“I Understand, but...”: Towards a Comprehensive Account of the Explainee’s Voice in Explanatory Dialogues

2025-12-19 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning · Depth: Advanced, quick

Summary

The paper "“I Understand, but...”: Towards a Comprehensive Account of the Explainee’s Voice in Explanatory Dialogues" by Zaninello, Bodlovic, Lewinski, and Magnini, presented at the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025) in Cagliari, Italy, from pages 1158–1170, investigates the role of the "explainee's voice" in dialogues where explanations are provided. This research focuses on understanding how the recipient of an explanation expresses their comprehension, confusion, or disagreement, moving beyond a simple binary understanding of explanation success. The authors aim to provide a detailed framework for analyzing the explainee's verbal and non-verbal cues, which can significantly impact the effectiveness and iterative nature of explanatory interactions, particularly in computational linguistics and human-computer interaction contexts.

Key takeaway

For research scientists developing conversational AI or explanation systems, you should prioritize incorporating robust mechanisms for detecting and interpreting explainee feedback. Your systems will benefit from moving beyond simple "understood/not understood" signals to capture the nuances of user comprehension, such as partial understanding or specific points of confusion, enabling more adaptive and effective explanatory interactions.

Key insights

Understanding the explainee's feedback is crucial for effective explanatory dialogues.

Principles

• Explanation is an iterative process.
• Explainee feedback shapes explanation success.

In practice

• Analyze explainee's verbal cues.
• Integrate explainee feedback mechanisms.

Topics

• Explanatory Dialogues
• Explainee's Voice
• Computational Linguistics
• Explainable AI
• Dialogue Systems

Best for: Research Scientist, AI Researcher, AI Scientist, NLP Engineer

Related on AIssential

• Characterizing the Response Space of Questions: data and theory — A dialogical formal semantics can characterize the full response space for questions.
• Beyond one-on-one: Authoring, simulating, and testing dynamic human-AI group conversations — DialogLab bridges scripted and generative AI dialogue for complex multi-party human-AI conversations.
• How NLP Communication Agents Actually Understand You (Spoiler: It’s a Lot Weirder Than You’d Think) — NLP systems process language through five interdependent layers, from tokenization to pragmatic intent.
• User-Aware Active Knowledge Acquisition for Emotional Support Dialogue — UKA uses active learning and Theory-of-Mind uncertainty to improve emotional support dialogue by efficiently acquiring user-aligned knowledge.
• ‘Alexa, tell me a joke’: how talking to AI impacts young children’s development — Routine AI interactions shape children's language habits and conversational expectations differently than human exchanges.
• A Dialogue Agent to Let Users Experience and Gently Enhance the "Gyaru-Mind" — A dialogue agent quantifies and enhances the "Gyaru-Mind" through real-time feedback and balanced conversational responses.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.