Decision-Oriented Dialogue for Human-AI Collaboration
This addresses the challenge of human-AI collaboration in decision-making tasks for users needing assistance with everyday decisions, but it is incremental as it builds on existing dialogue and AI assistant research.
The paper tackles the problem of AI assistants collaborating with humans via natural language to make complex decisions, such as assigning reviewers or planning itineraries, and finds that large language models achieve much lower rewards than human assistants despite longer dialogues.
We describe a class of tasks called decision-oriented dialogues, in which AI assistants such as large language models (LMs) must collaborate with one or more humans via natural language to help them make complex decisions. We formalize three domains in which users face everyday decisions: (1) choosing an assignment of reviewers to conference papers, (2) planning a multi-step itinerary in a city, and (3) negotiating travel plans for a group of friends. In each of these settings, AI assistants and users have disparate abilities that they must combine to arrive at the best decision: assistants can access and process large amounts of information, while users have preferences and constraints external to the system. For each task, we build a dialogue environment where agents receive a reward based on the quality of the final decision they reach. We evaluate LMs in self-play and in collaboration with humans and find that they fall short compared to human assistants, achieving much lower rewards despite engaging in longer dialogues. We highlight a number of challenges models face in decision-oriented dialogues, ranging from goal-directed behavior to reasoning and optimization, and release our environments as a testbed for future work.