Text style transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy,…

Computation and Language · Computer Science 2025-04-24 Sourabrata Mukherjee , Atul Kr. Ojha , John P. McCrae , Ondrej Dusek