# Probing Commonsense Explanation in Dialogue Response Generation

arXiv: https://arxiv.org/abs/2104.09574 · HTML: https://mlsanity.com/paper/2104.09574/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference](https://mlsanity.com/paper/1808.05326/) (2018)
- [The Second Conversational Intelligence Challenge (ConvAI2)](https://mlsanity.com/paper/1902.00098/) (2019)
- [MuTual: A Dataset for Multi-Turn Dialogue Reasoning](https://mlsanity.com/paper/2004.04494/) (2020)
- [A Neural Network Approach to Context-Sensitive Generation of Conversational Responses](https://mlsanity.com/paper/1506.06714/) (2015)
- [GLUCOSE: GeneraLized and COntextualized Story Explanations](https://mlsanity.com/paper/2009.07758/) (2020)
- [Probing Natural Language Inference Models through Semantic Fragments](https://mlsanity.com/paper/1909.07521/) (2019)
- [RiddleSense: Reasoning about Riddle Questions Featuring Linguistic Creativity and Commonsense Knowledge](https://mlsanity.com/paper/2101.00376/) (2021)
- [Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs](https://mlsanity.com/paper/1911.02707/) (2019)
- [Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study](https://mlsanity.com/paper/1906.01603/) (2019)
- [Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources](https://mlsanity.com/paper/2103.11320/) (2021)
- [Differentiable Open-Ended Commonsense Reasoning](https://mlsanity.com/paper/2010.14439/) (2020)
- [RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms](https://mlsanity.com/paper/2005.00782/) (2020)
- [Conversational Neuro-Symbolic Commonsense Reasoning](https://mlsanity.com/paper/2006.10022/) (2020)
- [What Does My QA Model Know? Devising Controlled Probes using Expert Knowledge](https://mlsanity.com/paper/1912.13337/) (2019)

## Built on by (most cited first, 13 of 13)

- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [Mind the Gap! Injecting Commonsense Knowledge for Abstractive Dialogue Summarization](https://mlsanity.com/paper/2209.00930/) (2022)
- [Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge](https://mlsanity.com/paper/2306.04657/) (2023)
- [Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations](https://mlsanity.com/paper/2305.14618/) (2023)
- [The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends](https://mlsanity.com/paper/2409.14195/) (2024)
- [Coalescing Global and Local Information for Procedural Text Understanding](https://mlsanity.com/paper/2208.12848/) (2022)
- [Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics](https://mlsanity.com/paper/2112.08321/) (2021)
- [Counterfactual Simulatability of LLM Explanations for Generation Tasks](https://mlsanity.com/paper/2505.21740/) (2025)
- [Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theory](https://mlsanity.com/paper/2312.08702/) (2023)
- [Explanation Regeneration via Information Bottleneck](https://mlsanity.com/paper/2212.09603/) (2022)
- [ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI](https://mlsanity.com/paper/2401.15471/) (2024)
- [Evaluate Confidence Instead of Perplexity for Zero-shot Commonsense Reasoning](https://mlsanity.com/paper/2208.11007/) (2022)
- [ConceptNet infused DialoGPT for Underlying Commonsense Understanding and Reasoning in Dialogue Response Generation](https://mlsanity.com/paper/2209.15109/) (2022)

## Abstract (arXiv)

Humans use commonsense reasoning (CSR) implicitly to produce natural and coherent responses in conversations. Aiming to close the gap between current response generation (RG) models and human communication abilities, we want to understand why RG models respond as they do by probing RG model's understanding of commonsense reasoning that elicits proper responses. We formalize the problem by framing commonsense as a latent variable in the RG task and using explanations for responses as textual form of commonsense. We collect 6k annotated explanations justifying responses from four dialogue datasets and ask humans to verify them and propose two probing settings to evaluate RG models' CSR capabilities. Probing results show that models fail to capture the logical relations between commonsense explanations and responses and fine-tuning on in-domain data and increasing model sizes do not lead to understanding of CSR for RG. We hope our study motivates more research in making RG models emulate the human reasoning process in pursuit of smooth human-AI communication.