# Human-like informative conversations: Better acknowledgements using conditional mutual information

arXiv: https://arxiv.org/abs/2104.07831 · HTML: https://mlsanity.com/paper/2104.07831/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 31 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [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)
- [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)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents](https://mlsanity.com/paper/1901.08149/) (2019)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Towards Unified Dialogue System Evaluation: A Comprehensive Analysis of Current Evaluation Protocols](https://mlsanity.com/paper/2006.06110/) (2020)
- [RefNet: A Reference-aware Network for Background Based Conversation](https://mlsanity.com/paper/1908.06449/) (2019)
- [Extending Neural Generative Conversational Model using External Knowledge Sources](https://mlsanity.com/paper/1809.05524/) (2018)
- [Thinking Globally, Acting Locally: Distantly Supervised Global-to-Local Knowledge Selection for Background Based Conversation](https://mlsanity.com/paper/1908.09528/) (2019)

## Built on by (most cited first, 6 of 6)

- [Grounding Gaps in Language Model Generations](https://mlsanity.com/paper/2311.09144/) (2023)
- [Navigating Rifts in Human-LLM Grounding: Study and Benchmark](https://mlsanity.com/paper/2503.13975/) (2025)
- [Pointwise Mutual Information Based Metric and Decoding Strategy for Faithful Generation in Document Grounded Dialogs](https://mlsanity.com/paper/2305.12191/) (2023)
- [Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent](https://mlsanity.com/paper/2207.12021/) (2022)
- [Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks](https://mlsanity.com/paper/2509.09870/) (2025)
- [Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection](https://mlsanity.com/paper/2203.11399/) (2022)

## Abstract (arXiv)

This work aims to build a dialogue agent that can weave new factual content into conversations as naturally as humans. We draw insights from linguistic principles of conversational analysis and annotate human-human conversations from the Switchboard Dialog Act Corpus to examine humans strategies for acknowledgement, transition, detail selection and presentation. When current chatbots (explicitly provided with new factual content) introduce facts into a conversation, their generated responses do not acknowledge the prior turns. This is because models trained with two contexts - new factual content and conversational history - generate responses that are non-specific w.r.t. one of the contexts, typically the conversational history. We show that specificity w.r.t. conversational history is better captured by Pointwise Conditional Mutual Information (pcmih) than by the established use of Pointwise Mutual Information (pmi). Our proposed method, Fused-PCMI, trades off pmi for pcmih and is preferred by humans for overall quality over the Max-PMI baseline 60% of the time. Human evaluators also judge responses with higher pcmih better at acknowledgement 74% of the time. The results demonstrate that systems mimicking human conversational traits (in this case acknowledgement) improve overall quality and more broadly illustrate the utility of linguistic principles in improving dialogue agents.