Program Synthesis Dialog Agents for Interactive Decision-Making

TL;DR

This paper introduces ProADA, a program synthesis-based dialog agent for interactive decision-making in eligibility assessments, significantly improving accuracy over existing language models while maintaining dialog efficiency.

Contribution

The paper presents ProADA, a novel method that uses program synthesis for decision-making in dialog agents, addressing hallucination issues and enhancing performance on the BeNYfits benchmark.

Findings

ProADA achieves an F1 score of 55.6, outperforming GPT-4o's 35.7.

ProADA maintains similar dialog length while improving accuracy.

Current language models struggle with hallucinations in decision-making tasks.

Abstract

Many real-world eligibility problems, ranging from medical diagnosis to tax planning, can be mapped to decision problems expressed in natural language, wherein a model must make a binary choice based on user features. Large-scale domains such as legal codes or frequently updated funding opportunities render human annotation (e.g., web forms or decision trees) impractical, highlighting the need for agents that can automatically assist in decision-making. Since relevant information is often only known to the user, it is crucial that these agents ask the right questions. As agents determine when to terminate a conversation, they face a trade-off between accuracy and the number of questions asked, a key metric for both user experience and cost. To evaluate this task, we propose BeNYfits, a new benchmark for determining user eligibility for multiple overlapping social benefits opportunities through interactive decision-making. Our experiments show that current language models struggle with frequent hallucinations, with GPT-4o scoring only 35.7 F1 using a ReAct-style chain-of-thought. To address this, we introduce ProADA, a novel approach that leverages program synthesis to assist in decision-making by mapping dialog planning to a code generation problem and using gaps in structured data to determine the best next action. Our agent, ProADA, improves the F1 score to 55.6 while maintaining nearly the same number of dialog turns.