Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples

• URL: http://arxiv.org/abs/2506.16502v1
• Date: Thu, 19 Jun 2025 17:56:16 GMT
• Title: Relic: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examples
• Authors: Soumya Suvra Ghosal, Vaibhav Singh, Akash Ghosh, Soumyabrata Pal, Subhadip Baidya, Sriparna Saha, Dinesh Manocha,
• Abstract summary: Most open-source multilingual reward models are primarily trained on preference datasets in high-resource languages.<n>We propose RELIC, a novel in-context learning framework for reward modeling in low-resource Indic languages.
• Score: 58.55904048776596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reward models are essential for aligning large language models (LLMs) with human preferences. However, most open-source multilingual reward models are primarily trained on preference datasets in high-resource languages, resulting in unreliable reward signals for low-resource Indic languages. Collecting large-scale, high-quality preference data for these languages is prohibitively expensive, making preference-based training approaches impractical. To address this challenge, we propose RELIC, a novel in-context learning framework for reward modeling in low-resource Indic languages. RELIC trains a retriever with a pairwise ranking objective to select in-context examples from auxiliary high-resource languages that most effectively highlight the distinction between preferred and less-preferred responses. Extensive experiments on three preference datasets- PKU-SafeRLHF, WebGPT, and HH-RLHF-using state-of-the-art open-source reward models demonstrate that RELIC significantly improves reward model accuracy for low-resource Indic languages, consistently outperforming existing example selection methods. For example, on Bodo-a low-resource Indic language-using a LLaMA-3.2-3B reward model, RELIC achieves a 12.81% and 10.13% improvement in accuracy over zero-shot prompting and state-of-the-art example selection method, respectively.

Related papers

• Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages [0.43498389175652036]
  This study integrates traditional and novel language models with fine-tuned Whisper models to raise their performance in less commonly studied languages.<n>We demonstrate substantial improvements in word error rate, particularly in low-resource scenarios.<n>While the integration reliably benefits all model sizes, the extent of improvement varies, highlighting the importance of optimized language model parameters.
  arXiv  Detail & Related papers  (2025-03-30T18:03:52Z)
• Challenges in Adapting Multilingual LLMs to Low-Resource Languages using LoRA PEFT Tuning [0.4194295877935868]
  This study investigates the effects of Low-Rank Adaptation (LoRA) -Efficient Fine-Tuning (PEFT) on multilingual Gemma models for Marathi.<n>Using a translated dataset with 52,000 instruction-response pairs, our findings reveal that while evaluation performance decline post-fine-tuning, manual assessments frequently suggest that the fine-tuned models outperform their original counterparts.
  arXiv  Detail & Related papers  (2024-11-27T18:14:38Z)
• Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition [2.7247388777405597]
  We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets. We fine-tune the Whisper multilingual ASR model on five high-resource languages and one low-resource language.
  arXiv  Detail & Related papers  (2024-09-25T14:09:09Z)
• SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition [55.2480439325792]
  Speech Meta In-Context LEarning (SMILE) is an innovative framework that combines meta-learning with speech in-context learning (SICL)<n>We show that SMILE consistently outperforms baseline methods in training-free few-shot multilingual ASR tasks.
  arXiv  Detail & Related papers  (2024-09-16T16:04:16Z)
• Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment [39.94156255629528]
  We evaluate a simple approach for zero-shot cross-lingual alignment. Cross-lingually aligned models are preferred by humans over unaligned models. A different-language reward model sometimes yields better aligned models than a same-language reward model.
  arXiv  Detail & Related papers  (2024-04-18T16:52:36Z)
• MaxMin-RLHF: Alignment with Diverse Human Preferences [101.57443597426374]
  Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data.<n>We learn a mixture of preference distributions via an expectation-maximization algorithm to better represent diverse human preferences.<n>Our algorithm achieves an average improvement of more than 16% in win-rates over conventional RLHF algorithms.
  arXiv  Detail & Related papers  (2024-02-14T03:56:27Z)
• Sample Efficient Preference Alignment in LLMs via Active Exploration [63.84454768573154]
  We take advantage of the fact that one can often choose contexts at which to obtain human feedback to most efficiently identify a good policy.<n>We propose an active exploration algorithm to efficiently select the data and provide theoretical proof that it has a worst-case regret bound.<n>Our method outperforms the baselines with limited samples of human preferences on several language models and four real-world datasets.
  arXiv  Detail & Related papers  (2023-12-01T00:54:02Z)
• Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation [21.057178077747754]
  In this work, we propose OPTICAL: Optimal Transport distillation for low-resource Cross-lingual information retrieval. By separating the cross-lingual knowledge from knowledge of query document matching, OPTICAL only needs bitext data for distillation training. Experimental results show that, with minimal training data, OPTICAL significantly outperforms strong baselines on low-resource languages.
  arXiv  Detail & Related papers  (2023-01-29T22:30:36Z)
• Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model [58.27176041092891]
  Recent research indicates that pretraining cross-lingual language models on large-scale unlabeled texts yields significant performance improvements. We propose a novel unsupervised feature decomposition method that can automatically extract domain-specific features from the entangled pretrained cross-lingual representations. Our proposed model leverages mutual information estimation to decompose the representations computed by a cross-lingual model into domain-invariant and domain-specific parts.
  arXiv  Detail & Related papers  (2020-11-23T16:00:42Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)
• Improving Candidate Generation for Low-resource Cross-lingual Entity Linking [81.41804263432684]
  Cross-lingual entity linking (XEL) is the task of finding referents in a target-language knowledge base (KB) for mentions extracted from source-language texts. In this paper, we propose three improvements that (1) reduce the disconnect between entity mentions and KB entries, and (2) improve the robustness of the model to low-resource scenarios.
  arXiv  Detail & Related papers  (2020-03-03T05:32:09Z)

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.