相关论文: BanglaSummEval: Reference-Free Factual Consistency…

Multimodal summarization aims to generate a concise summary based on the input text and image. However, the existing methods potentially suffer from unfactual output. To evaluate the factuality of multimodal summarization models, we propose…

Text summarization models are often trained to produce summaries that meet human quality requirements. However, the existing evaluation metrics for summary text are only rough proxies for summary quality, suffering from low correlation with…

We propose a new reference-free summary quality evaluation measure, with emphasis on the faithfulness. The measure is designed to find and count all possible minute inconsistencies of the summary with respect to the source document. The…

Despite the success of the neural sequence-to-sequence model for abstractive text summarization, it has a few shortcomings, such as repeating inaccurate factual details and tending to repeat themselves. We propose a hybrid pointer generator…

Automatic Speech Recognition (ASR) transcripts, especially in low-resource languages like Bangla, contain a critical ambiguity: word-word repetitions can be either Repetition Disfluency (unintentional ASR error/hesitation) or Morphological…

Evaluating text comprehension in educational settings is critical for understanding student performance and improving curricular effectiveness. This study investigates the capability of state-of-the-art language models-RoBERTa Base,…

Evaluating the factual consistency of abstractive text summarization remains a significant challenge, particularly for long documents, where conventional metrics struggle with input length limitations and long-range dependencies. In this…

Improving factual consistency of abstractive summarization has been a widely studied topic. However, most of the prior works on training factuality-aware models have ignored the negative effect it has on summary quality. We propose EFACTSUM…

A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce…

Hallucinated outputs from large language models (LLMs) pose risks in the medical domain, especially for lay audiences making health-related decisions. Existing automatic factual consistency evaluation methods, such as entailment- and…

Summarizing consumer health questions (CHQs) can ease communication in healthcare, but unfaithful summaries that misrepresent medical details pose serious risks. We propose a framework that combines TextRank-based sentence extraction and…

Current pre-trained models applied to summarization are prone to factual inconsistencies which either misrepresent the source text or introduce extraneous information. Thus, comparing the factual consistency of summaries is necessary as we…

Question-Answering (QA) models for low-resource languages like Bangla face challenges due to limited annotated data and linguistic complexity. A key issue is determining whether models rely more on pre-encoded (parametric) knowledge or…

Multimodal Large Language Models (MLLMs) have facilitated Multimodal Summarization with Multimodal Output (MSMO), wherein systems generate concise textual summaries accompanied by salient visuals from multimodal sources. However, current…

Being one of the most widely spoken language in the world, the use of Bangla has been increasing in the world of social media as well. Sarcasm is a positive statement or remark with an underlying negative motivation that is extensively…

Existing benchmarks for summarization quality evaluation often lack diverse input scenarios, focus on narrowly defined dimensions (e.g., faithfulness), and struggle with subjective and coarse-grained annotation schemes. To address these…

Cutting-edge abstractive summarisers generate fluent summaries, but the factuality of the generated text is not guaranteed. Early summary factuality evaluation metrics are usually based on n-gram overlap and embedding similarity, but are…

Despite the recent progress in language generation models, their outputs may not always meet user expectations. In this work, we study whether informational feedback in natural language can be leveraged to improve generation quality and…

Extractive Text Summarization is the process of selecting the most representative parts of a larger text without losing any key information. Recent attempts at extractive text summarization in Bengali, either relied on statistical…

While large language models (LLMs) have proven to be effective on a large variety of tasks, they are also known to hallucinate information. To measure whether an LLM prefers factually consistent continuations of its input, we propose a new…