@inproceedings{xie-etal-2026-fbks,
title = "{FBK}{'}s Long-form {S}peech{LLM}s for {IWSLT} 2026 Instruction Following",
author = "Xie, Zhihang and
Gaido, Marco and
Papi, Sara and
Negri, Matteo and
Bentivogli, Luisa",
editor = "Salesky, Elizabeth and
Anastasopoulos, Antonios and
Negri, Matteo and
Federico, Marcello",
booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
month = jul,
year = "2026",
address = "San Diego, USA (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwslt-1.29/",
pages = "255--267",
ISBN = "979-8-89176-411-8",
abstract = "This paper describes our submission to the IWSLT 2026 Instruction Following shared task. SpeechLLM systems are developed for both short-form and long-form speech instruction following under constrained settings. For the short track, strong performance is achieved on MCIF, with a SIFS score of 2.0708. For the long track, three speech segmentation strategies are investigated, and the HIFS score is introduced to account for unstable long-form generation. Experimental results show that fixed 30-second segmentation provides the most robust long-form performance, achieving the highest HIFS score of 2.0663. Further analysis shows that hallucination mainly manifests as repetitive insertions, substantially affecting ASR and SSUM, while short-form capabilities are largely retained after long-form extension."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xie-etal-2026-fbks">
<titleInfo>
<title>FBK’s Long-form SpeechLLMs for IWSLT 2026 Instruction Following</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Gaido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</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 23rd International Conference on Spoken Language Translation (IWSLT 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, USA (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-411-8</identifier>
</relatedItem>
<abstract>This paper describes our submission to the IWSLT 2026 Instruction Following shared task. SpeechLLM systems are developed for both short-form and long-form speech instruction following under constrained settings. For the short track, strong performance is achieved on MCIF, with a SIFS score of 2.0708. For the long track, three speech segmentation strategies are investigated, and the HIFS score is introduced to account for unstable long-form generation. Experimental results show that fixed 30-second segmentation provides the most robust long-form performance, achieving the highest HIFS score of 2.0663. Further analysis shows that hallucination mainly manifests as repetitive insertions, substantially affecting ASR and SSUM, while short-form capabilities are largely retained after long-form extension.</abstract>
<identifier type="citekey">xie-etal-2026-fbks</identifier>
<location>
<url>https://aclanthology.org/2026.iwslt-1.29/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>255</start>
<end>267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FBK’s Long-form SpeechLLMs for IWSLT 2026 Instruction Following
%A Xie, Zhihang
%A Gaido, Marco
%A Papi, Sara
%A Negri, Matteo
%A Bentivogli, Luisa
%Y Salesky, Elizabeth
%Y Anastasopoulos, Antonios
%Y Negri, Matteo
%Y Federico, Marcello
%S Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, USA (in-person and online)
%@ 979-8-89176-411-8
%F xie-etal-2026-fbks
%X This paper describes our submission to the IWSLT 2026 Instruction Following shared task. SpeechLLM systems are developed for both short-form and long-form speech instruction following under constrained settings. For the short track, strong performance is achieved on MCIF, with a SIFS score of 2.0708. For the long track, three speech segmentation strategies are investigated, and the HIFS score is introduced to account for unstable long-form generation. Experimental results show that fixed 30-second segmentation provides the most robust long-form performance, achieving the highest HIFS score of 2.0663. Further analysis shows that hallucination mainly manifests as repetitive insertions, substantially affecting ASR and SSUM, while short-form capabilities are largely retained after long-form extension.
%U https://aclanthology.org/2026.iwslt-1.29/
%P 255-267
Markdown (Informal)
[FBK’s Long-form SpeechLLMs for IWSLT 2026 Instruction Following](https://aclanthology.org/2026.iwslt-1.29/) (Xie et al., IWSLT 2026)
ACL
- Zhihang Xie, Marco Gaido, Sara Papi, Matteo Negri, and Luisa Bentivogli. 2026. FBK’s Long-form SpeechLLMs for IWSLT 2026 Instruction Following. In Proceedings of the 23rd International Conference on Spoken Language Translation (IWSLT 2026), pages 255–267, San Diego, USA (in-person and online). Association for Computational Linguistics.