We present LLM-Blender, an ensembling framework designed to attain consistently superior
performance by leveraging the diverse strengths of multiple open-source large language …

Conditional language models are predominantly trained with maximum likelihood estimation
(MLE), giving probability mass to sparsely observed target sequences. While MLE trained …

With direct access to human-written reference as memory, retrieval-augmented generation
has achieved much progress in a wide range of text generation tasks. Since better memory …

Extractive summarization is a crucial task in natural language processing that aims to
condense long documents into shorter versions by directly extracting sentences. The recent …

Abstractive text summarization is a task in natural language processing that automatically
generates the summary from the source document in a human-written form with minimal loss …

Large language models have shown impressive performance across a wide variety of tasks,
including text summarization. In this paper, we show that this strong performance extends to …

Hallucinations pose a significant challenge to the reliability of neural models for abstractive
summarisation. While automatically generated summaries may be fluent, they often lack …

There is a rapidly growing number of open-source Large Language Models (LLMs) and
benchmark datasets to compare them. While some models dominate these benchmarks, no …

Pre-trained language models (PLMs) have achieved remarkable success in natural
language generation (NLG) tasks. Up to now, most NLG-oriented PLMs are pre-trained in an …

Despite significant progress in understanding and improving faithfulness in abstractive
summarization, the question of how decoding strategies affect faithfulness is less studied …