# Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol

arXiv: https://arxiv.org/abs/2410.20600 · HTML: https://mlsanity.com/paper/2410.20600/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 27 Oct 2024.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [On scientific understanding with artificial intelligence](https://mlsanity.com/paper/2204.01467/) (2022)
- [Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models](https://mlsanity.com/paper/2304.11657/) (2023)
- [Beneficial and Harmful Explanatory Machine Learning](https://mlsanity.com/paper/2009.06410/) (2020)
- [Unpacking Human-AI interactions: From interaction primitives to a design space](https://mlsanity.com/paper/2401.05115/) (2024)
- [eXtended Artificial Intelligence: New Prospects of Human-AI Interaction Research](https://mlsanity.com/paper/2103.15004/) (2021)
- [A Model for Intelligible Interaction Between Agents That Predict and Explain](https://mlsanity.com/paper/2301.01819/) (2023)

## Built on by (most cited first, 4 of 4)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [A Survey of AI Agent Protocols](https://mlsanity.com/paper/2504.16736/) (2025)
- [Beyond Message Passing: A Semantic View of Agent Communication Protocols](https://mlsanity.com/paper/2604.02369/) (2026)
- [Knowledge Affordances for Hybrid Human-AI Information Seeking](https://mlsanity.com/paper/2604.27539/) (2026)

## Abstract (arXiv)

Our interest is in the design of software systems involving a human-expert interacting -- using natural language -- with a large language model (LLM) on data analysis tasks. For complex problems, it is possible that LLMs can harness human expertise and creativity to find solutions that were otherwise elusive. On one level, this interaction takes place through multiple turns of prompts from the human and responses from the LLM. Here we investigate a more structured approach based on an abstract protocol described in [3] for interaction between agents. The protocol is motivated by a notion of "two-way intelligibility" and is modelled by a pair of communicating finite-state machines. We provide an implementation of the protocol, and provide empirical evidence of using the implementation to mediate interactions between an LLM and a human-agent in two areas of scientific interest (radiology and drug design). We conduct controlled experiments with a human proxy (a database), and uncontrolled experiments with human subjects. The results provide evidence in support of the protocol's capability of capturing one- and two-way intelligibility in human-LLM interaction; and for the utility of two-way intelligibility in the design of human-machine systems. Our code is available at https://github.com/karannb/interact.