Adapting Multilingual Models to Code-Mixed Tasks via Model Merging

• URL: http://arxiv.org/abs/2510.19782v2
• Date: Thu, 23 Oct 2025 10:53:54 GMT
• Title: Adapting Multilingual Models to Code-Mixed Tasks via Model Merging
• Authors: Prashant Kodali, Vaishnavi Shivkumar, Swarang Joshi, Monojit Choudhary, Ponnurangam Kumaraguru, Manish Shrivastava,
• Abstract summary: We study model merging as a practical alternative to conventional adaptation strategies for code-mixed NLP.<n>We evaluate our approach for sentence classification (sentiment and hate speech) task in English-Hindi (En-Hi) and English-Spanish (En-Es) using XLM-R and Llama-3.2-1B models.
• Score: 9.620539727633274
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study model merging as a practical alternative to conventional adaptation strategies for code-mixed NLP. Starting from a multilingual base model, we: (i) perform continued pre-training (CPT) on unlabeled code-mixed text to obtain an adapted checkpoint, (ii) merge checkpoint with the base model, and (iii) fine-tune (FT) on the downstream task data. We evaluate our approach for sentence classification (sentiment and hate speech) task in English-Hindi (En-Hi) and English-Spanish (En-Es) using XLM-R and Llama-3.2-1B models. Our results show that merged models consistently outperform full fine-tuning and CPT->FT. We observe gains of 2--5 points in F1 over full fine-tuning and ~1-2 points over CPT->FT, indicating that unlabeled data is leveraged more effectively via merging than via CPT alone. Zero-/few-shot prompting with larger LLMs (e.g., Llama-3.3-70B) lags behind fine-tuned and merged checkpoints, underscoring limits of in-context learning for code-mixed inputs. We further test cross-pair transfer by training on En-Hi and evaluating on En-Ta and En-Ml: merged checkpoints transfer more strongly than monolingual-English baselines (e.g., TV/TIES variants reaching 0.65-0.68 F1 vs 0.61-0.63 for full fine-tuning), suggesting that code-mixed knowledge is a more reliable substrate for low-resource pairs. We conclude with adaptation recipes matched to common data regimes (labeled only; labeled+unlabeled; transfer-only) and discuss limitations and scaling considerations for broader tasks and larger models.

Related papers

• Binary Token-Level Classification with DeBERTa for All-Type MWE Identification: A Lightweight Approach with Linguistic Enhancement [1.8429656136522097]
  We present a comprehensive approach for multiword expression (MWE) identification that combines binary token-level classification, linguistic feature integration, and data augmentation.<n>Our DeBERTa-v3-large model achieves 69.8% F1 on the CoAM dataset, surpassing the best results (Qwen-72B, 57.8% F1) on this dataset by 12 points while using 165x fewer parameters.
  arXiv  Detail & Related papers  (2026-01-27T08:42:54Z)
• MobileLLM-R1: Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes [60.57770396565211]
  We show that strong reasoning abilities can emerge with far less data.<n>MobileLLM-R50M achieves an AIME score of 15.5, compared to just 0.6 for OLMo-2-1.48B and 0.3 for SmolLM-2-1.7B.
  arXiv  Detail & Related papers  (2025-09-29T15:43:59Z)
• XplaiNLP at CheckThat! 2025: Multilingual Subjectivity Detection with Finetuned Transformers and Prompt-Based Inference with Large Language Models [2.749729059235755]
  This notebook reports the Xplai submission to the CheckThat! 2025 shared task on multilingual subjectivity detection.<n>We evaluate two approaches: supervised fine-tuning of transformer encoders, EuroBERT, XLM-RoBERTa, and German-BERT, on monolingual and machine-translated training data.<n>For German, a German-BERT model fine-tuned on translated training data from typologically related languages yields competitive performance over the baseline.
  arXiv  Detail & Related papers  (2025-09-15T16:53:41Z)
• LLM-Based Detection of Tangled Code Changes for Higher-Quality Method-Level Bug Datasets [5.191767648600372]
  We investigate the utility of Large Language Models for detecting tangled code changes by leveraging both commit messages and method-level code diffs.<n>Our results demonstrate that combining commit messages with code diffs significantly enhances model performance.<n>Applying our approach to 49 open-source projects improves the distributional separability of code metrics between buggy and non-buggy methods.
  arXiv  Detail & Related papers  (2025-05-13T06:26:13Z)
• Parameter-Efficient Checkpoint Merging via Metrics-Weighted Averaging [2.9761595094633435]
  Checkpoint merging is a technique for combining multiple model snapshots into a single superior model.<n>This paper explores checkpoint merging in the context of parameter-efficient fine-tuning.<n>We propose Metrics-Weighted Averaging (MWA) to merge model checkpoints by weighting their parameters according to performance metrics.
  arXiv  Detail & Related papers  (2025-04-23T05:11:21Z)
• Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection [49.15148871877941]
  Next-token distribution outputs offer a theoretically appealing approach for detection of large language models (LLMs)<n>We propose the Perplexity Attention Weighted Network (PAWN), which uses the last hidden states of the LLM and positions to weight the sum of a series of features based on metrics from the next-token distribution across the sequence length.<n>PAWN shows competitive and even better performance in-distribution than the strongest baselines with a fraction of their trainable parameters.
  arXiv  Detail & Related papers  (2025-01-07T17:00:49Z)
• Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles [23.134664392314264]
  Tokenization is associated with many poorly understood shortcomings in language models (LMs)<n>This work studies how tokenization impacts model performance by analyzing and comparing models with their byte-level counterparts.<n>We introduce the Byte-Token Representation Lemma, a framework that establishes a mapping between the learned token distribution and its equivalent byte-level distribution.
  arXiv  Detail & Related papers  (2024-10-11T23:30:42Z)
• DeMuX: Data-efficient Multilingual Learning [57.37123046817781]
  DEMUX is a framework that prescribes exact data-points to label from vast amounts of unlabelled multilingual data. Our end-to-end framework is language-agnostic, accounts for model representations, and supports multilingual target configurations.
  arXiv  Detail & Related papers  (2023-11-10T20:09:08Z)
• Entity Matching using Large Language Models [3.7277730514654555]
  This paper investigates using generative large language models (LLMs) as a less task-specific training data-dependent alternative to PLM-based matchers. We show that GPT4 can generate structured explanations for matching decisions and can automatically identify potential causes of matching errors.
  arXiv  Detail & Related papers  (2023-10-17T13:12:32Z)
• The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute [66.84421705029624]
  We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours. We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length. This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
  arXiv  Detail & Related papers  (2023-09-20T10:31:17Z)
• Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels [53.68653940062605]
  We introduce a novel task, Partial labeling and Long-Tailed Multi-Label Classification (PLT-MLC) We find that most LT-MLC and PL-MLC approaches fail to solve the degradation-MLC. We propose an end-to-end learning framework: textbfCOrrection $rightarrow$ textbfModificattextbfIon $rightarrow$ balantextbfCe.
  arXiv  Detail & Related papers  (2023-04-20T20:05:08Z)
• Ensemble Transfer Learning for Multilingual Coreference Resolution [60.409789753164944]
  A problem that frequently occurs when working with a non-English language is the scarcity of annotated training data. We design a simple but effective ensemble-based framework that combines various transfer learning techniques. We also propose a low-cost TL method that bootstraps coreference resolution models by utilizing Wikipedia anchor texts.
  arXiv  Detail & Related papers  (2023-01-22T18:22:55Z)
• Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis [84.12658971655253]
  We propose Adapted Multimodal BERT, a BERT-based architecture for multimodal tasks. adapter adjusts the pretrained language model for the task at hand, while the fusion layers perform task-specific, layer-wise fusion of audio-visual information with textual BERT representations. In our ablations we see that this approach leads to efficient models, that can outperform their fine-tuned counterparts and are robust to input noise.
  arXiv  Detail & Related papers  (2022-12-01T17:31:42Z)

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.