SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.13632 · EMNLP · 2023

Detecting and Mitigating Hallucinations in Multilingual Summarisation

Shay Cohen, Edoardo Ponti, Yifu Qiu, Yftah Ziser, Anna Korhonen

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Hallucinations pose a significant challenge to the reliability of neural models for abstractive summarisation. While automatically generated summaries may be fluent, they often lack faithfulness to the original document. This issue becomes even more pronounced in lowresource languages, where summarisation requires cross-lingual transfer. With the existing faithful metrics focusing on English, even measuring the extent of this phenomenon in crosslingual settings is hard. To address this, we first develop a novel metric, mFACT, evaluating the faithfulness of non-English summaries, leveraging translation-based transfer from multiple English faithfulness metrics. Through extensive experiments in multiple languages, we demonstrate that mFACT is best suited to detect hallucinations compared to alternative metrics. With mFACT, we assess a broad range of multilingual large language models, and find that they all tend to hallucinate often in languages different from English. We then propose a simple but effective method to reduce hallucinations in cross-lingual transfer, which weighs the loss of each training example by its faithfulness score. This method drastically increases both performance and faithfulness according to both automatic and human evaluation when compared to strong baselines for cross-lingual transfer such as MAD-X. Our code and dataset are available at https: //github.com/yfqiu-nlp/mfact-summ.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.13632")
get_code_for_paper("2305.13632")
have("2305.13632")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.13632.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.13632.svg)](https://syntology.ai/paper/2305.13632)

Connect an agent — have() is free.