Salvato in:
| Autori principali: | , , , , |
|---|---|
| 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 |