# Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality

arXiv: https://arxiv.org/abs/2211.09267 · HTML: https://mlsanity.com/paper/2211.09267/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 38 references that are in the map.
- First posted on arXiv 16 Nov 2022.

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [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)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [ParlAI: A Dialog Research Software Platform](https://mlsanity.com/paper/1705.06476/) (2017)
- [MuTual: A Dataset for Multi-Turn Dialogue Reasoning](https://mlsanity.com/paper/2004.04494/) (2020)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)
- [CICERO: A Dataset for Contextualized Commonsense Inference in Dialogues](https://mlsanity.com/paper/2203.13926/) (2022)
- [Reason first, then respond: Modular Generation for Knowledge-infused Dialogue](https://mlsanity.com/paper/2111.05204/) (2021)
- [Commonsense-Focused Dialogues for Response Generation: An Empirical Study](https://mlsanity.com/paper/2109.06427/) (2021)
- [Grounding Conversations with Improvised Dialogues](https://mlsanity.com/paper/2004.09544/) (2020)

## Built on by (most cited first, 22 of 22)

- [SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization](https://mlsanity.com/paper/2212.10465/) (2022)
- [Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics](https://mlsanity.com/paper/2406.14703/) (2024)
- [Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents](https://mlsanity.com/paper/2310.09343/) (2023)
- [Navigating Rifts in Human-LLM Grounding: Study and Benchmark](https://mlsanity.com/paper/2503.13975/) (2025)
- [I Cast Detect Thoughts: Learning to Converse and Guide with Intents and Theory-of-Mind in Dungeons and Dragons](https://mlsanity.com/paper/2212.10060/) (2022)
- [Contextualization Distillation from Large Language Model for Knowledge Graph Completion](https://mlsanity.com/paper/2402.01729/) (2024)
- [Pearl: A Review-driven Persona-Knowledge Grounded Conversational Recommendation Dataset](https://mlsanity.com/paper/2403.04460/) (2024)
- [Commonsense-augmented Memory Construction and Management in Long-term Conversations via Context-aware Persona Refinement](https://mlsanity.com/paper/2401.14215/) (2024)
- [Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference](https://mlsanity.com/paper/2311.15316/) (2023)
- [Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents](https://mlsanity.com/paper/2502.17967/) (2025)
- [NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation](https://mlsanity.com/paper/2312.05979/) (2023)
- [Speechworthy Instruction-tuned Language Models](https://mlsanity.com/paper/2409.14672/) (2024)
- [Don't Take This Out of Context! On the Need for Contextual Models and Evaluations for Stylistic Rewriting](https://mlsanity.com/paper/2305.14755/) (2023)
- [ConvoSense: Overcoming Monotonous Commonsense Inferences for Conversational AI](https://mlsanity.com/paper/2401.15471/) (2024)
- [Tuning-Free Personalized Alignment via Trial-Error-Explain In-Context Learning](https://mlsanity.com/paper/2502.08972/) (2025)
- [Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs](https://mlsanity.com/paper/2510.25441/) (2025)
- [Tailoring Vaccine Messaging with Common-Ground Opinions](https://mlsanity.com/paper/2405.10861/) (2024)
- [MindDial: Belief Dynamics Tracking with Theory-of-Mind Modeling for Situated Neural Dialogue Generation](https://mlsanity.com/paper/2306.15253/) (2023)
- [Investigating Content Planning for Navigating Trade-offs in Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2402.02077/) (2024)
- [It Couldn't Help But Overhear: On the Limits of Modelling Meta-Communicative Grounding Acts with Supervised Learning](https://mlsanity.com/paper/2405.01139/) (2024)
- [Leveraging Explicit Reasoning for Inference Integration in Commonsense-Augmented Dialogue Models](https://mlsanity.com/paper/2406.09138/) (2024)
- [BotEval: Facilitating Interactive Human Evaluation](https://mlsanity.com/paper/2407.17770/) (2024)

## Abstract (arXiv)

Human communication relies on common ground (CG), the mutual knowledge and beliefs shared by participants, to produce coherent and interesting conversations. In this paper, we demonstrate that current response generation (RG) models produce generic and dull responses in dialogues because they act reflexively, failing to explicitly model CG, both due to the lack of CG in training data and the standard RG training procedure. We introduce Reflect, a dataset that annotates dialogues with explicit CG (materialized as inferences approximating shared knowledge and beliefs) and solicits 9k diverse human-generated responses each following one common ground. Using Reflect, we showcase the limitations of current dialogue data and RG models: less than half of the responses in current data are rated as high quality (sensible, specific, and interesting) and models trained using this data have even lower quality, while most Reflect responses are judged high quality. Next, we analyze whether CG can help models produce better-quality responses by using Reflect CG to guide RG models. Surprisingly, we find that simply prompting GPT3 to "think" about CG generates 30% more quality responses, showing promising benefits to integrating CG into the RG process.