# FBK's Long-form SpeechLLMs for IWSLT 2026 Instruction Following

arXiv: https://arxiv.org/abs/2606.26819 · HTML: https://mlsanity.com/paper/2606.26819/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 21 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates](https://mlsanity.com/paper/1911.03167/) (2019)
- [AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs](https://mlsanity.com/paper/2311.06753/) (2023)
- [GigaST: A 10,000-hour Pseudo Speech Translation Corpus](https://mlsanity.com/paper/2204.03939/) (2022)
- [Beyond Voice Activity Detection: Hybrid Audio Segmentation for Direct Speech Translation](https://mlsanity.com/paper/2104.11710/) (2021)
- [From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions](https://mlsanity.com/paper/2402.17633/) (2024)
- [Investigating End-to-End ASR Architectures for Long Form Audio Transcription](https://mlsanity.com/paper/2309.09950/) (2023)
- [Updated Corpora and Benchmarks for Long-Form Speech Recognition](https://mlsanity.com/paper/2309.15013/) (2023)
- [Investigating Decoder-only Large Language Models for Speech-to-text Translation](https://mlsanity.com/paper/2407.03169/) (2024)
- [Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison](https://mlsanity.com/paper/2501.02370/) (2025)
- [NAVER LABS Europe Submission to the Instruction-following Track](https://mlsanity.com/paper/2506.01808/) (2025)
- [KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 2025](https://mlsanity.com/paper/2505.13036/) (2025)

## Abstract (arXiv)

This paper describes our submission to the IWSLT 2026 Instruction Following shared task. SpeechLLMs 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 methods are explored, 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 in generated outputs, substantially affecting ASR and SSUM, while short-form capabilities are largely retained after long-form extension.