6 accepted papers
Abstractive dialogue summarization is the task of distilling conversations into informative and concise summaries. Although focused reviews have been conducted on this topic, there is a lack of comprehensive work that details the core challenges of dialogue summarization, unifies the differing under
Meeting summarization with large language models (LLMs) remains error-prone, often producing outputs with hallucinations, omissions, and irrelevancies. We present FRAME, a modular pipeline that reframes summarization as a semantic enrichment task. FRAME extracts and scores salient facts, organizes t
Meeting summarization suffers from limited high-quality data, mainly due to privacy restrictions and expensive collection processes. We address this gap with FAME, a dataset of 500 meetings in English and 300 in German produced by MIMIC, our new multi-agent meeting synthesis framework that generates…
Meeting summarization is crucial in digital communication, but existing solutions struggle with salience identification to generate personalized, workable summaries, and context understanding to fully comprehend the meetings’ content.Previous attempts to address these issues by considering related s…
Meeting summarization has become a critical task considering the increase in online interactions. Despite new techniques being proposed regularly, the evaluation of meeting summarization techniques relies on metrics not tailored to capture meeting-specific errors, leading to ineffective assessment.…
The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work.However, the role of large autoregressive models in generating machine-paraphrased plagiarism and their…