Related papers: Reducing Quantity Hallucinations in Abstractive Su…

Although many studies have investigated and reduced hallucinations in large language models (LLMs) for single-document tasks, research on hallucination in multi-document summarization (MDS) tasks remains largely unexplored. Specifically, it…

Large language models (LLMs) have shown promise on summarization tasks, but they often produce hallucinations, which are unsupported or incorrect statements that limit their reliability in specialized healthcare applications. We introduce…

We introduce a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary. Our work addresses current limitations of models for abstractive summarization that…

Large language models (LLMs) are known to "hallucinate" by generating false or misleading outputs. Hallucinations pose various harms, from erosion of trust to widespread misinformation. Existing hallucination evaluation, however, focuses…

While the reasoning capabilities of Large Language Models (LLMs) excel in analytical tasks such as mathematics and code generation, their utility for abstractive summarization remains widely assumed but largely unverified. To bridge this…

This work presents a new approach to unsupervised abstractive summarization based on maximizing a combination of coverage and fluency for a given length constraint. It introduces a novel method that encourages the inclusion of key terms…

We explore the notion of uncertainty in the context of modern abstractive summarization models, using the tools of Bayesian Deep Learning. Our approach approximates Bayesian inference by first extending state-of-the-art summarization models…

Hallucination is a well-known phenomenon in text generated by large language models (LLMs). The existence of hallucinatory responses is found in almost all application scenarios e.g., summarization, question-answering (QA) etc. For…

Abstractive summarization typically relies on large collections of paired articles and summaries. However, in many cases, parallel data is scarce and costly to obtain. We develop an abstractive summarization system that relies only on large…

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

Large language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we…

Context-grounded hallucinations are cases where model outputs contain information not verifiable against the source text. We study the applicability of LLMs for localizing such hallucinations, as a more practical alternative to existing…

How well can large language models (LLMs) generate summaries? We develop new datasets and conduct human evaluation experiments to evaluate the zero-shot generation capability of LLMs across five distinct summarization tasks. Our findings…

Modern summarization models generate highly fluent but often factually unreliable outputs. This motivated a surge of metrics attempting to measure the factuality of automatically generated summaries. Due to the lack of common benchmarks,…

Hallucination is often regarded as a major impediment for using large language models (LLMs), especially for knowledge-intensive tasks. Even when the training corpus consists solely of true statements, language models still generate…

Hallucinations in large language models (LLMs) during summarization of patient-clinician dialogues pose significant risks to patient care and clinical decision-making. However, the phenomenon remains understudied in the clinical domain,…

Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input. This phenomenon is emphasized in tasks like summarization, in which the…

Large Language Models (LLMs) are increasingly used to generate summaries of software bug reports, including sections such as Steps-to-Reproduce (S2R), Actual Behavior (AB), and Expected Behavior (EB). However, these models frequently…

Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest. Retrieval-augmented language model (RALM) -- which enhances models with up-to-date knowledge -- emerges as a…

Summarization is one of the most common tasks performed by large language models (LLMs), especially in applications like Retrieval-Augmented Generation (RAG). However, existing evaluations of hallucinations in LLM-generated summaries, and…