@inproceedings{tripathi-etal-2026-ai,
title = "{AI}-Monitors at {S}em{E}val-2026 Task 4: A Hybrid Embedding and {LLM} Ensemble for Narrative Similarity",
author = "Tripathi, Vishnu and
-, Azad and
Joshi, Prakhar and
Sahoo, Pragyananda and
Kumar, Gaurav and
Arora, Piyush and
Mani, Neel",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.271/",
pages = "2139--2148",
ISBN = "979-8-89176-414-9",
abstract = "Narrative similarity requires reasoning over the deeper structural properties of stories - shared themes, causal progression, and outcomes - rather than surface-level lexical overlap. We describe AI-Monitors, our system for SemEval-2026 Task 4 (Track A), which determines which of two candidate stories is more narratively similar to a given anchor. We explore a progression of approaches - from embedding-based similarity to structured LLM prompting and ensemble construction - guided by four hypotheses about where narrative reasoning gains can be found. The final system achieves 75{\textbackslash}{\%} test accuracy on 400 instances, ranking 3rd out of 47 systems and approaching the individual human annotator ceiling of 78{\textbackslash}{\%}.Our key findings are: i) structured few-shot prompting substantially outperforms dense embedding similarity; ii) selecting ensemble components by how differently they make errors - rather than by accuracy alone - produces stronger predictions; and iii) how you describe an example to the model affects its predictions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tripathi-etal-2026-ai">
<titleInfo>
<title>AI-Monitors at SemEval-2026 Task 4: A Hybrid Embedding and LLM Ensemble for Narrative Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishnu</namePart>
<namePart type="family">Tripathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azad</namePart>
<namePart type="family">-</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prakhar</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pragyananda</namePart>
<namePart type="family">Sahoo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piyush</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neel</namePart>
<namePart type="family">Mani</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 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>Narrative similarity requires reasoning over the deeper structural properties of stories - shared themes, causal progression, and outcomes - rather than surface-level lexical overlap. We describe AI-Monitors, our system for SemEval-2026 Task 4 (Track A), which determines which of two candidate stories is more narratively similar to a given anchor. We explore a progression of approaches - from embedding-based similarity to structured LLM prompting and ensemble construction - guided by four hypotheses about where narrative reasoning gains can be found. The final system achieves 75\textbackslash% test accuracy on 400 instances, ranking 3rd out of 47 systems and approaching the individual human annotator ceiling of 78\textbackslash%.Our key findings are: i) structured few-shot prompting substantially outperforms dense embedding similarity; ii) selecting ensemble components by how differently they make errors - rather than by accuracy alone - produces stronger predictions; and iii) how you describe an example to the model affects its predictions.</abstract>
<identifier type="citekey">tripathi-etal-2026-ai</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.271/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2139</start>
<end>2148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AI-Monitors at SemEval-2026 Task 4: A Hybrid Embedding and LLM Ensemble for Narrative Similarity
%A Tripathi, Vishnu
%A -, Azad
%A Joshi, Prakhar
%A Sahoo, Pragyananda
%A Kumar, Gaurav
%A Arora, Piyush
%A Mani, Neel
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F tripathi-etal-2026-ai
%X Narrative similarity requires reasoning over the deeper structural properties of stories - shared themes, causal progression, and outcomes - rather than surface-level lexical overlap. We describe AI-Monitors, our system for SemEval-2026 Task 4 (Track A), which determines which of two candidate stories is more narratively similar to a given anchor. We explore a progression of approaches - from embedding-based similarity to structured LLM prompting and ensemble construction - guided by four hypotheses about where narrative reasoning gains can be found. The final system achieves 75\textbackslash% test accuracy on 400 instances, ranking 3rd out of 47 systems and approaching the individual human annotator ceiling of 78\textbackslash%.Our key findings are: i) structured few-shot prompting substantially outperforms dense embedding similarity; ii) selecting ensemble components by how differently they make errors - rather than by accuracy alone - produces stronger predictions; and iii) how you describe an example to the model affects its predictions.
%U https://aclanthology.org/2026.semeval-1.271/
%P 2139-2148
Markdown (Informal)
[AI-Monitors at SemEval-2026 Task 4: A Hybrid Embedding and LLM Ensemble for Narrative Similarity](https://aclanthology.org/2026.semeval-1.271/) (Tripathi et al., SemEval 2026)
ACL
- Vishnu Tripathi, Azad -, Prakhar Joshi, Pragyananda Sahoo, Gaurav Kumar, Piyush Arora, and Neel Mani. 2026. AI-Monitors at SemEval-2026 Task 4: A Hybrid Embedding and LLM Ensemble for Narrative Similarity. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2139–2148, San Diego, California, USA. Association for Computational Linguistics.