Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908496742580224 |
|---|---|
| author | Wang, Qianli Anikina, Tatiana Feldhus, Nils Ostermann, Simon Splitt, Fedor Li, Jiaao Tsoneva, Yoana Möller, Sebastian Schmitt, Vera |
| author_facet | Wang, Qianli Anikina, Tatiana Feldhus, Nils Ostermann, Simon Splitt, Fedor Li, Jiaao Tsoneva, Yoana Möller, Sebastian Schmitt, Vera |
| contents | Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered considerable attention for their ability to enhance user comprehension through dialogue-based explanations. Current ConvXAI systems often are based on intent recognition to accurately identify the user's desired intention and map it to an explainability method. While such methods offer great precision and reliability in discerning users' underlying intentions for English, a significant challenge in the scarcity of training data persists, which impedes multilingual generalization. Besides, the support for free-form custom inputs, which are user-defined data distinct from pre-configured dataset instances, remains largely limited. To bridge these gaps, we first introduce MultiCoXQL, a multilingual extension of the CoXQL dataset spanning five typologically diverse languages, including one low-resource language. Subsequently, we propose a new parsing approach aimed at enhancing multilingual parsing performance, and evaluate three LLMs on MultiCoXQL using various parsing strategies. Furthermore, we present Compass, a new multilingual dataset designed for custom input extraction in ConvXAI systems, encompassing 11 intents across the same five languages as MultiCoXQL. We conduct monolingual, cross-lingual, and multilingual evaluations on Compass, employing three LLMs of varying sizes alongside BERT-type models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems Wang, Qianli Anikina, Tatiana Feldhus, Nils Ostermann, Simon Splitt, Fedor Li, Jiaao Tsoneva, Yoana Möller, Sebastian Schmitt, Vera Computation and Language Conversational explainable artificial intelligence (ConvXAI) systems based on large language models (LLMs) have garnered considerable attention for their ability to enhance user comprehension through dialogue-based explanations. Current ConvXAI systems often are based on intent recognition to accurately identify the user's desired intention and map it to an explainability method. While such methods offer great precision and reliability in discerning users' underlying intentions for English, a significant challenge in the scarcity of training data persists, which impedes multilingual generalization. Besides, the support for free-form custom inputs, which are user-defined data distinct from pre-configured dataset instances, remains largely limited. To bridge these gaps, we first introduce MultiCoXQL, a multilingual extension of the CoXQL dataset spanning five typologically diverse languages, including one low-resource language. Subsequently, we propose a new parsing approach aimed at enhancing multilingual parsing performance, and evaluate three LLMs on MultiCoXQL using various parsing strategies. Furthermore, we present Compass, a new multilingual dataset designed for custom input extraction in ConvXAI systems, encompassing 11 intents across the same five languages as MultiCoXQL. We conduct monolingual, cross-lingual, and multilingual evaluations on Compass, employing three LLMs of varying sizes alongside BERT-type models. |
| title | Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systems |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.14982 |