Pith. sign in

REVIEW 6 cited by

Rethinking Explainability as a Dialogue: A Practitioner's Perspective

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

arxiv 2202.01875 v1 pith:XDNPPI6T submitted 2022-02-03 cs.LG

classification cs.LG
keywords explanationsexplainabilityinteractivemodelsworkdecision-makerslanguagelearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

As practitioners increasingly deploy machine learning models in critical domains such as health care, finance, and policy, it becomes vital to ensure that domain experts function effectively alongside these models. Explainability is one way to bridge the gap between human decision-makers and machine learning models. However, most of the existing work on explainability focuses on one-off, static explanations like feature importances or rule lists. These sorts of explanations may not be sufficient for many use cases that require dynamic, continuous discovery from stakeholders. In the literature, few works ask decision-makers about the utility of existing explanations and other desiderata they would like to see in an explanation going forward. In this work, we address this gap and carry out a study where we interview doctors, healthcare professionals, and policymakers about their needs and desires for explanations. Our study indicates that decision-makers would strongly prefer interactive explanations in the form of natural language dialogues. Domain experts wish to treat machine learning models as "another colleague", i.e., one who can be held accountable by asking why they made a particular decision through expressive and accessible natural language interactions. Considering these needs, we outline a set of five principles researchers should follow when designing interactive explanations as a starting place for future work. Further, we show why natural language dialogues satisfy these principles and are a desirable way to build interactive explanations. Next, we provide a design of a dialogue system for explainability and discuss the risks, trade-offs, and research opportunities of building these systems. Overall, we hope our work serves as a starting place for researchers and engineers to design interactive explainability systems.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data

    cs.CL 2025-07 conditional novelty 6.0 of 10

    AraTable is the first Arabic tabular QA benchmark; its experiments show LLMs are much weaker at reasoning over Arabic tables than at direct lookup.

  2. Exploiting Constraint Reasoning to Build Graphical Explanations for Mixed-Integer Linear Programming

    cs.AI 2025-07 conditional novelty 6.0 of 10

    X-MILP builds contrastive explanations for MILP solutions by computing an Irreducible Infeasible Subsystem of a user-constrained satisfiability problem and presenting it as a connected graph of natural-language reasons.

  3. Let's Get You Hired: A Job Seeker's Perspective on Multi-Agent Recruitment Systems for Explaining Hiring Decisions

    cs.CY 2025-05 conditional novelty 6.0 of 10

    A multi-agent LLM chatbot for job seekers was perceived by 20 interviewed participants as more actionable, trustworthy, and fair than their recalled experiences with traditional hiring methods.

  4. MetaExplainer: A Framework to Generate Multi-Type User-Centered Explanations for AI Systems

    cs.HC 2025-08 conditional novelty 5.0 of 10

    A neuro-symbolic pipeline decomposes user questions, delegates to model explainers, and synthesizes natural-language explanations, achieving moderate stage-wise scores on a diabetes dataset.

  5. Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety

    cs.SE 2025-06 accept novelty 5.0 of 10

    A new survey organizes LLM interpretation methods by workflow stage and connects them to safety enhancement strategies and tools, covering around 70 works.

  6. Importance of User Control in Data-Centric Steering for Healthcare Experts

    cs.HC 2025-05 conditional novelty 5.0 of 10

    Healthcare experts who manually adjusted training data improved a diabetes prediction model more than those using automated corrections, without losing trust or understanding.

Pith tools