Related papers: ODSum: New Benchmarks for Open Domain Multi-Docume…
We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents. Unlike existing multi-document summarization methods, our framework processes documents telling different stories instead of…
Long-form video content constitutes a significant portion of internet traffic, making automated video summarization an essential research problem. However, existing video summarization datasets are notably limited in their size,…
Document retrieval is one of the most challenging tasks in Information Retrieval. It requires handling longer contexts, often resulting in higher query latency and increased computational overhead. Recently, Learned Sparse Retrieval (LSR)…
While large language models (LLMs) are increasingly capable of handling longer contexts, recent work has demonstrated that they exhibit the "lost in the middle" phenomenon (Liu et al., 2024) of unevenly attending to different parts of the…
We present a novel system providing summaries for Computer Science publications. Through a qualitative user study, we identified the most valuable scenarios for discovery, exploration and understanding of scientific documents. Based on…
Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains. In this paper, we propose SummPip: an unsupervised method for…
Long video summarization presents significant challenges for current multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and…
Contextual Markov Decision Processes (CMDPs) offer a framework for sequential decision-making under external signals, but existing methods often fail to generalize in high-dimensional or unstructured contexts, resulting in excessive…
The ever-increasing volume of digital information necessitates efficient methods for users to extract key insights from lengthy documents. Aspect-based summarization offers a targeted approach, generating summaries focused on specific…
Summarizing deeply nested discussion threads requires handling interleaved replies, quotes, and overlapping topics, which standard LLM summarizers struggle to capture reliably. We introduce ThreadSumm, a multi-stage LLM framework that…
Extracting summaries from long documents can be regarded as sentence classification using the structural information of the documents. How to use such structural information to summarize a document is challenging. In this paper, we propose…
Large language models (LLMs) have rapidly evolved from text generators into powerful problem solvers. Yet, many open tasks demand critical thinking, multi-source, and verifiable outputs, which are beyond single-shot prompting or standard…
Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key…
Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. Despite recent advances in visual document understanding, the…
Relevance judgments are central to the evaluation of Information Retrieval (IR) systems, but obtaining them from human annotators is costly and time-consuming. Large Language Models (LLMs) have recently been proposed as automated assessors,…
Multi-document summaritazion is the process of taking multiple texts as input and producing a short summary text based on the content of input texts. Up until recently, multi-document summarizers are mostly supervised extractive. However,…
Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network and directly maps queries to corresponding documents. These…
Text summarization helps readers capture salient information from documents, news, interviews, and meetings. However, most state-of-the-art pretrained language models (LM) are unable to efficiently process long text for many summarization…
Existing research on news summarization primarily focuses on single-language single-document (SLSD), single-language multi-document (SLMD) or cross-language single-document (CLSD). However, in real-world scenarios, news about a…
We develop and evaluate multilingual scientific documents similarity measurement models in this work. Such models can be used to find related works in different languages, which can help multilingual researchers find and explore papers more…