Related papers: Towards a Decomposable Metric for Explainable Eval…
Traditional automated metrics for evaluating conditional natural language generation use pairwise comparisons between a single generated text and the best-matching gold-standard ground truth text. When multiple ground truths are available,…
A major challenge in the field of Text Generation is evaluation: Human evaluations are cost-intensive, and automated metrics often display considerable disagreement with human judgments. In this paper, we propose a statistical model of Text…
Layered image generation and editing is a fundamental capability that enables layer-wise reuse, editing, and composition of generated visual content, analogous to word-level editing in natural language. Despite its importance, this remains…
The advent of NMT has expanded the scope of translation beyond isolated sentences, enabling context to be preserved across paragraphs and documents. However, current evaluation metrics largely remain restricted to the sentence level and…
Several code summarization techniques have been proposed in the literature to automatically document a code snippet or a function. Ideally, software developers should be involved in assessing the quality of the generated summaries. However,…
While machine-generated texts (MGTs) offer great convenience, they also pose risks such as disinformation and phishing, highlighting the need for reliable detection. Metric-based methods, which extract statistically distinguishable features…
Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…
Human evaluation is critical for validating the performance of text-to-image generative models, as this highly cognitive process requires deep comprehension of text and images. However, our survey of 37 recent papers reveals that many works…
The acceleration of Large Language Models (LLMs) research has opened up new possibilities for evaluating generated texts. They serve as scalable and economical evaluators, but the question of how reliable these evaluators are has emerged as…
In this work, we explore a useful but often neglected methodology for robustness analysis of text generation evaluation metrics: stress tests with synthetic data. Basically, we design and synthesize a wide range of potential errors and…
We propose a method to control the attributes of Language Models (LMs) for the text generation task using Causal Average Treatment Effect (ATE) scores and counterfactual augmentation. We explore this method, in the context of LM…
This study presents a new approach to metaphorical paraphrase generation by masking literal tokens of literal sentences and unmasking them with metaphorical language models. Unlike similar studies, the proposed algorithm does not only focus…
Recent advances in large language models and vision-language models have led to growing interest in explainable evaluation metrics for image captioning. However, these metrics generate explanations without standardized criteria, and the…
Despite demonstrating remarkable performance across a wide range of tasks, large language models (LLMs) have also been found to frequently produce outputs that are incomplete or selectively omit key information. In sensitive domains, such…
Large Language Models have significantly advanced natural language processing tasks, but remain prone to generating incorrect or misleading but plausible arguments. This issue, known as hallucination, is particularly concerning in…
Evaluating the compatibility between textual descriptions and corresponding images represents a core endeavor within multi-modal research. In recent years, a proliferation of reference-free methods, leveraging visual-language pre-trained…
In this paper, we propose a new metric for Machine Translation (MT) evaluation, based on bi-directional entailment. We show that machine generated translation can be evaluated by determining paraphrasing with a reference translation…
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…
Current evaluation metrics for language modeling and generation rely heavily on the accuracy of predicted (or generated) words as compared to a reference ground truth. While important, token-level accuracy only captures one aspect of a…
We propose BERTScore, an automatic evaluation metric for text generation. Analogously to common metrics, BERTScore computes a similarity score for each token in the candidate sentence with each token in the reference sentence. However,…