PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering

• URL: http://arxiv.org/abs/2608.20757v1
• Date: Fri, 21 Aug 2026 05:37:57 GMT
• Title: PSK at WMT 2026 MIST: Task-Specialized QLoRA Adapters for Multilingual Summarization and Question Answering
• Abstract summary: We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task.<n>Our system uses the 3.35B- parameter Tiny Aya Global model with three QLoRA adapters, one for each task.<n>Results for open QA are mixed and vary with answer length and evaluation method.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We describe the PSK submission to the WMT 2026 Multilingual Instruction Shared Task. Our system uses the 3.35B-parameter Tiny Aya Global model with three QLoRA adapters, one for each task. The adapters are trained on multilingual document-summary pairs, passage-based question answering, and filtered standalone question answering. The summarization data also includes scientific papers with their author-written abstracts. On our held-out split, the context and summarization adapters perform better than our multitask adapter, which was trained only on data supplied by the organizers. Results for open QA are mixed and vary with answer length and evaluation method. We therefore submit three systems with the same context and summarization adapters but different open-QA adapters.

Related papers

• PeerQA: A Scientific Question Answering Dataset from Peer Reviews [51.95579001315713]
  We present PeerQA, a real-world, scientific, document-level Question Answering dataset.<n>The dataset contains 579 QA pairs from 208 academic articles, with a majority from ML and NLP.<n>We provide a detailed analysis of the collected dataset and conduct experiments establishing baseline systems for all three tasks.
  arXiv  Detail & Related papers  (2025-02-19T12:24:46Z)
• Pilot: Building the Federated Multimodal Instruction Tuning Framework [79.56362403673354]
  Our framework integrates two stages of "adapter on adapter" into the connector of the vision encoder and the LLM.<n>In stage 1, we extract task-specific features and client-specific features from visual information.<n>In stage 2, we build the cross-task Mixture-of-Adapters(CT-MoA) module to perform cross-task interaction.
  arXiv  Detail & Related papers  (2025-01-23T07:49:24Z)
• GenAI Content Detection Task 1: English and Multilingual Machine-Generated Text Detection: AI vs. Human [71.42669028683741]
  We present a shared task on binary machine generated text detection conducted as a part of the GenAI workshop at COLING 2025.<n>The task consists of two subtasks: Monolingual (English) and Multilingual.<n>We provide a comprehensive overview of the data, a summary of the results, detailed descriptions of the participating systems, and an in-depth analysis of submissions.
  arXiv  Detail & Related papers  (2025-01-19T11:11:55Z)
• Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass [109.34230156454574]
  Large language models (LMs) are typically adapted to improve performance on new contexts. fine-tuning incurs significant training cost and prompting increases inference overhead. We introduce $GenerativeAdapter$, an effective and efficient adaptation method that directly maps new contexts to low-rank LM adapters.
  arXiv  Detail & Related papers  (2024-11-08T00:42:47Z)
• MARAGS: A Multi-Adapter System for Multi-Task Retrieval Augmented Generation Question Answering [0.43512163406552007]
  We present a multi-adapter retrieval augmented generation system (MARAGS) for Meta's Comprehensive RAG (CRAG) competition for KDD CUP 2024. Our system achieved 2nd place for Task 1 as well as 3rd place on Task 2.
  arXiv  Detail & Related papers  (2024-09-05T01:58:29Z)
• Stylus: Automatic Adapter Selection for Diffusion Models [81.90482700433822]
  We introduce Stylus, which efficiently selects and automatically composes task-specific adapters based on a prompt's keywords. Stylus outlines a three-stage approach that first summarizes adapters with improved descriptions and embeddings, retrieves relevant adapters, and then further assembles adapters based on prompts' keywords by checking how well they fit the prompt.
  arXiv  Detail & Related papers  (2024-04-29T17:59:16Z)
• AAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual Relatedness [16.896143197472114]
  This paper presents our system developed for the SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian languages. We propose using machine translation for data augmentation to address the low-resource challenge of limited training data. We achieve competitive results in the shared task: our system performs the best among all ranked teams in both subtask A (supervised learning) and subtask C (cross-lingual transfer)
  arXiv  Detail & Related papers  (2024-04-01T21:21:15Z)
• Visconde: Multi-document QA with GPT-3 and Neural Reranking [4.9069311006119865]
  This paper proposes a question-answering system that can answer questions whose supporting evidence is spread over multiple documents. The system, called Visconde, uses a three-step pipeline to perform the task: decompose, retrieve, and aggregate.
  arXiv  Detail & Related papers  (2022-12-19T17:39:07Z)
• Multi-Head Adapter Routing for Cross-Task Generalization [56.75667096355806]
  Polytropon learns an inventory of adapters and a routing function that selects a subset of adapters for each task during both pre-training and few-shot adaptation. We find that routing is most beneficial during multi-task pre-training rather than during few-shot adaptation.
  arXiv  Detail & Related papers  (2022-11-07T19:35:55Z)
• Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Task [95.06453182273027]
  This report describes Microsoft's machine translation systems for the WMT21 shared task on large-scale multilingual machine translation. Our model submissions to the shared task were with DeltaLMnotefooturlhttps://aka.ms/deltalm, a generic pre-trained multilingual-decoder model. Our final submissions ranked first on three tracks in terms of the automatic evaluation metric.
  arXiv  Detail & Related papers  (2021-11-03T09:16:17Z)
• Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks [37.2958914602899]
  We show that we can learn adapter parameters for all layers and tasks by generating them using shared hypernetworks. Experiments on the well-known GLUE benchmark show improved performance in multi-task learning while adding only 0.29% parameters per task.
  arXiv  Detail & Related papers  (2021-06-08T16:16:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.