paper-with-me

홈 › Papers

Truth or Error? Towards systematic analysis of factual errors in abstractive summaries

2020-11-01 · EMNLP (Eval4NLP) 2020 11 · Klaus-Michael Lux, Maya Sappelli, Martha Larson

This paper presents a typology of errors produced by automatic summarization systems. The typology was created by manually analyzing the output of four recent neural summarization systems. Our work is motivated by the growing awareness of the need for better summary evaluation methods that go beyond conventional overlap-based metrics. Our typology is structured into two dimensions. First, the Mapping Dimension describes surface-level errors and provides insight into word-sequence transformation issues. Second, the Meaning Dimension describes issues related to interpretation and provides insight into breakdowns in truth, i.e., factual faithfulness to the original text. Comparative analysis revealed that two neural summarization systems leveraging pre-trained models have an advantage in decreasing grammaticality errors, but not necessarily factual errors. We also discuss the importance of ensuring that summary length and abstractiveness do not interfere with evaluating summary quality.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Shortcomings of Question Answering Based Factuality Frameworks for Error Localization

2022-10-13 · Ryo Kamoi, Tanya Goyal, Greg Durrett

Despite recent progress in abstractive summarization, models often generate summaries with factual errors. Numerous approaches to detect these errors have been proposed, the most popular of which are question answering (…

Abstractive Text SummarizationQuestion AnsweringQuestion GenerationQuestion-Generation

FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models

2026-01-16 · Javier Carnerero-Cano, Massimiliano Pronesti, Radu Marinescu, Tigran Tchrakian 외 arxiv

Large language models (LLMs) are widely used in knowledge-intensive applications but often generate factually incorrect responses. A promising approach to rectify these flaws is correcting LLMs using feedback. Therefore,…

CLFEC: A New Task for Unified Linguistic and Factual Error Correction in paragraph-level Chinese Professional Writing

2026-02-27 · Jian Kai, Zidong Zhang, Jiwen Chen, Zhengxiang Wu 외 arxiv

Chinese text correction has traditionally focused on spelling and grammar, while factual error correction is usually treated separately. However, in paragraph-level Chinese professional writing, linguistic (word/grammar/…

LM vs LM: Detecting Factual Errors via Cross Examination

2023-05-22 · Roi Cohen, May Hamri, Mor Geva, Amir Globerson

A prominent weakness of modern language models (LMs) is their tendency to generate factually incorrect text, which hinders their usability. A natural question is whether such factual errors can be detected automatically.…

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

2024-10-03 · Hadas Orgad, Michael Toker, Zorik Gekhman, Roi Reichart 외

Large language models (LLMs) often produce errors, including factual inaccuracies, biases, and reasoning failures, collectively referred to as "hallucinations". Recent studies have demonstrated that LLMs' internal states…