Salvato in:
Dettagli Bibliografici
Autori principali: Kim, Takyoung, Shin, Jamin, Kim, Young-Ho, Bae, Sanghwan, Kim, Sungdong
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2305.13857
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929403004452864
author Kim, Takyoung
Shin, Jamin
Kim, Young-Ho
Bae, Sanghwan
Kim, Sungdong
author_facet Kim, Takyoung
Shin, Jamin
Kim, Young-Ho
Bae, Sanghwan
Kim, Sungdong
contents Most task-oriented dialogue (TOD) benchmarks assume users that know exactly how to use the system by constraining the user behaviors within the system's capabilities via strict user goals, namely "user familiarity" bias. This data bias deepens when it combines with data-driven TOD systems, as it is impossible to fathom the effect of it with existing static evaluations. Hence, we conduct an interactive user study to unveil how vulnerable TOD systems are against realistic scenarios. In particular, we compare users with 1) detailed goal instructions that conform to the system boundaries (closed-goal) and 2) vague goal instructions that are often unsupported but realistic (open-goal). Our study reveals that conversations in open-goal settings lead to catastrophic failures of the system, in which 92% of the dialogues had significant issues. Moreover, we conduct a thorough analysis to identify distinctive features between the two settings through error annotation. From this, we discover a novel "pretending" behavior, in which the system pretends to handle the user requests even though they are beyond the system's capabilities. We discuss its characteristics and toxicity while showing recent large language models can also suffer from this behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2305_13857
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Revealing User Familiarity Bias in Task-Oriented Dialogue via Interactive Evaluation
Kim, Takyoung
Shin, Jamin
Kim, Young-Ho
Bae, Sanghwan
Kim, Sungdong
Computation and Language
Most task-oriented dialogue (TOD) benchmarks assume users that know exactly how to use the system by constraining the user behaviors within the system's capabilities via strict user goals, namely "user familiarity" bias. This data bias deepens when it combines with data-driven TOD systems, as it is impossible to fathom the effect of it with existing static evaluations. Hence, we conduct an interactive user study to unveil how vulnerable TOD systems are against realistic scenarios. In particular, we compare users with 1) detailed goal instructions that conform to the system boundaries (closed-goal) and 2) vague goal instructions that are often unsupported but realistic (open-goal). Our study reveals that conversations in open-goal settings lead to catastrophic failures of the system, in which 92% of the dialogues had significant issues. Moreover, we conduct a thorough analysis to identify distinctive features between the two settings through error annotation. From this, we discover a novel "pretending" behavior, in which the system pretends to handle the user requests even though they are beyond the system's capabilities. We discuss its characteristics and toxicity while showing recent large language models can also suffer from this behavior.
title Revealing User Familiarity Bias in Task-Oriented Dialogue via Interactive Evaluation
topic Computation and Language
url https://arxiv.org/abs/2305.13857