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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mestha, Harshvardhan, Bania, Karan, Sathyanarayana, Shreyas V, Liu, Sidong, Srinivasan, Ashwin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909832721727488
author Mestha, Harshvardhan
Bania, Karan
Sathyanarayana, Shreyas V
Liu, Sidong
Srinivasan, Ashwin
author_facet Mestha, Harshvardhan
Bania, Karan
Sathyanarayana, Shreyas V
Liu, Sidong
Srinivasan, Ashwin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20600
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol
Mestha, Harshvardhan
Bania, Karan
Sathyanarayana, Shreyas V
Liu, Sidong
Srinivasan, Ashwin
Artificial Intelligence
Human-Computer Interaction
Machine Learning
Multiagent Systems
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.
title Multi-Turn Human-LLM Interaction Through the Lens of a Two-Way Intelligibility Protocol
topic Artificial Intelligence
Human-Computer Interaction
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2410.20600