@inproceedings{singh-mishra-2026-conceptweave,
title = "{C}oncept{W}eave: Concept-Driven Prompting through Adaptive Semantic Infilling",
author = "Singh, Atul Kumar and
Mishra, Rahul",
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.187/",
pages = "4190--4207",
ISBN = "979-8-89176-439-2",
abstract = "Conventional prompting and prompt-based finetuning offer only weak semantic structure, leaving models to derive task-specific reasoning from limited cues. Existing techniques, such as using demonstrations, chain-of-thought prompting, or retrieval augmentation, can improve performance, but often at the cost of longer, more redundant prompts, higher inference overhead, and reliance on external knowledge sources. We present ConceptWeave, a novel concept-centric prompt-based finetuning approach built on adaptive semantic infilling. Instead of depending on external resources, it extracts concise, task-relevant concepts directly from a small portion of downstream data and organizes them into a dynamically evolving hierarchical memory. During fine-tuning, ConceptWeave identifies informative spans in the input through semantic alignment and augments them with corresponding concept representations, enabling fine-grained, localized conditioning of the model. As training progresses, the concepts are continuously refined and structured into a hierarchy that supports efficient retrieval while preserving semantic richness and scalability. We validate ConceptWeave across a range of NLP tasks, including misinformation detection, question answering, sentiment analysis, and hate speech classification, where it consistently outperforms strong baselines and recent state-of-the-art methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-mishra-2026-conceptweave">
<titleInfo>
<title>ConceptWeave: Concept-Driven Prompting through Adaptive Semantic Infilling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Mishra</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>Conventional prompting and prompt-based finetuning offer only weak semantic structure, leaving models to derive task-specific reasoning from limited cues. Existing techniques, such as using demonstrations, chain-of-thought prompting, or retrieval augmentation, can improve performance, but often at the cost of longer, more redundant prompts, higher inference overhead, and reliance on external knowledge sources. We present ConceptWeave, a novel concept-centric prompt-based finetuning approach built on adaptive semantic infilling. Instead of depending on external resources, it extracts concise, task-relevant concepts directly from a small portion of downstream data and organizes them into a dynamically evolving hierarchical memory. During fine-tuning, ConceptWeave identifies informative spans in the input through semantic alignment and augments them with corresponding concept representations, enabling fine-grained, localized conditioning of the model. As training progresses, the concepts are continuously refined and structured into a hierarchy that supports efficient retrieval while preserving semantic richness and scalability. We validate ConceptWeave across a range of NLP tasks, including misinformation detection, question answering, sentiment analysis, and hate speech classification, where it consistently outperforms strong baselines and recent state-of-the-art methods.</abstract>
<identifier type="citekey">singh-mishra-2026-conceptweave</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.187/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>4190</start>
<end>4207</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ConceptWeave: Concept-Driven Prompting through Adaptive Semantic Infilling
%A Singh, Atul Kumar
%A Mishra, Rahul
%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 singh-mishra-2026-conceptweave
%X Conventional prompting and prompt-based finetuning offer only weak semantic structure, leaving models to derive task-specific reasoning from limited cues. Existing techniques, such as using demonstrations, chain-of-thought prompting, or retrieval augmentation, can improve performance, but often at the cost of longer, more redundant prompts, higher inference overhead, and reliance on external knowledge sources. We present ConceptWeave, a novel concept-centric prompt-based finetuning approach built on adaptive semantic infilling. Instead of depending on external resources, it extracts concise, task-relevant concepts directly from a small portion of downstream data and organizes them into a dynamically evolving hierarchical memory. During fine-tuning, ConceptWeave identifies informative spans in the input through semantic alignment and augments them with corresponding concept representations, enabling fine-grained, localized conditioning of the model. As training progresses, the concepts are continuously refined and structured into a hierarchy that supports efficient retrieval while preserving semantic richness and scalability. We validate ConceptWeave across a range of NLP tasks, including misinformation detection, question answering, sentiment analysis, and hate speech classification, where it consistently outperforms strong baselines and recent state-of-the-art methods.
%U https://aclanthology.org/2026.aacl-long.187/
%P 4190-4207
Markdown (Informal)
[ConceptWeave: Concept-Driven Prompting through Adaptive Semantic Infilling](https://aclanthology.org/2026.aacl-long.187/) (Singh & Mishra, AACL-IJCNLP 2026)
ACL
- Atul Kumar Singh and Rahul Mishra. 2026. ConceptWeave: Concept-Driven Prompting through Adaptive Semantic Infilling. 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 4190–4207, Hengqin, China. Association for Computational Linguistics.