LOW-RESOURCE SCENARIOS

AdapterHub: A Framework for Adapting Transformers (2020.emnlp-demos)

Challenge:	Existing approaches to pre-training language models rely on verbalizers to translate the predicted vocabulary to task-specific labels.
Approach:	They propose a framework that incorporates conceptual knowledge for text classification in the extreme zero-shot setting.
Outcome:	The proposed framework outperforms prompt-based approaches on four widely-used datasets for sentiment analysis and topic detection on the same experimental settings.

Copied to clipboard

Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, Iryna Gurevych

PIEKM: ML-based Procedural Information Extraction and Knowledge Management System for Materials Science Literature (2022.aacl-demo)

Challenge:	AdapterHub framework enables dynamic “stiching-in” of pre-trained adapters for different tasks and languages.
Approach:	They propose a framework that allows dynamic "stiching-in" of pre-trained adapters for different tasks and languages.
Outcome:	The proposed framework allows dynamic “stiching-in” of pre-trained adapters for different tasks and languages.

Copied to clipboard

Huichen Yang, Carlos Aguirre, William Hsu

Better Quality Pre-training Data and T5 Models for African Languages (2023.emnlp-main)

Challenge:	Existing literature search engines cannot deliver recipe steps of the literature . manual processing and assimilating useful information is expensive and time-consuming for researchers.
Approach:	They propose a machine learning-based procedural information extraction and knowledge management system that extracts procedural recipe steps, figures, and tables from materials science articles.
Outcome:	The proposed system extracts procedural information recipe steps, figures, and tables from materials science articles and provides information retrieval capability and statistics visualization functionality.

Copied to clipboard

Akintunde Oladipo, Mofetoluwa Adeyemi, Orevaoghene Ahia, Abraham Owodunni, Odunayo Ogundepo, David Adelani, Jimmy Lin

Parsing linearizations appreciate PoS tags - but some are fussy about errors (2022.aacl-short)

Challenge:	Existing web crawls have demonstrated quality issues for low-resource languages . Existing pretraining corpora have numerous quality issues .
Approach:	They propose to audit existing pretraining corpora to understand and rectify quality issues . they pretrain a new T5-based model and evaluate its performance on multiple tasks .
Outcome:	The proposed model outperforms existing pretrained models on four NLP tasks.

Copied to clipboard

Alberto Muñoz-Ortiz, Mark Anderson, David Vilares, Carlos Gómez-Rodríguez

Syntactic Text Processing

Challenge:	Recent work on the impact of PoS tags on graph- and transition-based parsers suggests that they are only useful when tagging accuracy is prohibitively high or in low-resource scenarios.
Approach:	They examine the impact of PoS tags on graph- and transition-based parsers and propose to use them in a new paradigm for sequence labeling.
Outcome:	The proposed model is best when tagging accuracy and resource availability are high.

Cross-lingual Parsing with Polyglot Training and Multi-treebank Learning: A Faroese Case Study (D19-61)

Copied to clipboard

James Barry, Joachim Wagner, Jennifer Foster

Syntactic Text Processing

Challenge:	Cross-lingual dependency parsing involves transferring syntactic knowledge from one language to another.
Approach:	They compare two approaches to cross-lingual dependency parsing using monolingual source models and a polyglot model which is trained on the combination of all source languages.
Outcome:	The proposed methods improve low-resource dependency parsers by transferring syntactic knowledge from one language to another.

Adaptively Scheduled Multitask Learning: The Case of Low-Resource Neural Machine Translation (D19-56)

Copied to clipboard

Poorya Zaremoodi, Gholamreza Haffari

How DDAIR you? Disambiguated Data Augmentation for Intent Recognition (2026.eacl-short)

Challenge:	Neural Machine Translation suffers from the lack of bilingual data in low-resource scenarios.
Approach:	They propose to inject inductive biases into Neural Machine Translation (NMT) using auxiliary syntactic and semantic tasks.
Outcome:	The proposed approach improves translation quality by reweighing training data of main and auxiliary tasks based on their contributions to generalisability of main task.

Copied to clipboard

Galo Castillo-López, Alexis Lombard, Nasredine Semmar, Gaël de Chalendar

CoRAG: Collaborative Retrieval-Augmented Generation (2025.naacl-short)

Challenge:	Large Language Models (LLMs) produce ambiguous examples with regard to untargeted classes.
Approach:	They propose to use a sentence transformer to detect ambiguous augmented examples generated by Large Language Models for intent recognition.
Outcome:	The proposed method improves the quality of augmented data generated by large language models in low-resource scenarios.

Copied to clipboard

Aashiq Muhamed, Mona T. Diab, Virginia Smith

Data-driven Model Generalizability in Crosslinguistic Low-resource Morphological Segmentation (2022.tacl-1)

Challenge:	Existing research on Retrieval-Augmented Generation models has focused on centralized settings where a single entity controls both the model and the datastore.
Approach:	They propose a framework for RAG where clients jointly train a shared model using a collaborative passage store.
Outcome:	The proposed framework outperforms parametric learning methods and locally trained models in low-resource scenarios.

Copied to clipboard

Zoey Liu, Emily Prud’hommeaux

Pretrained Image-Text Models are Secretly Video Captioners (2025.naacl-short)

Challenge:	morphological segmentation is a common method of evaluation for multilingual tasks . authors often examine models with one data set that is representative of all possible data .
Approach:	They compare three broad classes of models with different parameterizations using morphological segmentation as the test case.
Outcome:	The results show that the extent of model generalization depends on the characteristics of the data set, and does not necessarily rely heavily on the data sets size.

Copied to clipboard

Chunhui Zhang, Yiren Jian, Zhongyu Ouyang, Soroush Vosoughi

Multimodality

Challenge:	Current video captioning methods often incorporate intricate designs tailored to video inputs.
Approach:	They adapt an image-based captioning model to address dynamic video sequences without modifications.
Outcome:	The proposed model outperforms specialised captioning systems on major benchmarks.

Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection (2022.aacl-main)

Copied to clipboard

Tulika Bose, Irina Illina, Dominique Fohr

READ: Improving Relation Extraction from an ADversarial Perspective (2024.findings-naacl)

Challenge:	Existing approaches to detect hate speech are expensive and time-consuming . a new approach allows for flexible learning of neighborhood information .
Approach:	They propose a method that allows flexible modeling of neighbors retrieved from a resource-rich corpus to learn the amount of transfer.
Outcome:	The proposed training strategy improves on low-resource hate speech corpora over baselines.

Copied to clipboard

Dawei Li, William Hogan, Jingbo Shang

Robustness in NLP

Challenge:	Recent work in relation extraction (RE) has high generalization capability, but adversarial training methods rely on entities.
Approach:	They propose an adversarial training method specifically designed for relation extraction that introduces sequence- and token-level perturbations to the sample and uses a separate perturbation vocabulary to improve the search for entity and context perturbations.
Outcome:	The proposed method significantly improves accuracy and robustness in low-resource scenarios.

Pre-training via Leveraging Assisting Languages for Neural Machine Translation (2020.acl-srw)

Copied to clipboard

Haiyue Song, Raj Dabre, Zhuoyuan Mao, Fei Cheng, Sadao Kurohashi, Eiichiro Sumita

PromptDA: Label-guided Data Augmentation for Prompt-based Few Shot Learners (2023.eacl-main)

Challenge:	Sequence-to-sequence (S2S) pre-training with large monolingual data is not always available for the languages of interest (LOI).
Approach:	They propose to use monolingual corpora of other languages to complement the scarce monolingual LOI by script mapping (Chinese to Japanese) . Using only Chinese and French monolinguals, they improve Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios.
Outcome:	The proposed approach improves Japanese-English translation quality by up to 8.5 BLEU in low-resource scenarios.

Copied to clipboard

Canyu Chen, Kai Shu

Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai (2025.acl-industry)

Challenge:	Existing studies on prompt-based few-shot tuning focus on deriving proper label words with a verbalizer or generating prompt templates to elicit semantics from PLMs.
Approach:	They propose a framework that leverages label semantics for prompt-based tuning.
Outcome:	The proposed framework improves on few-shot text classification tasks by leveraging label semantics and data augmentation.

Copied to clipboard

Yizhong Geng, Jizhuo Xu, Zeyu Liang, Jinghan Yang, Xiaoyi Shi, Xiaoyu Shen

Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation (2022.acl-long)

Challenge:	Text-to-speech (TTS) systems are limited by limited data and linguistic complexities.
Approach:	They propose a data-optimized framework with an advanced acoustic model to build high-quality TTS systems for low-resource scenarios.
Outcome:	The proposed framework enables zero-shot voice cloning and improved performance across diverse client applications, including finance, healthcare, education, and law.

Copied to clipboard

Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian Sun, Nevin Zhang

Fixed Encoder Self-Attention Patterns in Transformer-Based Machine Translation (2020.findings-emnlp)

Challenge:	Building models of natural language processing (NLP) is challenging in low-resource scenarios where limited data are available.
Approach:	They propose a memory imitation meta-learning method that enhances the model’s reliance on support sets for task adaptation.
Outcome:	The proposed method outperforms baselines on both text classification and generation tasks.

Copied to clipboard

Alessandro Raganato, Yves Scherrer, Jörg Tiedemann

PLATO-Ad: A Unified Advertisement Text Generation Framework with Multi-Task Prompt Learning (2022.emnlp-industry)

Challenge:	Recent studies have shown that attention heads learn simple positional patterns .
Approach:	They propose to replace all but one attention head of each encoder layer with simple fixed – non-learnable – attentive patterns that are solely based on position and do not require external knowledge.
Outcome:	The proposed model improves translation quality and improves BLEU scores by up to 3 points in low-resource scenarios.

Copied to clipboard

Zeyang Lei, Chao Zhang, Xinchao Xu, Wenquan Wu, Zheng-yu Niu, Hua Wu, Haifeng Wang, Yi Yang, Shuanglong Li

S4-Tuning: A Simple Cross-lingual Sub-network Tuning Method (2022.acl-short)

Challenge:	Online advertisement text generation models have achieved remarkable success in generating high-quality text ads, but some challenges remain, such as low-resource scenarios and training efficiency for multiple ad tasks.
Approach:	They propose a unified text ad generation framework with multi-task prompt learning to tackle low-resource ade generation problem and a multi-step prompt learning mechanism to efficiently solve multiple aed generation tasks.
Outcome:	The proposed framework outperforms the state-of-the-art on offline and online metrics.

Copied to clipboard

Runxin Xu, Fuli Luo, Baobao Chang, Songfang Huang, Fei Huang

Cross-Lingual Transfer

Challenge:	Existing multilingual pre-trained language models allow to adapt to target languages with only few labeled examples.
Approach:	They propose a simple cross-lingual sub-network tuning method that detects the most essential sub-netzwork for each target language and updates it during fine-tuning.
Outcome:	The proposed method improves on three multi-lingual tasks involving 37 different languages.

Controlling Language Confusion in Multilingual LLMs (2025.acl-srw)

Copied to clipboard

Nahyun Lee, Yeongseo Woo, Hyunwoo Ko, Guijin Son

The Past, Present, and Future of Typological Databases in NLP (2023.findings-emnlp)

Challenge:	Large language models suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages.
Approach:	They propose a supervised fine-tuning methodology which optimizes the likelihood of correct tokens without explicitly penalizing undesired outputs such as cross-lingual mixing.
Outcome:	The proposed model suppresses language-confused generation while maintaining strong language consistency even under high decoding temperatures while preserving general QA performance.

Copied to clipboard

Emi Baylor, Esther Ploeger, Johannes Bjerva

When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (N18-2)

Challenge:	Typological information is inconsistent with each other and other sources of typological information, such as linguistic grammars.
Approach:	They propose to examine disagreements between typological databases and their uses in NLP by exploring disagreements across databases and resources.
Outcome:	The proposed view of typology has significant potential in the future, including in language modeling in low-resource scenarios.

Copied to clipboard

Ye Qi, Devendra Sachan, Matthieu Felix, Sarguna Padmanabhan, Graham Neubig

A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches (2025.findings-naacl)

Challenge:	Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks where large-scale parallel corpora cannot be obtained.
Approach:	They perform five sets of experiments to analyze when pre-trained word embeddings can be useful in NMT tasks.
Outcome:	The embeddings provide gains of up to 20 BLEU points in the most favorable setting.

Copied to clipboard

Gaurav Sahu, Olga Vechtomova, Issam H. Laradji

An LLM-Enhanced Adversarial Editing System for Lexical Simplification (2024.lrec-main)

Challenge:	Existing approaches for low-resource text summarization use large language models (LLMs) but such models suffer from inconsistent outputs and are difficult to adapt to domain-specific data.
Approach:	They propose two methods to effectively utilize large language models for low-resource text summarization.
Outcome:	The proposed methods synthesize high-quality documents using LLaMA-3-70b-Instruct model . they achieve competitive ROUGE scores as a fully supervised method with 5% of the labeled data.

Copied to clipboard

Keren Tan, Kangyang Luo, Yunshi Lan, Zheng Yuan, Jinlong Shu

An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification (2024.emnlp-main)

Challenge:	Existing methods to simplify text rely heavily on annotated data, making it challenging to apply in low-resource scenarios.
Approach:	They propose a Lexical Simplification method without parallel corpora that uses an Adversarial Editing System and an LLM-enhanced loss to distill knowledge into a small-size LS system.
Outcome:	The proposed method uses an LLM-enhanced loss to distill knowledge from Large Language Models (LLMs) into a small-size LS system.

Copied to clipboard

Zhuowei Chen, Lianxi Wang, Yuben Wu, Xinfeng Liao, Yujia Tian, Junyang Zhong

Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Tasks (D19-1)

Challenge:	Existing models for textual data augmentation (DA) are highly data-hungry and struggle to perform satisfactorily under noisy conditions.
Approach:	They propose to leverage a diffusion language model to capture in-domain knowledge and generate pseudo samples by reconstructing strong label-related tokens.
Outcome:	The proposed method captures in-domain knowledge and generates pseudo samples by reconstructing strong label-related tokens.

Copied to clipboard

Zi-Yi Dou, Keyi Yu, Antonios Anastasopoulos

Gold Doesn’t Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information (2023.eacl-main)

Challenge:	Existing methods to learn general representations of text can achieve sub-optimal performance in low-resource scenarios.
Approach:	They propose to use language model pre-training and multi-task learning to learn robust representations but these methods can achieve sub-optimal performance in low-resource scenarios.
Outcome:	The proposed model outperforms strong baselines on the GLUE benchmark and can be adapted to new tasks efficiently and effectively.

Copied to clipboard

Shun Shao, Yftah Ziser, Shay B. Cohen

Unsupervised Parallel Sentence Extraction with Parallel Segment Detection Helps Machine Translation (P19-1)

Challenge:	Spectral Attribute removaL is a method to remove private or guarded information from neural representations.
Approach:	They propose a method to remove guarded or private information from neural representations by matrix decomposition.
Outcome:	The proposed method retains better main task performance after removing guarded information compared to previous work.

Copied to clipboard

Viktor Hangya, Alexander Fraser

Style Transfer as Data Augmentation: A Case Study on Named Entity Recognition (2022.emnlp-main)

Challenge:	Recent advances in unsupervised bilingual word embeddings make it possible to mine parallel sentences from comparable corpora.
Approach:	They propose a strong unsupervised system for parallel sentence mining based on cosine similarities of source and target words . they show that parallel sentences mined from real-life sources improve unsupervised MT .
Outcome:	The proposed system improves unsupervised MT on three language pairs.

Copied to clipboard

Shuguang Chen, Leonardo Neves, Thamar Solorio

Named Entity Recognition

Challenge:	Existing methods to increase training data in low-resource domains may not be effective due to data scarcity.
Approach:	They propose a method to transform a high-resource domain into a low-resourced domain by changing its style-related attributes to generate synthetic data for training.
Outcome:	The proposed method can significantly improve results on five domain pairs under different data regimes.

DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction (2023.findings-emnlp)

Copied to clipboard

Gang Zhao, Xiaocheng Gong, Xinjie Yang, Guanting Dong, Shudong Lu, Si Li

Prompt Combines Paraphrase: Teaching Pre-trained Models to Understand Rare Biomedical Words (2022.coling-1)

Challenge:	Current Event Extraction methods focus on high-resource scenarios, which requires large amount of annotated data.
Approach:	They propose a demonstration-based learning paradigm for EE to fully use annotated data . they propose EE as a natural language generation task guided by schema-based prompts .
Outcome:	The proposed model outperforms current methods in low-resource scenarios.

Copied to clipboard

Haochun Wang, Chi Liu, Nuwa Xi, Sendong Zhao, Meizhi Ju, Shiwei Zhang, Ziheng Zhang, Yefeng Zheng, Bing Qin, Ting Liu

HCL-TAT: A Hybrid Contrastive Learning Method for Few-shot Event Detection with Task-Adaptive Threshold (2022.findings-emnlp)

Challenge:	Pre-trained models perform poorly with limited data and rare biomedical words.
Approach:	They propose to use prompt to fine-tune pre-trained models for biomedical domain tuning with a simple approach.
Outcome:	The proposed method achieves up to 6% improvement in biomedical natural language inference task without any extra parameters or training steps using few-shot vanilla prompt settings.

Copied to clipboard

Ruihan Zhang, Wei Wei, Xian-Ling Mao, Rui Fang, Dangyang Chen

Towards Low-Resource Harmful Meme Detection with LMM Agents (2024.emnlp-main)

Challenge:	Existing methods for event detection have failed to address the problem of constantly emerging event types with limited data.
Approach:	They propose a novel method for event detection with a task-adaptive threshold . they propose to learn discriminative representations with 'two-view contrastive loss'
Outcome:	The proposed method achieves better results than the state-of-the-art methods on a benchmark dataset.

Copied to clipboard

Jianzhao Huang, Hongzhan Lin, Liu Ziyan, Ziyang Luo, Guang Chen, Jing Ma

Reusing Transferable Weight Increments for Low-resource Style Generation (2024.emnlp-main)

Challenge:	Existing methods for harmful meme detection are limited due to the dynamic nature of memes . eliciting knowledge-revising behavior within the LMM agent is a key factor in achieving this goal .
Approach:	They propose an agency-driven framework for low-resource harmful meme detection . they use annotated memes to leverage label information as auxiliary signals for model .
Outcome:	The proposed framework achieves superior performance than state-of-the-art methods on the low-resource harmful meme detection task.

Copied to clipboard

Chunzhen Jin, Eliot Huang, Heng Chang, Yaqi Wang, Peng Cao, Osmar Zaiane

Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification (2026.findings-eacl)

Challenge:	Text style transfer (TST) is crucial in natural language processing, aiming to endow text with a new style without altering its meaning.
Approach:	They propose a framework to use style features in weight increments to transfer low-resource styles effectively.
Outcome:	The proposed framework achieves remarkable performance across different backbones, achieving particularly effective results in low-resource scenarios.

Copied to clipboard

Branislav Pecher, Jan Cegin, Robert Belanec, Ivan Srba, Jakub Simko, Maria Bielikova

Language-aware Interlingua for Multilingual Neural Machine Translation (2020.acl-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable multilingual capabilities, making them promising tools in both high- and low-resource languages.
Approach:	They use a multilingual LLM to generate synthetic datasets covering 11 languages and 4 classification tasks and use them to train smaller models.
Outcome:	The proposed model outperforms the large generator in low-resource languages and tasks.

Copied to clipboard

Changfeng Zhu, Heng Yu, Shanbo Cheng, Weihua Luo

ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual Summarization (2023.findings-acl)

Challenge:	Existing multilingual neural machine translation models fail to capture diversity and specificity of different languages, resulting in inferior performance against individual models that are sufficiently trained.
Approach:	They propose to integrate a language-aware interlingua into an Encoder-Decoder architecture to learn a semantic representation from the semantic spaces of different languages while allowing for language-specific specialization of a particular language pair.
Outcome:	The proposed model achieves remarkable improvements over state-of-the-art multilingual NMT models and produces comparable performance with strong individual models.

Copied to clipboard

Peiyao Li, Zhengkun Zhang, Jun Wang, Liang Li, Adam Jatowt, Zhenglu Yang

Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing (2023.eacl-main)

Challenge:	Existing studies ignore data imbalance in multilingual settings and do not utilize monolingual data.
Approach:	They propose a cross-lingual summarization model that aligns cross-linguistic data with high-resource monolingual data via contrastive and consistency loss.
Outcome:	The proposed model outperforms baseline models and consistently dominates on 45 language pairs.

Copied to clipboard

Jivnesh Sandhan, Laxmidhar Behera, Pawan Goyal

MELM: Data Augmentation with Masked Entity Language Modeling for Low-Resource NER (2022.acl-long)

Challenge:	Several strategies have been proposed to enhance performance in low-resource scenarios.
Approach:	They propose to use 5 low-resource strategies for dependency parsing for multiple languages . they use ensembled approach on 7 UD low-rsource languages based on their results .
Outcome:	The proposed approach improves on a low-resource language Sanskrit.

Copied to clipboard

Ran Zhou, Xin Li, Ruidan He, Lidong Bing, Erik Cambria, Luo Si, Chunyan Miao

BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog (2022.findings-naacl)

Challenge:	Named entity recognition (NER) tasks have limited amount of labeled data . data augmentation methods suffer from token-label misalignment, which leads to unsatsifactory performance.
Approach:	They propose a data augmentation framework that explicitly injects NER labels into sentence context and generates high-quality augmented data with novel entities.
Outcome:	The proposed framework outperforms baseline methods on low-resource tasks.

Copied to clipboard

Haipeng Sun, Junwei Bao, Youzheng Wu, Xiaodong He

Dialogue Systems & Conversational Agents

Challenge:	Existing task-oriented dialog systems suffer from error propagation from inaccurate dialog states and responses.
Approach:	They propose a back reconstruction approach for end-to-end task-oriented dialog system . they use back reconstruction to reconstruct the original input context from the generated dialog states .
Outcome:	Extensive experiments on MultiWOZ 2.0 and CamRest676 show the effectiveness of the proposed model.

Dynamic Prefix as Instructor for Incremental Named Entity Recognition: A Unified Seq2Seq Generation Framework (2025.findings-acl)

Copied to clipboard

Zihao Wu, YongXiang Hua, Yongxin Zhu, Fang Zhang, Linli Xu

GRAMMAR-LLM: Grammar-Constrained Natural Language Generation (2025.findings-acl)

Challenge:	Named Entity Recognition (NER) is a fundamental problem in information extraction.
Approach:	They propose a parameter-efficient method for Incremental Named Entity Recognition (INER) task aimed at updating a model to extract entities from an expanding set of entity type candidates by employing a dynamic prefix as a task instructor to guide the generative model.
Outcome:	Empirical results show that the proposed method preserves task-invariant knowledge while adapting to new entities with minimal parameter updates.

Copied to clipboard

Gabriele Tuccio, Luana Bulla, Maria Madonia, Aldo Gangemi, Misael Mongiovì

From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding (2021.naacl-main)

Challenge:	Existing approaches to fine-tuning and prompting are insufficient to ensure compliance with predefined taxonomies, syntactic structures, or domain-specific rules.
Approach:	They propose a framework that integrates formal grammatical constraints into the decoding process to enforce syntactic correctness in linear time while maintaining expressiveness in grammar rule definition.
Outcome:	The proposed framework enforces syntactic correctness in linear time while maintaining expressiveness in grammar rule definition.

Copied to clipboard

Rob van der Goot, Ibrahim Sharaf, Aizhan Imankulova, Ahmet Üstün, Marija Stepanović, Alan Ramponi, Siti Oryza Khairunnisa, Mamoru Komachi, Barbara Plank

LightNER: A Lightweight Tuning Paradigm for Low-resource NER via Pluggable Prompting (2022.coling-1)

Challenge:	Lack of publicly available evaluation data for low-resource languages limits progress in SLU . despite advances in neural modeling for slot and intent detection, datasets for SLU remain limited.
Approach:	They propose a joint learning approach with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer.
Outcome:	The proposed model can learn English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer.

Copied to clipboard

Xiang Chen, Lei Li, Shumin Deng, Chuanqi Tan, Changliang Xu, Fei Huang, Luo Si, Huajun Chen, Ningyu Zhang

ImaRA: An Imaginative Frame Augmented Method for Low-Resource Multimodal Metaphor Detection and Explanation (2025.findings-naacl)

Challenge:	Existing approaches for Named Entity Recognition (NER) use extensive labeled data for model training, which struggles in low-resource scenarios.
Approach:	They propose a lightweight tuning paradigm for low-resource NER via pluggable prompting . they construct a learnable verbalizer of entity categories without any label-specific classifiers .
Outcome:	The proposed model outperforms baselines and class transfer models in low-resource scenarios.

Copied to clipboard

Yuan Tian, Minzheng Wang, Nan Xu, Wenji Mao

LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphs (2024.findings-acl)

Challenge:	Existing methods for multimodal metaphor detection neglect cross-domain and attribute similarity characteristics underlying multimodal understanding.
Approach:	They propose an Imaginative FRame Augmented method for multimodal metaphor detection and explanation . they use a cross-modal imagination dataset rich in multimodal multimodal expressions .
Outcome:	The proposed method outperforms existing methods with training data on two datasets.

Copied to clipboard

Kai Wang, Yuwei Xu, Zhiyong Wu, Siqiang Luo

Prompting Few-shot Multi-hop Question Generation via Comprehending Type-aware Semantics (2024.findings-naacl)

Challenge:	Knowledge Graph (KG) inductive reasoning is widely adopted in various applications.
Approach:	They propose a framework for low-resource inductive reasoning using Large Language Models to generate a graph-structural prompt for pre-trained KGs.
Outcome:	The proposed framework outperforms previous methods in three-shot, one-shot and zero-shot reasoning tasks.

Copied to clipboard

Zefeng Lin, Weidong Chen, Yan Song, Yongdong Zhang

Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation (2021.findings-acl)

Challenge:	Existing approaches for multi-hop question generation rely on large annotated data . supervised approaches rely only on large labeled data, making it hard to perform tasks.
Approach:	They propose a type-aware semantics extraction-based chain-of-thought method for multi-hop question generation for documents . they first extract question types and essential semantic phrases from the given documents and the answer .
Outcome:	The proposed approach extracts question types and essential semantic phrases from documents and the answer.

Copied to clipboard

Meng Zhang, Liangyou Li, Qun Liu

Back Translation for Speech-to-text Translation Without Transcripts (2023.acl-long)

Challenge:	Neural machine translation suffers when parallel data is scarce for training . a new framework to transfer multiple sources of auxiliary data is proposed .
Approach:	They propose a framework to transfer multiple sources of auxiliary data from high-resource parallel data to low-resourced translation models using pretrained language models.
Outcome:	The proposed approach yields consistent improvements over strong competitors for multiple translation directions.

Copied to clipboard

Qingkai Fang, Yang Feng

Glyph2Vec: Learning Chinese Out-of-Vocabulary Word Embedding from Glyphs (2020.acl-main)

Challenge:	End-to-end speech-totext translation (ST) is often achieved by utilizing source transcripts, but transcripts are only sometimes available since numerous unwritten languages exist worldwide.
Approach:	They propose an algorithm to synthesize pseudo ST data from monolingual target data to enhance ST without generating source transcripts.
Outcome:	The proposed method achieves an average boost of 2.3 BLEU on MuST-C En-De, En-Fr, and En-Es datasets.

Copied to clipboard

Hong-You Chen, Sz-Han Yu, Shou-de Lin

Representation Learning

Challenge:	Chinese NLP applications that rely on large text often contain huge amounts of vocabulary which are sparse in corpus.
Approach:	They propose a multi-modal model that extracts visual features from Chinese word glyphs to expand current word embedding space without accessing any corpus.
Outcome:	The proposed model can embed words in Chinese without accessing corpus without a corpus.

Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios (2022.emnlp-main)

Copied to clipboard

Ngoc Dang Nguyen, Lan Du, Wray Buntine, Changyou Chen, Richard Beare

Generation-Augmented and Embedding Fusion in Document-Level Event Argument Extraction (2025.coling-main)

Challenge:	Named Entity Recognition (NER) tasks require a large amount of training data and domains are often scarcely labeled.
Approach:	They propose a hardness-guided domain adaptation framework for bioNER tasks that leverages domain hardness information to improve the adaptability of the learnt model in low-resource scenarios.
Outcome:	The proposed model outperforms the state-of-the-art MetaNER model on biomedical datasets.

Copied to clipboard

Xingjian Lin, Shengfei Lyu, Xin Wang, Qiuju Chen, Huanhuan Chen

X-METRA-ADA: Cross-lingual Meta-Transfer learning Adaptation to Natural Language Understanding and Question Answering (2021.naacl-main)

Challenge:	Document-level event argument extraction is a crucial task that aims to extract arguments from the entire document, beyond sentence-level analysis.
Approach:	They propose a novel approach to document-level event argument extraction that integrates predefined templates and generative language models into a foundational embedding derived from a classification model.
Outcome:	The proposed approach is more effective than baseline models and data-efficient in low-resource scenarios.

Copied to clipboard

Meryem M’hamdi, Doo Soon Kim, Franck Dernoncourt, Trung Bui, Xiang Ren, Jonathan May

Robust Self-Augmentation for Named Entity Recognition with Meta Reweighting (2022.naacl-main)

Challenge:	Multilingual models have gained popularity for their zero-shot cross-lingual transfer learning capabilities, but their generalization ability is inconsistent for typologically diverse languages.
Approach:	They propose a meta-learning approach that adapts MAML to learn to adapt to new languages . they extensively evaluate two cross-lingual NLU tasks using English as source and spanish as target .
Outcome:	The proposed approach outperforms naive fine-tuning on cross-lingual tasks for most languages.

Copied to clipboard

Linzhi Wu, Pengjun Xie, Jie Zhou, Meishan Zhang, Ma Chunping, Guangwei Xu, Min Zhang

Robustness in NLP

Challenge:	Prior research has focused on reducing noise for specific methods to achieve an effective integration.
Approach:	They propose to use token substitution and mixup to improve named entity recognition (NER) using a meta-reweighting strategy, which is extensible and requires little effort.
Outcome:	The proposed method is extensible, imposing little effort on a specific self-augmentation method.

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks (2020.coling-main)

Copied to clipboard

Lichao Sun, Congying Xia, Wenpeng Yin, Tingting Liang, Philip Yu, Lifang He

Benchmarking Neural and Statistical Machine Translation on Low-Resource African Languages (2020.lrec-1)

Challenge:	Recent work on data augmentation techniques that interpolate inputs and labels shows strong effectiveness in image classification.
Approach:	They propose to integrate mixup to transformer-based pre-trained architecture for NLP tasks while keeping the whole end-to-end training system.
Outcome:	The proposed framework improves on GLUEbenchmark and transformer-based learning models while keeping the whole end-to-end training system.

Copied to clipboard

Kevin Duh, Paul McNamee, Matt Post, Brian Thompson

Imagination-Augmented Natural Language Understanding (2022.naacl-main)

Challenge:	a recent study has focused on languages where large amounts of resources are available.
Approach:	They benchmark state of the art statistical and neural machine translation systems on Somali and Swahili languages . they find that statistical machine translation and neural translation can perform similarly in low-resource scenarios .
Outcome:	The results show that statistical machine translation and neural machine translation perform similarly in low-resource scenarios.

Copied to clipboard

Yujie Lu, Wanrong Zhu, Xin Wang, Miguel Eckstein, William Yang Wang

Multimodality

Challenge:	Existing methods for Natural Language Understanding focus on textual signals, which hinders models from learning efficiently from limited data samples.
Approach:	They propose an Imagination-Augmented Cross-modal Encoder to solve natural language understanding tasks from a novel learning perspective.
Outcome:	The proposed learning paradigm bridges the gap between human and agent language understanding in both linguistic and perceptual procedures.

DSP: Discriminative Soft Prompts for Zero-Shot Entity and Relation Extraction (2023.findings-acl)

Copied to clipboard

Bo Lv, Xin Liu, Shaojie Dai, Nayu Liu, Fan Yang, Ping Luo, Yue Yu

Continued Pre-training on Sentence Analogies for Translation with Small Data (2024.lrec-main)

Challenge:	Prompt-based methods have shown their efficacy in transferring general knowledge within pre-trained language models (PLMs) however, when applied to zero-shot entity and relation extraction, they struggle with the limited coverage of verbalizers to labels and the slow inference speed.
Approach:	They propose a method which reformulates zero-shot tasks into token discrimination tasks without having to construct verbalizers.
Outcome:	The proposed method outperforms baselines on two zero-shot entity recognition datasets with higher inference speed and achieves 7.5% improvement over previous state-of-the-art models on Wiki-ZSL and FewRel.

Copied to clipboard

Liyan Wang, Haotong Wang, Yves Lepage

SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics (2024.emnlp-main)

Challenge:	Using 10 times fewer instances, CPoA can achieve gains of +1.4 and +1.3 BLEU points over the original model.
Approach:	They propose to train models with analogical abilities on sentence analogies retrieved from corpus . they use a weighting scalar to adjust the influence of closer analogies while diminishing impact of far ones .
Outcome:	The proposed approach improves translation performance on a low-resource translation task in german-upper sorbian . it uses 10 times fewer instances to achieve gains of +1.4 and +1.3 BLEU points over the original model .

Copied to clipboard

Zhiwen You, Kanyao Han, Haotian Zhu, Bertram Ludaescher, Jana Diesner

Toeing the Party Line: Election Manifestos as a Key to Understand Political Discourse on Twitter (2024.findings-emnlp)

Challenge:	Recent studies have used prompt-based fine-tuning methods for text classification tasks . however, the difficulty and costs of manually selecting domain label terms for the verbalizer remain unexplored .
Approach:	They propose a framework to automatically retrieve scientific topic-related terms for low-resource text classification tasks.
Outcome:	The proposed method outperforms state-of-the-art methods on scientific text classification tasks under few and zero-shot settings.

Copied to clipboard

Maximilian Maurer, Tanise Ceron, Sebastian Padó, Gabriella Lapesa

Challenge:	Recent work on political positioning on Twitter has tended to focus on manifestos rather than social media since it is ambiguous and dependent on social context.
Approach:	They propose to use hashtags as a signal to fine-tune text representations for politicians' tweets using a hashtag-based method to predict pairwise positional similarities between parties from the manifesto case to the Twitter case.
Outcome:	The proposed method matches politicians' statements to official lines of the parties' tweets, even when only small subsets from shorter time periods are available.

Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health (2021.findings-emnlp)

Copied to clipboard

Andrew Lee, Jonathan K. Kummerfeld, Larry An, Rada Mihalcea

Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning (2025.coling-main)

Challenge:	Existing statistical models are not explainable, struggle in low-resource scenarios and cannot be reused for multiple tasks.
Approach:	They propose a micromodel architecture that embeds domain knowledge and provides explanations throughout the model’s decision process.
Outcome:	The proposed model is validated on depression classification, PTSD classification, and suicidal risk assessment tasks.

Copied to clipboard

Aditya Narayan Sankaran, Reza Farahbakhsh, Noel Crespi

NAT: Enhancing Agent Tuning with Negative Samples (2025.naacl-long)

Challenge:	Online abusive content detection, particularly in low-resource settings, remains underexplored.
Approach:	They propose to use pre-trained audio representations to detect abusive language in Indian languages using Few Shot Learning (FSL) .
Outcome:	The proposed model can be used to classify abusive language in 10 languages using the ADIMA dataset with FSL.

Copied to clipboard

Renxi Wang, Xudong Han, Yixuan Zhang, Timothy Baldwin, Haonan Li

Challenge:	Existing methods for fine-tuning and reinforcement learning use only positive examples, limiting their efficiency in low-resource scenarios.
Approach:	They propose a method that leverages both successful and failed trajectories for fine-tuning, maximizing the utility of limited resources.
Outcome:	The proposed method surpasses existing methods, including SFT, DPO, and PPO, across various tasks.

A Rigorous Evaluation of LLM Data Generation Strategies for Low-Resource Languages (2025.emnlp-main)

Copied to clipboard

Tatiana Anikina, Jan Cegin, Jakub Simko, Simon Ostermann

Tackling the Low-resource Challenge for Canonical Segmentation (2020.emnlp-main)

Challenge:	Large Language Models (LLMs) are increasingly used to generate synthetic textual data for training smaller specialized models.
Approach:	They evaluate the performance of large language models and their generation strategies in 11 different languages using 3 NLP tasks and 4 open-source LLMs.
Outcome:	The proposed generation strategies and their combinations yield strong results across 11 languages, including several extremely low-resource ones.

Copied to clipboard

Manuel Mager, Özlem Çetinoğlu, Katharina Kann

A Multi-Task Approach for Improving Biomedical Named Entity Recognition by Incorporating Multi-Granularity information (2021.findings-acl)

Challenge:	morphological segmentation is a task of dividing words into their constituting morphemes . we compare two new approaches for the task when training data is limited .
Approach:	They propose to use an LSTM pointer-generator and a sequence-to-sequence model to perform canonical segmentation when training data is limited.
Outcome:	The proposed models outperform existing models on German, English, and Indonesian in low-resource scenarios by 11.4% accuracy.

Copied to clipboard

Yiqi Tong, Yidong Chen, Xiaodong Shi

Data Augmentation for Cross-Domain Named Entity Recognition (2021.emnlp-main)

Challenge:	Neural named entity recognition (BioNER) methods require large amount of annotated data, while the annotating BioNER datasets are often difficult to obtain and small in scale due to the limitations of privacy, ethics and high degree of specialization.
Approach:	They propose a method that utilizes latent multi-granularity information in annotated bioNER datasets to alleviate the lack of training samples.
Outcome:	The proposed model improves over the BioBERT baseline and can get more than 3% improvement of F1score in low-resource scenarios.

Copied to clipboard

Shuguang Chen, Gustavo Aguilar, Leonardo Neves, Thamar Solorio

Automatic Interlinear Glossing for Under-Resourced Languages Leveraging Translations (2020.coling-main)

Challenge:	Existing methods for named entity recognition focus on augmenting in-domain data in low-resource scenarios where annotated data is limited.
Approach:	They propose a neural architecture to transform data from high-resource to low-resourced domains by learning the patterns in the text that differentiate them.
Outcome:	The proposed approach improves on high-resource domain representations over high- and low-resourced domains.

Copied to clipboard

Xingyuan Zhao, Satoru Ozaki, Antonios Anastasopoulos, Graham Neubig, Lori Levin

TCProF:Time-Complexity Prediction SSL Framework (2025.naacl-long)

Challenge:	Documentation is not a cure-all for language loss, but it is an important part of language preservation.
Approach:	They propose to use multi-source neural models to create automatic glossing models . they also explore cross-lingual transfer and a simple output length control mechanism .
Outcome:	The proposed model outperforms state-of-the-art models on low-resource scenarios.

Copied to clipboard

Joonghyuk Hahn, Hyeseon Ahn, Jungin Kim, Soohan Lim, Yo-Sub Han

Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignment (2023.findings-emnlp)

Challenge:	determining the precise time complexity of a code is theoretically undecidable . determining time complexity is a challenging task in programming efficiency analysis .
Approach:	They propose a time-complexity prediction SSL framework that uses code snippets labeled with their time complexity classes to predict code time.
Outcome:	The proposed approach improves performance by 60% over self-training methods.

Copied to clipboard

Zhen Zhang, Jialu Wang, Xin Wang

Good Meta-tasks Make A Better Cross-lingual Meta-transfer Learning for Low-resource Languages (2023.findings-emnlp)

Challenge:	Existing cross-lingual transfer methods that use labeled data and linguistic resources would consume excessive resources for a large number of languages.
Approach:	They propose a parameter-efficient cross-lingual transfer learning framework that utilizes a translation-based alignment method to mitigate multilingual disparities.
Outcome:	The proposed framework reduces disparities among languages and improves cross-lingual transfer results in low-resource scenarios while keeping and fine-tuning only a small number of parameters.

Copied to clipboard

Linjuan Wu, Zongyi Guo, Baoliang Cui, Haihong Tang, Weiming Lu

Cross-Lingual Transfer

Challenge:	Model-agnostic meta-learning has garnered attention as a promising technique for enhancing few-shot cross-lingual transfer learning in low-resource scenarios.
Approach:	They propose a Meta-Task Collector-based Cross-lingual Meta-Transfer framework to adapt data selection strategies to construct cross-lingual meta-tasks to reduce language gaps.
Outcome:	The proposed framework significantly improves model performance in the target language with minimal annotation costs.

On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role Labeling (2021.emnlp-main)

Copied to clipboard

Zhisong Zhang, Emma Strubell, Eduard Hovy

Coordination Generation via Synchronized Text-Infilling (2022.coling-1)

Challenge:	Recent advances in neural architectures and pre-trained representations have greatly improved the performance of fully-supervised semantic role labeling (SRL) but there are limitations in the availability of supervised training data.
Approach:	They propose to leverage syntactic dependencies to facilitate cross-lingual transfer by annotating predicate-argument structures in text.
Outcome:	The proposed model can be extended to other languages with limited training data.

Copied to clipboard

Hiroki Teranishi, Yuji Matsumoto

MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translation (2023.findings-acl)

Challenge:	Generating synthetic data from pre-trained language models has enhanced performance across several NLP tasks.
Approach:	They propose a method for generating sentences with a coordinate structure in which the boundaries of its conjuncts are explicitly specified.
Outcome:	The proposed method produces promising coordination instances that provide gains for the task in low-resource settings.

Copied to clipboard

Sebastian Vincent, Robert Flynn, Carolina Scarton

Uncertainty-aware Parameter-Efficient Self-training for Semi-supervised Language Understanding (2023.findings-emnlp)

Challenge:	Existing research has focused on providing individual, well-defined types of context in translation, such as the surrounding text or discrete external variables like the speaker’s gender.
Approach:	They introduce a novel neural machine translation framework that interprets all context as text.
Outcome:	The proposed framework outperforms a baseline that matched the parameters and significantly outperformed it in English translation.

Copied to clipboard

Jianing Wang, Qiushi Sun, Nuo Chen, Chengyu Wang, Jun Huang, Ming Gao, Xiang Li

Combining Word Embeddings with Bilingual Orthography Embeddings for Bilingual Dictionary Induction (2020.coling-main)

Challenge:	Existing methods for pre-trained language models rely on noisy data, which can be expensive if all parameters are updated.
Approach:	They propose a self-training framework that incorporates Monte Carlo dropouts into the model and judiciously selects reliable pseudo-labeled examples based on confidence and certainty.
Outcome:	The proposed framework improves performance and efficiency over multiple tasks over multiple datasets.

Copied to clipboard

Silvia Severini, Viktor Hangya, Alexander Fraser, Hinrich Schütze

Document-Level Event Argument Extraction With a Chain Reasoning Paradigm (2023.acl-long)

Challenge:	Bilingual dictionary induction (BDI) is a task of finding target language translations of source language words.
Approach:	They propose to use bilingual orthography Embeddings to enrich BWE-based BDI with transliteration information to make a decision on which information source is more reliable for a particular word pair.
Outcome:	The proposed system improves on English-Russian BDI and shows that it can be built with only weak bilingual signals and even without any bilingual signal.

Copied to clipboard

Jian Liu, Chen Liang, Jinan Xu, Haoyan Liu, Zhe Zhao

Reasoning

Challenge:	Document-level event argument extraction aims to identify event arguments beyond sentence level, where a significant challenge is to model long-range dependencies.
Approach:	They propose a chain reasoning paradigm which captures long-range interdependence due to the chains’ compositional nature and generates decomposable first-order logic rules for reasoning.
Outcome:	The proposed method outperforms previous methods on two benchmarks and is robust enough to defend against adversarial attacks.

Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training (2023.findings-acl)

Copied to clipboard

Sai Ashish Somayajula, Lifeng Jin, Linfeng Song, Haitao Mi, Dong Yu

Few-shot Unified Question Answering: Tuning Models or Prompts? (2023.findings-emnlp)

Challenge:	Existing approaches to fine tune a large language model in low-resource settings are limited in their expressiveness or rely on task-independent knowledge.
Approach:	They propose a framework where all parameters are finetuned with task-dependent information from the training data only.
Outcome:	The proposed framework outperforms baseline models on several classification datasets in low-resource scenarios.

Copied to clipboard

Srijan Bansal, Semih Yavuz, Bo Pang, Meghana Bhat, Yingbo Zhou

Revisiting Interpolation Augmentation for Speech-to-Text Generation (2024.findings-acl)

Challenge:	Question-answering (QA) tasks investigate specific question types, knowledge domains, or reasoning skills, leading to specialized models catering to specific categories of QA tasks.
Approach:	They propose to use model and prompt tuning for unified QA in a low-resource setting to overcome drawbacks of unified models.
Outcome:	The proposed model and prompt tuning paradigms outperform model tuning in a few-shot setting with a good initialization and achieve a significant performance boost from pre-training in 'low-resource' setting.

Copied to clipboard

Chen Xu, Jie Wang, Xiaoqian Liu, Qian Dong, Chunliang Zhang, Tong Xiao, JingBo Zhu, Dapeng Man, Wu Yang

Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models (2024.acl-long)

Challenge:	Existing approaches to speech-to-text generation tasks are limited by the lack of extensive labeled datasets.
Approach:	They propose to use interpolation augmentation to construct virtual training samples by transforming inputs and labels to enhance generalization in other domains.
Outcome:	The proposed approach significantly improves performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings.

Copied to clipboard

Guanming Xiong, Junwei Bao, Wen Zhao

SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations (2023.findings-emnlp)

Challenge:	Knowledge base question answering (KBQA) is a challenging task, particularly in parsing intricate questions into executable logical forms.
Approach:	They propose a framework to generate logical forms through direct interaction with knowledge bases (KBs) by annotating a dataset with step-wise reasoning processes.
Outcome:	The proposed framework achieves competitive results on the WebQuestionsSP, ComplexWebQuestIONS, KQA Pro, and MetaQA datasets with a minimal number of examples (shots). Importantly, the proposed model supports manual intervention, allowing for the iterative refinement of LLM outputs.

Copied to clipboard

Ioannis Tsiamas, José Fonollosa, Marta Costa-jussà

Progressive Translation: Improving Domain Robustness of Neural Machine Translation with Intermediate Sequences (2023.findings-acl)

Challenge:	End-to-end Speech Translation models are limited by a data bottleneck . end-to end models can address several shortcomings of cascaded models .
Approach:	They propose a data augmentation strategy to augment sentence-level datasets by using an Audio Segmentation system to re-segment the speech of each document with different length constraints.
Outcome:	The proposed method achieves state-of-the-art results in MuST-C and in mTEDx.

Copied to clipboard

Chaojun Wang, Yang Liu, Wai Lam

Robustness in NLP

Challenge:	Existing studies show that intermediate supervision signals benefit various tasks such as math word problems and commonsense reasoning.
Approach:	They propose to introduce an inductive bias that reflects a domain-agnostic principle of translation and a full-permutation multi-task learning to alleviate spurious correlations.
Outcome:	The proposed signals reduce spurious correlations and spurious hallucinations on out-of-domain translation, and are especially promising in low-resource scenarios.

From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)

Copied to clipboard

Feng Zhang, Wei Chen, Fei Ding, Meng Gao, Tengjiao Wang, Jiahui Yao, Jiabin Zheng

PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation (2024.emnlp-main)

Challenge:	Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains.
Approach:	They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates.
Outcome:	The proposed model outperforms baselines that need further fine-tuning or domain-specific samples.

Copied to clipboard

Christoph Leiter, Steffen Eger

Multijugate Dual Learning for Low-Resource Task-Oriented Dialogue System (2023.findings-acl)

Challenge:	Large language models (LLMs) are useful for low-resource scenarios and time-restricted applications.
Approach:	They propose a large-scale evaluation tool for large language models that uses prompts . they evaluate 720 prompt templates for open-source LLM-based metrics on MT and summarization datasets a 6.6M evaluations.
Outcome:	The proposed model evaluates 720 prompt templates on machine translation and summarization datasets.

Copied to clipboard

Shimin Li, Xiaotian Zhang, Yanjun Zheng, Linyang Li, Xipeng Qiu

Dialogue Systems & Conversational Agents

Challenge:	End-to-end task-oriented dialogue systems are expensive to annotate and lack data in real scenarios.
Approach:	They propose to implement dual learning in task-oriented dialogues to exploit the correlation of heterogeneous data.
Outcome:	The proposed method improves the effectiveness of end-to-end task-oriented dialogue systems under multiple benchmarks and obtains state-of-the-art results in low-resource scenarios.

Continual Contrastive Finetuning Improves Low-Resource Relation Extraction (2023.acl-long)

Copied to clipboard

Wenxuan Zhou, Sheng Zhang, Tristan Naumann, Muhao Chen, Hoifung Poon

DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis (2025.acl-long)

Challenge:	Relation extraction (RE) has been challenging in low-resource domains and with limited resources.
Approach:	They propose to pretrain and finetune the RE model using consistent objectives of contrastive learning.
Outcome:	The proposed method outperforms PLM-based RE classifier on two document-level RE datasets.

Copied to clipboard

Hongling Xu, Yice Zhang, Qianlong Wang, Ruifeng Xu

Sentiment Analysis

Challenge:	Existing methods for annotating data are time-consuming and labor-intensive . Existing low-resource solutions comprise data augmentation and in-context learning .
Approach:	They propose a dual-stream data synthesis framework for few-shot ABSA . it leverages key-point-driven and instance-driven LLMs to generate diverse data .
Outcome:	Extensive experiments show that DS2-ABSA outperforms existing methods . previous studies have shown that the proposed approach generates diverse data .

Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture (2023.findings-emnlp)

Copied to clipboard

Bingsheng Yao, Ishan Jindal, Lucian Popa, Yannis Katsis, Sayan Ghosh, Lihong He, Yuxuan Lu, Shashank Srivastava, Yunyao Li, James Hendler, Dakuo Wang

FSTs vs ICL: Generalisation in LLMs for an under-resourced language (2025.findings-emnlp)

Challenge:	Existing low-resource learning techniques focus on label annotation while neglecting the natural language explanation of a data point.
Approach:	They propose a novel architecture that leverages an explanation-generation model to produce explanations guided by human explanations and a prediction model that utilizes generated explanations toward prediction faithfully.
Outcome:	The proposed architecture produces explanations guided by human explanations, a prediction model that utilizes generated explanations toward prediction faithfully, and a data diversity-based AL sampling strategy that benefits from the explanation annotations.

Copied to clipboard

Ximena Gutierrez, Mikel Segura Elizalde, Victor Mijangos

IM-BERT: Enhancing Robustness of BERT through the Implicit Euler Method (2024.emnlp-main)

Challenge:	LLMs have been widely adopted to tackle many traditional NLP tasks, but their effectiveness remains uncertain in scenarios where pre-trained models have limited prior knowledge of a language.
Approach:	They propose a rule-based method using a finite-state transducer and an in-context learning method that provides the model with string transduction examples.
Outcome:	The proposed method outperforms FSTs in zero-shot settings while ICL surpasses FLMs.

Copied to clipboard

MiHyeon Kim, Juhyoung Park, YoungBin Kim

UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective (2023.acl-long)

Challenge:	Pre-trained Language Models (PLMs) have shown remarkable performance on diverse NLP tasks through pre-training and fine-tuning.
Approach:	They propose a numerically robust IM-connection incorporating a layer of BERT as a solution of Ordinary Differential Equations (ODEs) . Experimental results validate the robustness of IM BERT under various conditions.
Outcome:	The proposed model outperforms the existing model on the adversarial GLUE dataset by 5.9%p on low-resource scenarios.

Copied to clipboard

Yang Ping, JunYu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Pingjian Zhang, Jiaxing Zhang

Making Pre-trained Language Models Better Continual Few-Shot Relation Extractors (2024.lrec-main)

Challenge:	Existing approaches for information extraction (IE) are limited by the number of subtasks and the isolation of the subtask.
Approach:	They propose a new paradigm for universal information extraction that is compatible with any schema format and applicable to a list of IE tasks.
Outcome:	The proposed framework outperforms generative universal IE models on 14 benchmarks with the supervised setting and the state-of-the-art performance in low-resource scenarios.

Copied to clipboard

Shengkun Ma, Jiale Han, Yi Liang, Bo Cheng

LOHRec: Leveraging Order and Hierarchy in Generative Sequential Recommendation (2025.findings-emnlp)

Challenge:	Existing methods to learn new relations with limited labeled data are prone to catastrophic forgetting and overfitting.
Approach:	They propose a framework that uses prompts to acquire more generalized knowledge . they propose CFRE to continuously learn new relations while retaining knowledge of old ones .
Outcome:	The proposed method outperforms state-of-the-art methods by a large margin and significantly mitigates catastrophic forgetting and overfitting in low-resource scenarios.

Copied to clipboard

Jiawen Xie, Haiyang Wu, Deyi Ji, Yuekui Yang, Shaoping Ma

Challenge:	generative recommenders focus on maximizing the prediction probability of the next item in the temporal sequence, ignoring diverse potential items.
Approach:	They propose a learning framework that leverages order and hierarchy in generative recommendation using quantized identifiers to further explore performance ceiling of lightweight generative recommenders.
Outcome:	The proposed learning framework outperforms strong prior baselines across multiple datasets.

Meta-Adapter for Self-Supervised Speech Models: A Solution to Low-Resource Speech Recognition Challenges (2024.lrec-main)

Copied to clipboard

Yaqi Chen, Hao Zhang, Xukui Yang, Wenlin Zhang, Dan Qu

RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction (2023.findings-emnlp)

Challenge:	Existing self-supervised learning models can learn latent representations from large amounts of unlabeled data, but they are expensive to fine-tune.
Approach:	They develop a meta-adapter to obtain meta-initialized parameters for self-supervised models . meta-Adapters show better generalization and extensibility than traditional pretraining methods .
Outcome:	Experiments on common voice and FLEURS datasets show Meta-Adapter performs better on low-resource languages . authors show it can be used on 12 low-source languages, but it requires huge computational resources .

Copied to clipboard

Chengyuan Liu, Fubang Zhao, Yangyang Kang, Jingyuan Zhang, Xiang Zhou, Changlong Sun, Kun Kuang, Fei Wu

Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training (2025.acl-long)

Challenge:	Named Entity Recognition (NER) and Relation Extraction (RE) models have limited success when extracting general schemas such as quadruples and quintuples.
Approach:	They propose a formal formulation that covers almost all extraction schemas and a Recursive Method with Explicit Schema Instructor for UIE.
Outcome:	The proposed method shows strong performance under full-shot and few-shot settings and achieves state-of-the-art results on the tasks of extracting complex schemas.

Copied to clipboard

Ziyong Lin, Haoyi Wu, Shu Wang, Kewei Tu, Zilong Zheng, Zixia Jia

Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMs (2025.findings-emnlp)

Challenge:	Existing methods for converting large language models into powerful text encoders require extensive training on large datasets.
Approach:	They propose a training-free approach that enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance.
Outcome:	The proposed approach enables bidirectional attention and suppresses the attention sink phenomenon, resulting in superior performance.

Copied to clipboard

Yao Fu, Runchao Li, Xianxuan Long, Haotian Yu, Xiaotian Han, Yu Yin, Pan Li

Challenge:	Neural network pruning disrupts LLMs’ internal activation features crucial for lie detection . layer-wise pruning sparsity inadvertently removes crucial weights, failing to improve lie detection performance despite its reliance on the most crucial LLM layer.
Approach:	They propose a pruning approach that places greater emphasis on layers with more activation outliers and stronger discriminative features simultaneously.
Outcome:	The proposed approach improves the hallucination detection for pruned LLMs (achieving 88% accuracy at 50% sparsity) and enhances their performance on TruthfulQA.

Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation (2025.findings-emnlp)

Copied to clipboard

Armel Randy Zebaze, Benoît Sagot, Rachel Bawden

HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment (2026.acl-long)

Challenge:	generative large language models (LLMs) can perform in-context learning . machine translation (MT) has been shown to benefit from in-constitu examples .
Approach:	They propose a compositional translation paradigm that replaces naive few-shot MT with similarity-based demonstrations.
Outcome:	The proposed paradigm replaces naive few-shot MT with similarity-based demonstrations.

Copied to clipboard

Zhanyu Liu, Qingguo Hu, Ante Wang, Chenqing Liu, Zhishang Xiang, Hui Li, Delai Qiu, Jinsong Su

PARME: Parallel Corpora for Low-Resourced Middle Eastern Languages (2025.acl-long)

Challenge:	Existing methods for training reasoning-oriented large language models assume high-resource settings with abundant data.
Approach:	They propose a framework that integrates high-value general-domain data to promote more diverse exploration.
Outcome:	The proposed framework matches or surpasses RLVR trained with 32 target-domain samples using 32 target domain samples.

Copied to clipboard

Sina Ahmadi, Rico Sennrich, Erfan Karami, Ako Marani, Parviz Fekrazad, Gholamreza Akbarzadeh Baghban, Hanah Hadi, Semko Heidari, Mahîr Dogan, Pedram Asadi, Dashne Bashir, Mohammad Amin Ghodrati, Kourosh Amini, Zeynab Ashourinezhad, Mana Baladi, Farshid Ezzati, Alireza Ghasemifar, Daryoush Hosseinpour, Behrooz Abbaszadeh, Amin Hassanpour, Bahaddin Jalal Hamaamin, Saya Kamal Hama, Ardeshir Mousavi, Sarko Nazir Hussein, Isar Nejadgholi, Mehmet Ölmez, Horam Osmanpour, Rashid Roshan Ramezani, Aryan Sediq Aziz, Ali Salehi, Mohammadreza Yadegari, Kewyar Yadegari, Sedighe Zamani Roodsari

TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills (2024.lrec-main)

Challenge:	UNESCO has identified 60 varieties of Middle Eastern languages as underrepresented . a limited availability of language technology perpetuates a cycle of digital exclusion .
Approach:	They develop a parallel corpora for eight severely under-resourced varieties in the region . they evaluate machine translation capabilities through zero-shot approaches and fine-tuning experiments .
Outcome:	The proposed model aims to improve the processing of the eight under-resourced languages in the Middle East.

Copied to clipboard

Qiushi Sun, Nuo Chen, Jianing Wang, Ming Gao, Xiang Li

Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque (2025.emnlp-main)

Challenge:	Existing methods to fine-tune code intelligence models to individual tasks are costly and require large data sets.
Approach:	They propose a Transferable fine-tuning strategy for Code representation learning that uses a tunable prefix encoder to capture cross-task and cross-language transferable knowledge and apply it to downstream adaptation.
Outcome:	The proposed method can lead to superior performance on code-related tasks and encourage mutual reinforcement.

Copied to clipboard

Oscar Sainz, Naiara Perez, Julen Etxaniz, Joseba Fernandez de Landa, Itziar Aldabe, Iker García-Ferrero, Aimar Zabala, Ekhi Azurmendi, German Rigau, Eneko Agirre, Mikel Artetxe, Aitor Soroa

WkNER: Enhancing Named Entity Recognition with Word Segmentation Constraints and kNN Retrieval (2024.lrec-main)

Challenge:	Instructing language models with user intent requires large instruction datasets limited to a limited set of languages.
Approach:	They propose to use existing LLMs and synthetically generated instructions to train models with user intent.
Outcome:	The proposed model outperforms base non-instructed models on Basque without Basque instructions.

Copied to clipboard

Yanchun Li, Senlin Deng, Dongsu Shen, Shujuan Tian, Saiqin Long

Syntactic Text Processing

Challenge:	Named Entity Recognition (NER) tasks require detecting the span and category of the entity from the text block.
Approach:	They propose a kNN retrieval enhancement algorithm that incorporates word segmentation information to enhance the model’s generalization ability and alleviate the problem of missing entity tokens in prediction.
Outcome:	The proposed method improves the performance of baseline models and achieves better or compared recognition accuracy than previous state-of-the-art models in multiple public Chinese and English datasets.

Enrich, Aggregate, and Generate: Three-stage Biomedical Data-to-Text Generation Using Large Language Models in Low-resource Scenarios (2026.findings-acl)

Copied to clipboard

Yupian Lin, Guangya Yu, Yuang Bian, Cheng Yuan, Hui Luo, Tong Ruan

BubbleRAG: Interactive Cognitive Offloading with Thought Bubble in Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Biomedical data-to-text generation is a branch of Natural Language Generation, aiming at generating textual natural language descriptions that can fluently and precisely describe the structured data.
Approach:	They propose an LLM framework that can be used to generate textual natural language descriptions using in-context learning.
Outcome:	The proposed framework provides good interpretability and superior performance on the BioLeaflets dataset.

Copied to clipboard

Fuda Ye, Jiachuan Wang, Yongqi Zhang, Lei Chen, Shuangyin Li