CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ghaddar, Abbas, Alfonso-Hermelo, David, Langlais, Philippe, Rezagholizadeh, Mehdi, Chen, Boxing, Parthasarathi, Prasanna
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917673983541248
author Ghaddar, Abbas
Alfonso-Hermelo, David
Langlais, Philippe
Rezagholizadeh, Mehdi
Chen, Boxing
Parthasarathi, Prasanna
author_facet Ghaddar, Abbas
Alfonso-Hermelo, David
Langlais, Philippe
Rezagholizadeh, Mehdi
Chen, Boxing
Parthasarathi, Prasanna
contents In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, which may bias models towards completely ignoring the conversation history. We therefore introduce CHARP, a diagnostic test set, designed for an improved evaluation of hallucinations in conversational model. CHARP not only measures hallucination but also the compliance of the models to the conversation task. Our extensive analysis reveals that models primarily exhibit poor performance on CHARP due to their inability to effectively attend to and reason over the conversation history. Furthermore, the evaluation methods of FaithDial fail to capture these shortcomings, neglecting the conversational history. Our findings indicate that there is substantial room for contribution in both dataset creation and hallucination evaluation for knowledge-grounded dialogue, and that CHARP can serve as a tool for monitoring the progress in this particular research area. CHARP is publicly available at https://huggingface.co/datasets/huawei-noah/CHARP
format Preprint
id arxiv_https___arxiv_org_abs_2405_15110
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems
Ghaddar, Abbas
Alfonso-Hermelo, David
Langlais, Philippe
Rezagholizadeh, Mehdi
Chen, Boxing
Parthasarathi, Prasanna
Computation and Language
In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, which may bias models towards completely ignoring the conversation history. We therefore introduce CHARP, a diagnostic test set, designed for an improved evaluation of hallucinations in conversational model. CHARP not only measures hallucination but also the compliance of the models to the conversation task. Our extensive analysis reveals that models primarily exhibit poor performance on CHARP due to their inability to effectively attend to and reason over the conversation history. Furthermore, the evaluation methods of FaithDial fail to capture these shortcomings, neglecting the conversational history. Our findings indicate that there is substantial room for contribution in both dataset creation and hallucination evaluation for knowledge-grounded dialogue, and that CHARP can serve as a tool for monitoring the progress in this particular research area. CHARP is publicly available at https://huggingface.co/datasets/huawei-noah/CHARP
title CHARP: Conversation History AwaReness Probing for Knowledge-grounded Dialogue Systems
topic Computation and Language
url https://arxiv.org/abs/2405.15110