@inproceedings{colli-etal-2026-tfb,
title = "{TFB} at {S}em{E}val-2026 Task 4: Diagnosing Model Failures in Narrative Understanding",
author = "Colli, Anna and
Rachmat, Benedictus Kent and
Sauvage, Eve and
Battistelli, Delphine and
Gerald, Thomas and
Grouin, Cyril and
Tourille, Julien and
Zhang, Zheng",
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-1.367/",
pages = "2932--2938",
ISBN = "979-8-89176-414-9",
abstract = "We describe the participation of team TFB in SemEval-2026 Task 4 on narrative similarity. We explore ColBERT-inspired sentence-level late interaction to capture event reordering, compare fine-tuning with synthetic data at multiple difficulty tiers, finding that distribution proximity to the target data matters more than volume and evaluate chain-of-thought prompting. We complement our approaches with a human annotation study (Krippendorff{'}s alpha=0.32) confirming the task{'}s inherent difficulty, an analysis of synthetic data distribution shift explaining why fine-tuning on out-of-distribution data hurts the model{'}s performance. Despite our tests, we didn{'}t surpass results of sentence-t5-xxl on Track B and Qwen2.5-7B on Track A. We finally decided to submit these two models for the task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="colli-etal-2026-tfb">
<titleInfo>
<title>TFB at SemEval-2026 Task 4: Diagnosing Model Failures in Narrative Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Colli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benedictus</namePart>
<namePart type="given">Kent</namePart>
<namePart type="family">Rachmat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eve</namePart>
<namePart type="family">Sauvage</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Delphine</namePart>
<namePart type="family">Battistelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Gerald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyril</namePart>
<namePart type="family">Grouin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julien</namePart>
<namePart type="family">Tourille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Zhang</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>We describe the participation of team TFB in SemEval-2026 Task 4 on narrative similarity. We explore ColBERT-inspired sentence-level late interaction to capture event reordering, compare fine-tuning with synthetic data at multiple difficulty tiers, finding that distribution proximity to the target data matters more than volume and evaluate chain-of-thought prompting. We complement our approaches with a human annotation study (Krippendorff’s alpha=0.32) confirming the task’s inherent difficulty, an analysis of synthetic data distribution shift explaining why fine-tuning on out-of-distribution data hurts the model’s performance. Despite our tests, we didn’t surpass results of sentence-t5-xxl on Track B and Qwen2.5-7B on Track A. We finally decided to submit these two models for the task.</abstract>
<identifier type="citekey">colli-etal-2026-tfb</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.367/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2932</start>
<end>2938</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TFB at SemEval-2026 Task 4: Diagnosing Model Failures in Narrative Understanding
%A Colli, Anna
%A Rachmat, Benedictus Kent
%A Sauvage, Eve
%A Battistelli, Delphine
%A Gerald, Thomas
%A Grouin, Cyril
%A Tourille, Julien
%A Zhang, Zheng
%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 colli-etal-2026-tfb
%X We describe the participation of team TFB in SemEval-2026 Task 4 on narrative similarity. We explore ColBERT-inspired sentence-level late interaction to capture event reordering, compare fine-tuning with synthetic data at multiple difficulty tiers, finding that distribution proximity to the target data matters more than volume and evaluate chain-of-thought prompting. We complement our approaches with a human annotation study (Krippendorff’s alpha=0.32) confirming the task’s inherent difficulty, an analysis of synthetic data distribution shift explaining why fine-tuning on out-of-distribution data hurts the model’s performance. Despite our tests, we didn’t surpass results of sentence-t5-xxl on Track B and Qwen2.5-7B on Track A. We finally decided to submit these two models for the task.
%U https://aclanthology.org/2026.semeval-1.367/
%P 2932-2938
Markdown (Informal)
[TFB at SemEval-2026 Task 4: Diagnosing Model Failures in Narrative Understanding](https://aclanthology.org/2026.semeval-1.367/) (Colli et al., SemEval 2026)
ACL
- Anna Colli, Benedictus Kent Rachmat, Eve Sauvage, Delphine Battistelli, Thomas Gerald, Cyril Grouin, Julien Tourille, and Zheng Zhang. 2026. TFB at SemEval-2026 Task 4: Diagnosing Model Failures in Narrative Understanding. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2932–2938, San Diego, California, USA. Association for Computational Linguistics.