# Few-Shot Adaptation for Parsing Contextual Utterances with LLMs

arXiv: https://arxiv.org/abs/2309.10168 · HTML: https://mlsanity.com/paper/2309.10168/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 18 Sep 2023.

## Builds on (most cited first, 20 of 20)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Adafactor: Adaptive Learning Rates with Sublinear Memory Cost](https://mlsanity.com/paper/1804.04235/) (2018)
- [Learning To Retrieve Prompts for In-Context Learning](https://mlsanity.com/paper/2112.08633/) (2021)
- [CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases](https://mlsanity.com/paper/1909.05378/) (2019)
- [Constrained Language Models Yield Few-Shot Semantic Parsers](https://mlsanity.com/paper/2104.08768/) (2021)
- [Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://mlsanity.com/paper/1606.03777/) (2016)
- [Task-Oriented Dialogue as Dataflow Synthesis](https://mlsanity.com/paper/2009.11423/) (2020)
- [Few-Shot Generative Conversational Query Rewriting](https://mlsanity.com/paper/2006.05009/) (2020)
- [Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions](https://mlsanity.com/paper/1909.00786/) (2019)
- [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://mlsanity.com/paper/2303.06573/) (2023)
- [Few-Shot Semantic Parsing with Language Models Trained On Code](https://mlsanity.com/paper/2112.08696/) (2021)
- [Conversational Semantic Parsing for Dialog State Tracking](https://mlsanity.com/paper/2010.12770/) (2020)
- [Incomplete Utterance Rewriting as Semantic Segmentation](https://mlsanity.com/paper/2009.13166/) (2020)
- [Learning to Map Context-Dependent Sentences to Executable Formal Queries](https://mlsanity.com/paper/1804.06868/) (2018)
- [Scaling Multi-Domain Dialogue State Tracking via Query Reformulation](https://mlsanity.com/paper/1903.05164/) (2019)
- [Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation](https://mlsanity.com/paper/2204.03958/) (2022)
- [Simplifying Semantic Annotations of SMCalFlow](https://mlsanity.com/paper/2206.13425/) (2022)
- [Pre-Training for Query Rewriting in A Spoken Language Understanding System](https://mlsanity.com/paper/2002.05607/) (2020)
- [MLR: A Two-stage Conversational Query Rewriting Model with Multi-task Learning](https://mlsanity.com/paper/2004.05812/) (2020)

## Built on by (most cited first, 1 of 1)

- [Randomly Sampled Language Reasoning Problems Elucidate Limitations of In-Context Learning](https://mlsanity.com/paper/2501.02825/) (2025)

## Abstract (arXiv)

We evaluate the ability of semantic parsers based on large language models (LLMs) to handle contextual utterances. In real-world settings, there typically exists only a limited number of annotated contextual utterances due to annotation cost, resulting in an imbalance compared to non-contextual utterances. Therefore, parsers must adapt to contextual utterances with a few training examples. We examine four major paradigms for doing so in conversational semantic parsing i.e., Parse-with-Utterance-History, Parse-with-Reference-Program, Parse-then-Resolve, and Rewrite-then-Parse. To facilitate such cross-paradigm comparisons, we construct SMCalFlow-EventQueries, a subset of contextual examples from SMCalFlow with additional annotations. Experiments with in-context learning and fine-tuning suggest that Rewrite-then-Parse is the most promising paradigm when holistically considering parsing accuracy, annotation cost, and error types.