Saved in:
Bibliographic Details
Main Authors: Leiser, Florian, Eckhardt, Sven, Leuthe, Valentin, Knaeble, Merlin, Maedche, Alexander, Schwabe, Gerhard, Sunyaev, Ali
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.06710
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913357420822528
author Leiser, Florian
Eckhardt, Sven
Leuthe, Valentin
Knaeble, Merlin
Maedche, Alexander
Schwabe, Gerhard
Sunyaev, Ali
author_facet Leiser, Florian
Eckhardt, Sven
Leuthe, Valentin
Knaeble, Merlin
Maedche, Alexander
Schwabe, Gerhard
Sunyaev, Ali
contents Large language models (LLMs) are prone to hallucinations, i.e., nonsensical, unfaithful, and undesirable text. Users tend to overrely on LLMs and corresponding hallucinations which can lead to misinterpretations and errors. To tackle the problem of overreliance, we propose HILL, the "Hallucination Identifier for Large Language Models". First, we identified design features for HILL with a Wizard of Oz approach with nine participants. Subsequently, we implemented HILL based on the identified design features and evaluated HILL's interface design by surveying 17 participants. Further, we investigated HILL's functionality to identify hallucinations based on an existing question-answering dataset and five user interviews. We find that HILL can correctly identify and highlight hallucinations in LLM responses which enables users to handle LLM responses with more caution. With that, we propose an easy-to-implement adaptation to existing LLMs and demonstrate the relevance of user-centered designs of AI artifacts.
format Preprint
id arxiv_https___arxiv_org_abs_2403_06710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HILL: A Hallucination Identifier for Large Language Models
Leiser, Florian
Eckhardt, Sven
Leuthe, Valentin
Knaeble, Merlin
Maedche, Alexander
Schwabe, Gerhard
Sunyaev, Ali
Human-Computer Interaction
Large language models (LLMs) are prone to hallucinations, i.e., nonsensical, unfaithful, and undesirable text. Users tend to overrely on LLMs and corresponding hallucinations which can lead to misinterpretations and errors. To tackle the problem of overreliance, we propose HILL, the "Hallucination Identifier for Large Language Models". First, we identified design features for HILL with a Wizard of Oz approach with nine participants. Subsequently, we implemented HILL based on the identified design features and evaluated HILL's interface design by surveying 17 participants. Further, we investigated HILL's functionality to identify hallucinations based on an existing question-answering dataset and five user interviews. We find that HILL can correctly identify and highlight hallucinations in LLM responses which enables users to handle LLM responses with more caution. With that, we propose an easy-to-implement adaptation to existing LLMs and demonstrate the relevance of user-centered designs of AI artifacts.
title HILL: A Hallucination Identifier for Large Language Models
topic Human-Computer Interaction
url https://arxiv.org/abs/2403.06710