German also Hallucinates! Inconsistency Detection in News Summaries with the Absinth Dataset
(2403.03750)Abstract
The advent of LLMs has led to remarkable progress on a wide range of natural language processing tasks. Despite the advances, these large-sized models still suffer from hallucinating information in their output, which poses a major issue in automatic text summarization, as we must guarantee that the generated summary is consistent with the content of the source document. Previous research addresses the challenging task of detecting hallucinations in the output (i.e. inconsistency detection) in order to evaluate the faithfulness of the generated summaries. However, these works primarily focus on English and recent multilingual approaches lack German data. This work presents absinth, a manually annotated dataset for hallucination detection in German news summarization and explores the capabilities of novel open-source LLMs on this task in both fine-tuning and in-context learning settings. We open-source and release the absinth dataset to foster further research on hallucination detection in German.
Overview
-
The ABSINTH dataset is a pioneering resource in NLP for detecting inconsistencies in German news summaries, featuring 4,314 annotated pairs of articles and summaries.
-
It categorizes inconsistencies into intrinsic (counterfactual information) and extrinsic (unverifiable information) hallucinations, with summaries from various models including GPT-4 and LLama 2.
-
Experiments with open-source LLMs, especially mBERT, on the ABSINTH dataset show promising results in inconsistency detection within a few-shot and zero-shot setting.
-
This research highlights the need for more robust models in non-English NLP tasks and opens up new research avenues in inconsistency detection and automatic text summarization improvement.
Inconsistency Detection in German News Summaries: Introducing the ABSINTH Dataset
Overview of the ABSINTH Dataset
The ABSINTH dataset represents a significant advancement in the field of NLP, specifically focusing on the detection of hallucinations in German news article summaries. The dataset comprises 4,314 manually annotated pairs of news articles and their corresponding summaries. These annotations differentiate between two types of hallucinations: intrinsic, where the summary contains counterfactual information, and extrinsic, where additional, unverifiable information is added to the summary. The inclusion of summaries generated by a range of models, from pre-trained language models specifically fine-tuned for German summarization to the latest prompt-based LLMs like GPT-4 and LLama 2, makes this dataset a comprehensive resource for studying summarization inconsistencies in the German language.
Dataset Construction and Annotation
The dataset construction involved a careful selection of 200 articles from the "20Minuten" test split, ensuring a variety of source material. Summaries were generated using an array of models, including multilingual transformer-based models and cutting-edge LLMs, with a focus on producing diverse examples of factual consistency and hallucinations. The annotation process was meticulously designed to ensure the high quality of the labels assigned to each summary sentence. This involved training and continuous monitoring of annotators, ensuring an agreement level indicative of reliable data quality.
Experimentation with Open-Source LLMs
The paper reports on experiments assessing the effectiveness of recent open-source LLMs in detecting inconsistencies in the generated summaries. This involved not only fine-tuning these models on the ABSINTH dataset but also exploring their performance in zero-shot and few-shot settings. Among the significant findings, mBERT emerged as a particularly effective model for this task, outperforming other LLMs in detecting both intrinsic and extrinsic hallucinations.
Implications and Future Directions
The ABSINTH dataset opens new avenues for research into inconsistency detection in non-English languages, addressing a gap in the field of NLP. The experiments conducted demonstrate the potential of fine-tuning well-established transformer models like mBERT for this purpose. However, they also highlight the challenges faced by state-of-the-art LLMs in generalizing their performance to tasks like hallucination detection. Future work may explore the development of more sophisticated models or annotation techniques that can further enhance the accuracy and reliability of inconsistency detection.
Conclusion
The creation of the ABSINTH dataset marks a significant step towards understanding and improving the quality of automated news article summarization in German. It provides a valuable resource for developing and benchmarking NLP models capable of identifying inconsistencies in text summarization. The research presented not only sheds light on the current capabilities and limitations of existing models but also sets the stage for future advancements in the domain of trustworthy and reliable automatic text summarization.
Create an account to read this summary for free: