# Investigating Co-Constructive Behavior of Large Language Models in Explanation Dialogues

arXiv: https://arxiv.org/abs/2504.18483 · HTML: https://mlsanity.com/paper/2504.18483/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 67 references that are in the map.
- First posted on arXiv 25 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting](https://mlsanity.com/paper/2309.07034/) (2023)
- [One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency](https://mlsanity.com/paper/2001.09734/) (2020)
- [VALUE: Understanding Dialect Disparity in NLU](https://mlsanity.com/paper/2204.03031/) (2022)
- [On the Multi-turn Instruction Following for Conversational Web Agents](https://mlsanity.com/paper/2402.15057/) (2024)
- [Properties and Challenges of LLM-Generated Explanations](https://mlsanity.com/paper/2402.10532/) (2024)
- [Modeling Human Subjectivity in LLMs Using Explicit and Implicit Human Factors in Personas](https://mlsanity.com/paper/2406.14462/) (2024)
- [Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations](https://mlsanity.com/paper/2405.17974/) (2024)
- [User Characteristics in Explainable AI: The Rabbit Hole of Personalization?](https://mlsanity.com/paper/2403.00137/) (2024)
- [Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue](https://mlsanity.com/paper/2402.06967/) (2024)
- ["Mama Always Had a Way of Explaining Things So I Could Understand'': A Dialogue Corpus for Learning to Construct Explanations](https://mlsanity.com/paper/2209.02508/) (2022)
- [Measuring User Understanding in Dialogue-based XAI Systems](https://mlsanity.com/paper/2408.06960/) (2024)
- [Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection](https://mlsanity.com/paper/2502.06487/) (2025)

## Built on by (most cited first, 2 of 2)

- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [Exploring Plan Space through Conversation: An Agentic Framework for LLM-Mediated Explanations in Planning](https://mlsanity.com/paper/2603.02070/) (2026)

## Abstract (arXiv)

The ability to generate explanations that are understood by explainees is the quintessence of explainable artificial intelligence. Since understanding depends on the explainee's background and needs, recent research focused on co-constructive explanation dialogues, where an explainer continuously monitors the explainee's understanding and adapts their explanations dynamically. We investigate the ability of large language models (LLMs) to engage as explainers in co-constructive explanation dialogues. In particular, we present a user study in which explainees interact with an LLM in two settings, one of which involves the LLM being instructed to explain a topic co-constructively. We evaluate the explainees' understanding before and after the dialogue, as well as their perception of the LLMs' co-constructive behavior. Our results suggest that LLMs show some co-constructive behaviors, such as asking verification questions, that foster the explainees' engagement and can improve understanding of a topic. However, their ability to effectively monitor the current understanding and scaffold the explanations accordingly remains limited.