Measuring and Mitigating Constraint Violations of In-Context Learning for Utterance-to-API Semantic Parsing

Shufan Wang, Sébastien Jean, Sailik Sengupta, James Gung, Nikolaos Pappas, Yi Zhang

Submission Type: Regular Long Paper

Submission Track: Dialogue and Interactive Systems

Submission Track 2: Resources and Evaluation

Keywords: executable semantic parsing, task-oriented semantic parsing, utterance-to-API generation, in-context learning

TL;DR: We define and analyze various categories of constraint violations by LLMs in utterance-to-API generation, and examine common mitigation strategies with our proposed fine-grained metrics.

Abstract:

In executable task-oriented semantic parsing, the system aims to translate users' utterances in natural language to machine-interpretable programs (API calls) that can be executed according to pre-defined API specifications.
With the popularity of Large Language Models (LLMs), in-context learning offers a strong baseline for such scenarios, especially in data-limited regimes.
However, LLMs are known to hallucinate and therefore pose a formidable challenge in constraining generated content.
Thus, it remains uncertain if LLMs can effectively perform task-oriented utterance-to-API generation, where respecting the API's structural and task-specific constraints is crucial.
In this work, we seek to measure, analyze and mitigate such constraints violations. First, we identify the categories of various constraints in obtaining API-semantics from task-oriented utterances, and define fine-grained metrics that complement traditional ones. Second, we leverage these metrics to conduct a detailed error analysis of constraints violations seen in state-of-the-art LLMs, which motivates us to investigate two popular mitigation strategies-- Semantic-Retrieval of Demonstrations (SRD) and API-aware Constrained Decoding (API-CD).
Our experiments show that these strategies are effective at reducing constraints violations and improving the quality of the generated API calls, but require careful consideration given their implementation complexity and latency.

Submission Number: 4419