arXiv Computation and Language September 11, 2026 By Jordi Luque, Lorenzo Concina, Marco Matassoni, Alessio Brutti, Filippo Vella

The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge

Read the original on arXiv Computation and Language →

The Eloquence team presents three methods for the Interspeech 2026 MLC‑SLM Task 2, a multilingual MCQA challenge covering 21 languages. They fine‑tune Voxtral‑Mini‑3B with LoRA and data augmentation, achieving 0.72 macro‑accuracy; they use multimodal in‑context learning on Voxtral‑24B to correct label bias, reaching 0.81; and they deploy a training‑free retrieval system with a voice‑anchored memory, scoring 0.68. All approaches surpass the official baseline.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Sep 10

The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge

The Eloquence team presents three strategies for the Interspeech 2026 MLC‑SLM Task 2, a multilingual MCQA challenge across 21 languages. They fine‑tune Voxtral‑Mini‑3B with LoRA and cross‑lingual augmentations, achieving 0.72 macro‑accuracy; they use multimodal in‑context learning on the frozen Voxtral‑24B to correct label bias, reaching 0.81; and they deploy a training‑free retrieval system with a voice‑anchored memory, scoring 0.68. All approaches surpass the official baseline.

llms nlp fine-tuning multimodal safety

arXiv Computation and Language

Sep 22

Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models

arXiv:2609.22452v1 Announce Type: new Abstract: Long-context understanding remains a fundamental challenge for large language models, as excessively long inputs often lead models to forget salient in...

By Xize Cheng, Wenxu Jia, Chenyuhao Wen, Dongjie Fu, Zehan Wang, Xinyu Zhang, Tao Jin

llms rag benchmarks

arXiv AI

Aug 26

EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$

EXAM$^2$ is a new benchmark for audio understanding that covers six languages and multiple modalities—speech, sound, music, mixed-audio, and visual images—providing 5,667 multiple-choice questions, 22,614 image instances, and 135,684 multilingual translations. It evaluates large audio language models (LALMs) and multimodal large language models (LLMs), revealing significant gaps in multilingual and cross‑modal performance. The authors also introduce Gemma3n-EXAM$^2$, a lightweight fusion model that improves multilingual results by up to 12.4% and multimodal results by 21.7% over a strong baseline.

By Jiawen Wang, Xiaoxue Gao, Zi Haur Pang, Nancy F. Chen

llms fine-tuning multimodal benchmarks

arXiv AI

Jul 1

ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models

arXiv:2606. 30682v1 Announce Type: cross Abstract: Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space.

By Fengjie Lu, Chenang Jiang, Jiarui Hai, Helin Wang, Aaron Yee

llms rag nlp multimodal benchmarks

arXiv Computation and Language

Sep 22

The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding

arXiv:2609.22214v1 Announce Type: new Abstract: Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker...

By Shangkun Huang, Junchao Hu, Huan Shen, Guoji Wang, Yingao Wang, Shaosai Li, Wei Zou, Yunzhang Chen

nlp multimodal

arXiv AI

Oct 5

EXAM2: Extending Audio Understanding in Multilingual and Multimodal Analysis

arXiv:2608.23758v3 Announce Type: replace-cross Abstract: Recent large audio language models (LALMs) have achieved impressive progress in audio understanding. However, existing evaluations remain lar...

By Jiawen Wang, Xiaoxue Gao, Zi Haur Pang, Nancy F. Chen

llms fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge

Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models

EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}ultilingual$ $and$ $\underline{M}ultimodal$ $Analysis$

ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models

The Bairong System for MLC-SLM 2026: Dynamic Question-Aware Evidence Routing for Multilingual Conversational Speech Understanding

EXAM2: Extending Audio Understanding in Multilingual and Multimodal Analysis