arXiv Computation and Language November 2, 2026 By Eugene Matsumura, Yuki Arase

CEFR Level Assessment across Languages and Text Granularities

Read the original on arXiv Computation and Language →

The paper introduces a unified training objective that blends focal loss with supervised contrastive learning to improve automatic CEFR level assessment. This approach addresses class imbalance and ambiguous level boundaries by emphasizing hard examples and learning discriminative representations. Experiments on sentence- and document-level CEFR assessment in both monolingual and multilingual contexts show that the method outperforms strong baselines and sets new state‑of‑the‑art results on multiple benchmarks.

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.

arXiv Computation and Language

Aug 25

LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data

LuxIT is a monolingual instruction‑tuning dataset for Luxembourgish, created by synthesizing instruction‑answer pairs from native texts using the DeepSeek‑R1‑0528 model and a quality‑assurance LLM‑as‑judge process. The resulting 227,507 high‑quality pairs were used to fine‑tune 14 LLMs (≤15 B parameters), yielding an average accuracy increase of +5.37 percentage points on standardized Luxembourgish proficiency exams and improvements in macro‑averaged F1 on nine of the fourteen downstream NLP tasks. These findings demonstrate that synthetic monolingual data can effectively enhance LLM performance in low‑resource languages and reveal the complex relationship between exam performance and practical NLP gains.

By Julian Valline, Cedric Lothritz, Siwen Guo, Jordi Cabot

llms nlp fine-tuning benchmarks

arXiv Machine Learning

Jun 18

Fair Cognitive Impairment Detection Through Unlearning

arXiv:2606. 18571v1 Announce Type: new Abstract: Mild Cognitive Impairment (MCI) is a medical condition characterized by a noticeable decline in memory, language, or thinking abilities.

By William Nguyen, Jiali Cheng, Hadi Amiri

rag multimodal benchmarks

arXiv AI

Aug 7

Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation

arXiv:2608. 05785v1 Announce Type: cross Abstract: Multilingual text embedding models are commonly adapted using a single training objective across diverse tasks, despite different tasks requiring fundamentally different optimization strategies.

By Tirth Bhatt, Naren Kumar S, Mayank Singh

rag diffusion benchmarks

arXiv Computation and Language

Oct 8

Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring

arXiv:2610.09660v1 Announce Type: new Abstract: Automatic Short Answer Scoring (ASAS) requires models that can score student responses against question-specific criteria while remaining efficient and...

By Zhifan Sun, Sebastian Gombert, Fabian Zehner, Leon Camus, Longwei Cong, Hendrik Drachsler

llms benchmarks

arXiv Computation and Language

Oct 8

MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation

arXiv:2606.22272v2 Announce Type: replace Abstract: Applying pre-trained language models to new domains through full fine-tuning is computationally expensive and prone to catastrophic forgetting. To...

By Mohammed Rawhani, Dervi\c{s} Karabo\u{g}a, \"Ozkan Ufuk Nalbanto\u{g}lu, Alper Ba\c{s}t\"urk, Bahriye Akay

llms fine-tuning benchmarks

arXiv AI

Aug 7

Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors

arXiv:2608. 06300v1 Announce Type: new Abstract: Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it critical to show that their scores depend on speaking proficiency rather than irrelevant speaker attributes such as first language (L1) or age.

By Arya Labroo, Mengjie Qian, Kate Knill

llms rag diffusion multimodal safety

One email a morning, machine-written

Related stories

LuxIT: A Luxembourgish Instruction Tuning Dataset from Monolingual Seed Data

Fair Cognitive Impairment Detection Through Unlearning

Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation

Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring

MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation

Bias Analysis of L2 Speaking Assessment Systems Using Concept Activation Vectors