@inproceedings{maji-etal-2026-remind,
title = "{REMIND}: Enhancing {C}o{T} Reliability with Self-Supervised Introspection",
author = "Maji, Souvik and
Bandyopadhyay, Dibyanayan and
Ekbal, Asif",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.133/",
pages = "2917--2942",
ISBN = "979-8-89176-439-2",
abstract = "Chain-of-Thought (CoT) prompting has significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, CoT can also produce fluent but logically flawed reasoning chains that make incorrect answers appear more reliable. In this work, we introduce REMIND (Reliability Enhancement via Metacognitive INtrospection and Debiasing), a framework that enables LLMs to learn from their own failures via episodic memory. Unlike standard error-correction methods that rely on external feedback or extensive fine-tuning, REMIND leverages a self-supervised introspection cycle. We first isolate epistemic failure{---}instances where CoT decreases model confidence despite yielding incorrect results. The model then performs structured introspection to diagnose the root cause and synthesizes a reusable natural language lesson. These lessons are stored in a vector database and retrieved during future inference steps to correct similar future errors. Experiments on eight diverse reasoning benchmarks spanning mathematical, scientific, multi-hop, truthfulness, and commonsense reasoning demonstrate that REMIND significantly improves reliability by effectively converting past CoT failures into actionable insights for unseen problems. Codes are available in https://github.com/newcodevelop/REMIND."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maji-etal-2026-remind">
<titleInfo>
<title>REMIND: Enhancing CoT Reliability with Self-Supervised Introspection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Souvik</namePart>
<namePart type="family">Maji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dibyanayan</namePart>
<namePart type="family">Bandyopadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Chain-of-Thought (CoT) prompting has significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, CoT can also produce fluent but logically flawed reasoning chains that make incorrect answers appear more reliable. In this work, we introduce REMIND (Reliability Enhancement via Metacognitive INtrospection and Debiasing), a framework that enables LLMs to learn from their own failures via episodic memory. Unlike standard error-correction methods that rely on external feedback or extensive fine-tuning, REMIND leverages a self-supervised introspection cycle. We first isolate epistemic failure—instances where CoT decreases model confidence despite yielding incorrect results. The model then performs structured introspection to diagnose the root cause and synthesizes a reusable natural language lesson. These lessons are stored in a vector database and retrieved during future inference steps to correct similar future errors. Experiments on eight diverse reasoning benchmarks spanning mathematical, scientific, multi-hop, truthfulness, and commonsense reasoning demonstrate that REMIND significantly improves reliability by effectively converting past CoT failures into actionable insights for unseen problems. Codes are available in https://github.com/newcodevelop/REMIND.</abstract>
<identifier type="citekey">maji-etal-2026-remind</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.133/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2917</start>
<end>2942</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REMIND: Enhancing CoT Reliability with Self-Supervised Introspection
%A Maji, Souvik
%A Bandyopadhyay, Dibyanayan
%A Ekbal, Asif
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F maji-etal-2026-remind
%X Chain-of-Thought (CoT) prompting has significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, CoT can also produce fluent but logically flawed reasoning chains that make incorrect answers appear more reliable. In this work, we introduce REMIND (Reliability Enhancement via Metacognitive INtrospection and Debiasing), a framework that enables LLMs to learn from their own failures via episodic memory. Unlike standard error-correction methods that rely on external feedback or extensive fine-tuning, REMIND leverages a self-supervised introspection cycle. We first isolate epistemic failure—instances where CoT decreases model confidence despite yielding incorrect results. The model then performs structured introspection to diagnose the root cause and synthesizes a reusable natural language lesson. These lessons are stored in a vector database and retrieved during future inference steps to correct similar future errors. Experiments on eight diverse reasoning benchmarks spanning mathematical, scientific, multi-hop, truthfulness, and commonsense reasoning demonstrate that REMIND significantly improves reliability by effectively converting past CoT failures into actionable insights for unseen problems. Codes are available in https://github.com/newcodevelop/REMIND.
%U https://aclanthology.org/2026.aacl-long.133/
%P 2917-2942
Markdown (Informal)
[REMIND: Enhancing CoT Reliability with Self-Supervised Introspection](https://aclanthology.org/2026.aacl-long.133/) (Maji et al., AACL-IJCNLP 2026)
ACL
- Souvik Maji, Dibyanayan Bandyopadhyay, and Asif Ekbal. 2026. REMIND: Enhancing CoT Reliability with Self-Supervised Introspection. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2917–2942, Hengqin, China. Association for Computational Linguistics.