Pith. sign in

REVIEW 1 cited by

Leveraging Code to Improve In-context Learning for Semantic Parsing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.09519 v2 pith:OYIKP2O2 submitted 2023-11-16 cs.CL

classification cs.CL
keywords semanticimprovelearningparsingcodecompositionaldemonstrationsdsls
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In-context learning (ICL) is an appealing approach for semantic parsing due to its few-shot nature and improved generalization. However, learning to parse to rare domain-specific languages (DSLs) from just a few demonstrations is challenging, limiting the performance of even the most capable LLMs. In this work, we improve the effectiveness of ICL for semantic parsing by (1) using general-purpose programming languages such as Python instead of DSLs, and (2) augmenting prompts with a structured domain description that includes, e.g., the available classes and functions. We show that both these changes significantly improve accuracy across three popular datasets. Combined, they lead to dramatic improvements (e.g. 7.9% to 66.5% on SMCalFlow compositional split), nearly closing the performance gap between easier i.i.d.\ and harder compositional splits when used with a strong model, and reducing the need for a large number of demonstrations. We find that the resemblance of the target parse language to general-purpose code is a more important factor than the language's popularity in pre-training corpora. Our findings provide an improved methodology for building semantic parsers in the modern context of ICL with LLMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Natural Language Interaction with Databases on Edge Devices in the Internet of Battlefield Things

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A two-step LLM pipeline that relaxes exact-match requirements for text-to-Cypher queries improves question answering on a small IoBT-style graph database, with Llama 3.1 8B performing best.

Pith tools