@inproceedings{takahashi-etal-2025-llms,
title = "Can {LLM}s Learn from Their Mistakes? Self-Correcting Instruction Tuning for Named Entity Recognition",
author = "Takahashi, Takumi and
Taniguchi, Tomoki and
Zhu, Chencheng and
Ohkuma, Tomoko",
editor = "Inui, Kentaro and
Sakti, Sakriani and
Wang, Haofen and
Wong, Derek F. and
Bhattacharyya, Pushpak and
Banerjee, Biplab and
Ekbal, Asif and
Chakraborty, Tanmoy and
Singh, Dhirendra Pratap",
booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-ijcnlp.106/",
pages = "1695--1712",
ISBN = "979-8-89176-303-6",
abstract = "Recent instruction-tuned large language models (LLMs) have demonstrated remarkable performance on various downstream tasks, including named entity recognition (NER). However, previous approaches often generate incorrect predictions, particularly regarding entity boundaries and types. Many of these errors can be corrected to match the ground truth by revising the entity boundaries and/or types. In this paper, we propose a self-correcting instruction tuning approach that simultaneously learns to perform NER and correct errors through natural language instructions. Self-correcting instruction tuning requires only a standard annotated NER dataset. Supervision for self-correction can be automatically generated from error patterns observed in LLMs fine-tuned solely on NER tasks. We conducted extensive experiments on eight NER datasets with two LLMs to validate the effectiveness of the proposed approach. The results demonstrate that the proposed approach enhances NER performance by effectively correcting prediction errors and substantially reducing false positives. We further analyze the self-correction behavior to better understand how the models improve performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takahashi-etal-2025-llms">
<titleInfo>
<title>Can LLMs Learn from Their Mistakes? Self-Correcting Instruction Tuning for Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Takumi</namePart>
<namePart type="family">Takahashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Taniguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chencheng</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoko</namePart>
<namePart type="family">Ohkuma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haofen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biplab</namePart>
<namePart type="family">Banerjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhirendra</namePart>
<namePart type="given">Pratap</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The Asian Federation of Natural Language Processing and The Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-303-6</identifier>
</relatedItem>
<abstract>Recent instruction-tuned large language models (LLMs) have demonstrated remarkable performance on various downstream tasks, including named entity recognition (NER). However, previous approaches often generate incorrect predictions, particularly regarding entity boundaries and types. Many of these errors can be corrected to match the ground truth by revising the entity boundaries and/or types. In this paper, we propose a self-correcting instruction tuning approach that simultaneously learns to perform NER and correct errors through natural language instructions. Self-correcting instruction tuning requires only a standard annotated NER dataset. Supervision for self-correction can be automatically generated from error patterns observed in LLMs fine-tuned solely on NER tasks. We conducted extensive experiments on eight NER datasets with two LLMs to validate the effectiveness of the proposed approach. The results demonstrate that the proposed approach enhances NER performance by effectively correcting prediction errors and substantially reducing false positives. We further analyze the self-correction behavior to better understand how the models improve performance.</abstract>
<identifier type="citekey">takahashi-etal-2025-llms</identifier>
<location>
<url>https://aclanthology.org/2025.findings-ijcnlp.106/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>1695</start>
<end>1712</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can LLMs Learn from Their Mistakes? Self-Correcting Instruction Tuning for Named Entity Recognition
%A Takahashi, Takumi
%A Taniguchi, Tomoki
%A Zhu, Chencheng
%A Ohkuma, Tomoko
%Y Inui, Kentaro
%Y Sakti, Sakriani
%Y Wang, Haofen
%Y Wong, Derek F.
%Y Bhattacharyya, Pushpak
%Y Banerjee, Biplab
%Y Ekbal, Asif
%Y Chakraborty, Tanmoy
%Y Singh, Dhirendra Pratap
%S Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics
%D 2025
%8 December
%I The Asian Federation of Natural Language Processing and The Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-303-6
%F takahashi-etal-2025-llms
%X Recent instruction-tuned large language models (LLMs) have demonstrated remarkable performance on various downstream tasks, including named entity recognition (NER). However, previous approaches often generate incorrect predictions, particularly regarding entity boundaries and types. Many of these errors can be corrected to match the ground truth by revising the entity boundaries and/or types. In this paper, we propose a self-correcting instruction tuning approach that simultaneously learns to perform NER and correct errors through natural language instructions. Self-correcting instruction tuning requires only a standard annotated NER dataset. Supervision for self-correction can be automatically generated from error patterns observed in LLMs fine-tuned solely on NER tasks. We conducted extensive experiments on eight NER datasets with two LLMs to validate the effectiveness of the proposed approach. The results demonstrate that the proposed approach enhances NER performance by effectively correcting prediction errors and substantially reducing false positives. We further analyze the self-correction behavior to better understand how the models improve performance.
%U https://aclanthology.org/2025.findings-ijcnlp.106/
%P 1695-1712
Markdown (Informal)
[Can LLMs Learn from Their Mistakes? Self-Correcting Instruction Tuning for Named Entity Recognition](https://aclanthology.org/2025.findings-ijcnlp.106/) (Takahashi et al., Findings 2025)
ACL
- Takumi Takahashi, Tomoki Taniguchi, Chencheng Zhu, and Tomoko Ohkuma. 2025. Can LLMs Learn from Their Mistakes? Self-Correcting Instruction Tuning for Named Entity Recognition. In Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, pages 1695–1712, Mumbai, India. The Asian Federation of Natural Language Processing and The Association for Computational Linguistics.