@inproceedings{shuai-etal-2026-learning,
title = "Learning from Near-Misses: Error-Aware Contrastive Few-Shot Learning for {NL}2{F}ormula",
author = "Shuai, Zhihao and
Chen, Yiyun and
Ma, Maolin and
Chen, Yutong and
Qiu, Hanjia and
Xu, Jing and
Chen, Ziye and
Yang, Weikai",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1368/",
pages = "29662--29676",
ISBN = "979-8-89176-390-6",
abstract = "Natural Language to Excel Formula (NL2Formula) translates user intent into executable spreadsheet formulas. However, current models often produce near-miss outputs{---}formulas that parse correctly yet fail at execution due to an incorrect function, operator, or reference. Through a systematic error analysis, we find that these errors repeatedly arise from a small set of structural decision points, motivating the need for typed error supervision rather than general error signals. To this end, we introduce an abstract syntax tree (AST)-based error taxonomy that organizes common error modes by the kind of decision that goes wrong in the parse tree. Building on this taxonomy, we propose Error-Aware Contrastive Few-Shot Learning (ECFL), an error-aware framework that unifies training and inference around typed error supervision. During offline training, ECFL mines near-miss errors, assigns error types under the taxonomy, and builds error-aware contrastive demonstrations for fine-tuning. During online inference, a lightweight predictor estimates likely error types and triggers targeted retrieval of contrastive demonstrations to guide single-pass decoding. Experiments show ECFL improves Exact Match (EM) by 6.4 points over supervised fine-tuning (SFT) and matches self-consistency (SC@5) accuracy at substantially lower inference cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shuai-etal-2026-learning">
<titleInfo>
<title>Learning from Near-Misses: Error-Aware Contrastive Few-Shot Learning for NL2Formula</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihao</namePart>
<namePart type="family">Shuai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maolin</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjia</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziye</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weikai</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Natural Language to Excel Formula (NL2Formula) translates user intent into executable spreadsheet formulas. However, current models often produce near-miss outputs—formulas that parse correctly yet fail at execution due to an incorrect function, operator, or reference. Through a systematic error analysis, we find that these errors repeatedly arise from a small set of structural decision points, motivating the need for typed error supervision rather than general error signals. To this end, we introduce an abstract syntax tree (AST)-based error taxonomy that organizes common error modes by the kind of decision that goes wrong in the parse tree. Building on this taxonomy, we propose Error-Aware Contrastive Few-Shot Learning (ECFL), an error-aware framework that unifies training and inference around typed error supervision. During offline training, ECFL mines near-miss errors, assigns error types under the taxonomy, and builds error-aware contrastive demonstrations for fine-tuning. During online inference, a lightweight predictor estimates likely error types and triggers targeted retrieval of contrastive demonstrations to guide single-pass decoding. Experiments show ECFL improves Exact Match (EM) by 6.4 points over supervised fine-tuning (SFT) and matches self-consistency (SC@5) accuracy at substantially lower inference cost.</abstract>
<identifier type="citekey">shuai-etal-2026-learning</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1368/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>29662</start>
<end>29676</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning from Near-Misses: Error-Aware Contrastive Few-Shot Learning for NL2Formula
%A Shuai, Zhihao
%A Chen, Yiyun
%A Ma, Maolin
%A Chen, Yutong
%A Qiu, Hanjia
%A Xu, Jing
%A Chen, Ziye
%A Yang, Weikai
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F shuai-etal-2026-learning
%X Natural Language to Excel Formula (NL2Formula) translates user intent into executable spreadsheet formulas. However, current models often produce near-miss outputs—formulas that parse correctly yet fail at execution due to an incorrect function, operator, or reference. Through a systematic error analysis, we find that these errors repeatedly arise from a small set of structural decision points, motivating the need for typed error supervision rather than general error signals. To this end, we introduce an abstract syntax tree (AST)-based error taxonomy that organizes common error modes by the kind of decision that goes wrong in the parse tree. Building on this taxonomy, we propose Error-Aware Contrastive Few-Shot Learning (ECFL), an error-aware framework that unifies training and inference around typed error supervision. During offline training, ECFL mines near-miss errors, assigns error types under the taxonomy, and builds error-aware contrastive demonstrations for fine-tuning. During online inference, a lightweight predictor estimates likely error types and triggers targeted retrieval of contrastive demonstrations to guide single-pass decoding. Experiments show ECFL improves Exact Match (EM) by 6.4 points over supervised fine-tuning (SFT) and matches self-consistency (SC@5) accuracy at substantially lower inference cost.
%U https://aclanthology.org/2026.acl-long.1368/
%P 29662-29676
Markdown (Informal)
[Learning from Near-Misses: Error-Aware Contrastive Few-Shot Learning for NL2Formula](https://aclanthology.org/2026.acl-long.1368/) (Shuai et al., ACL 2026)
ACL
- Zhihao Shuai, Yiyun Chen, Maolin Ma, Yutong Chen, Hanjia Qiu, Jing Xu, Ziye Chen, and Weikai Yang. 2026. Learning from Near-Misses: Error-Aware Contrastive Few-Shot Learning for NL2Formula. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 29662–29676, San Diego, California, United States. Association for Computational Linguistics.