While large language models (LLMs) have demonstrated remarkable capabilities across a
range of downstream tasks, a significant concern revolves around their propensity to exhibit …

Faithfully correcting factual errors is critical for maintaining the integrity of textual knowledge
bases and preventing hallucinations in sequence-to-sequence models. Drawing on humans' …

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 …

Recent advancements in large vision-language models (LVLMs) have led to significant
progress in generating natural language descriptions for visual content and thus enhancing …

Recent work has explored the capability of large language models (LLMs) to identify and
correct errors in LLM-generated responses. These refinement approaches frequently …

Existing factual consistency evaluation approaches for text summarization provide binary
predictions and limited insights into the weakness of summarization systems. Therefore, we …

Factuality is important to dialogue summarization. Factual error correction (FEC) of model-
generated summaries is one way to improve factuality. Current FEC evaluation that relies on …

Multi-document Summarization (MDS) characterizes compressing information from multiple
source documents to its succinct summary. An ideal summary should encompass all topics …

We explore the design of Marvista—a human-AI collaborative tool that employs a suite of
natural language processing models to provide end-to-end support for reading online news …

Missing information is a common issue of dialogue summarization where some information
in the reference summaries is not covered in the generated summaries. To address this …