REVIEW 2 cited by
Mediators: Conversational Agents Explaining NLP Model Behavior
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The human-centric explainable artificial intelligence (HCXAI) community has raised the need for framing the explanation process as a conversation between human and machine. In this position paper, we establish desiderata for Mediators, text-based conversational agents which are capable of explaining the behavior of neural models interactively using natural language. From the perspective of natural language processing (NLP) research, we engineer a blueprint of such a Mediator for the task of sentiment analysis and assess how far along current research is on the path towards dialogue-based explanations.
Forward citations
Cited by 2 Pith papers
-
Finding Uncommon Ground: A Human-Centered Model for Extrospective Explanations
AI explanations should present the least-supported beliefs in the agent's reasoning, because those are the likely source of user surprise when behavior is unexpected.
-
Terminating representations, transformations and summations for the $q$ and $q^{-1}$-symmetric subfamilies of the Askey--Wilson polynomials
The abstract claims a complete catalog of terminating basic hypergeometric representations, transformations, and q-Askey symmetry structure for four Askey-Wilson subfamilies, but the full text is a different paper, so...
Discussion (0). Continue with ORCID to comment.