InterroLang: Exploring NLP Models and Datasets through Dialogue-based Explanations
This work addresses the problem of making NLP model explanations more accessible and effective for users through interactive dialogue, though it is incremental as it builds on prior conversational explanation frameworks.
The authors tackled the lack of interactive tools for explaining NLP models by developing InterroLang, a dialogue-based system that adapts an existing framework to NLP with new operations like free-text rationalization, and found in user studies that it improved users' ability to predict model outcomes compared to one-off explanations.
While recently developed NLP explainability methods let us open the black box in various ways (Madsen et al., 2022), a missing ingredient in this endeavor is an interactive tool offering a conversational interface. Such a dialogue system can help users explore datasets and models with explanations in a contextualized manner, e.g. via clarification or follow-up questions, and through a natural language interface. We adapt the conversational explanation framework TalkToModel (Slack et al., 2022) to the NLP domain, add new NLP-specific operations such as free-text rationalization, and illustrate its generalizability on three NLP tasks (dialogue act classification, question answering, hate speech detection). To recognize user queries for explanations, we evaluate fine-tuned and few-shot prompting models and implement a novel Adapter-based approach. We then conduct two user studies on (1) the perceived correctness and helpfulness of the dialogues, and (2) the simulatability, i.e. how objectively helpful dialogical explanations are for humans in figuring out the model's predicted label when it's not shown. We found rationalization and feature attribution were helpful in explaining the model behavior. Moreover, users could more reliably predict the model outcome based on an explanation dialogue rather than one-off explanations.