In this paper, we present a systematic survey and methodological guidelines for explanation evaluation and statistical significance testing in explainable NLP (XAI). We systematically reviewed 494 verified papers from the ACL Anthology (2020–2025) to identify how explanations are evaluated and the frequency of statistical validation. Our analysis identifies a persistent **rigour gap**: although **the number of explainable NLP papers increased fivefold** during the study period, there was **no corresponding increase in the use of explanation-specific statistical testing**. Across the full corpus, only 25.30% (125/494) of studies substantiate evaluation claims with hypothesis testing. This remains a minority practice in every surveyed year. We categorise the primary barriers to rigour into three issues: implicit generalisation, inferential reporting gap, and incomplete rigour. To address these, we propose a bipartite framework that maps research hypotheses to appropriate statistical testing regimes. Our goal is to clarify when statistical testing is necessary and to provide a guideline for more rigorous, reproducible explainability research in the LLM era.

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside a training dataset (1 million instances). Our findings show that while VLMs perform better with correct location context, they struggle with adversarial contexts and predicting specific regional cuisines and languages. To support future research, we release a knowledge base with annotated food entries and images along with the VQA data.

Interpretation methods provide saliency scores indicating the importance of input words for neural summarization models. Prior work has analyzed models by comparing them to human behavior, often using eye-gaze as a proxy for human attention in reading tasks such as classification. This paper presents a framework to analyze the model behavior in summarization by comparing it to human summarization behavior using eye-gaze data. We examine two research questions: RQ1) whether model saliency conforms to human gaze during summarization and RQ2) how model saliency and human gaze affect summarization performance. For RQ1, we measure conformity by calculating the correlation between model saliency and human fixation counts. For RQ2, we conduct ablation experiments removing words/sentences considered important by models or humans. Experiments on two datasets with human eye-gaze during summarization partially confirm that model saliency aligns with human gaze (RQ1). However, ablation experiments show that removing highly-attended words/sentences from the human gaze does not significantly degrade performance compared with the removal by the model saliency (RQ2).

Most Semantic Role Labeling (SRL) approaches are supervised methods which require a significant amount of annotated corpus, and the annotation requires linguistic expertise. In this paper, we propose a Multi-Task Active Learning framework for Semantic Role Labeling with Entity Recognition (ER) as the auxiliary task to alleviate the need for extensive data and use additional information from ER to help SRL. We evaluate our approach on Indonesian conversational dataset. Our experiments show that multi-task active learning can outperform single-task active learning method and standard multi-task learning. According to our results, active learning is more efficient by using 12% less of training data compared to passive learning in both single-task and multi-task setting. We also introduce a new dataset for SRL in Indonesian conversational domain to encourage further research in this area.