ZERO-SHOT TRANSFER

On Efficiently Acquiring Annotations for Multilingual Models (2022.acl-short)

Challenge:	Negation resolution remains an acute and continuously researched question in Natural Language Processing.
Approach:	They propose to use multilingual pre-trained general representation models to detect negation scope in languages without annotated data.
Outcome:	The proposed model achieves token-level F1 score between English, Spanish, French, and Russian.

Copied to clipboard

Joel Ruben Antony Moniz, Barun Patra, Matthew Gormley

Green & Sustainable NLP

Challenge:	a recent study shows that joint learning across multiple languages performs better than the aforementioned approaches . traditional approaches to support NLP tasks require a lot of annotations to perform . a new approach is to train a model for each language with annotation budget divided equally among them .
Approach:	They propose a method for joint learning across multiple languages using a single model . they show that active learning provides additional, complementary benefits .
Outcome:	The proposed method outperforms other models on a diverse set of tasks . it can arbitrate its annotation budget to query languages it is less certain on .

Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages (2022.acl-long)

Copied to clipboard

Vaidehi Patil, Partha Talukdar, Sunita Sarawagi

Low-Resource NLP

Challenge:	Pre-trained multilingual models have shown great potential for zero-shot cross-lingual transfer to low web-resource languages (LRLs).
Approach:	They propose a vocabulary generation algorithm which enhances lexical overlap across related languages by generating a token that increases the representation of LRLs.
Outcome:	The proposed approach improves cross-lingual transfer accuracy without reducing HRL representation and accuracy.

DiTTO: A Feature Representation Imitation Approach for Improving Cross-Lingual Transfer (2023.eacl-main)

Copied to clipboard

Shanu Kumar, Soujanya Abbaraju, Sandipan Dandapat, Sunayana Sitaram, Monojit Choudhury

Zero-shot Dependency Parsing with Pre-trained Multilingual Sentence Representations (D19-61)

Challenge:	Zero-shot cross-lingual transfer has been shown to be sub-optimal across low-resource languages due to the skew in resource distribution in languages.
Approach:	They propose to jointly reduce feature incongruity between the source and target language and increase generalization capabilities of pre-trained multilingual transformers.
Outcome:	Empirical results show that the proposed approach outperforms the standard zero-shot fine-tuning method on multiple datasets across all languages using only unlabeled instances in the target language.

Copied to clipboard

Ke Tran, Arianna Bisazza

Zero-Shot vs. Translation-Based Cross-Lingual Transfer: The Case of Lexical Gaps (2024.naacl-short)

Challenge:	Pretrained sentence representations have set the new state of the art in many language understanding tasks.
Approach:	They propose to use a multilingual corpus to train deep bidirectional sentence representations that are fully lexicalized to allow for the development of an unsupervised universal dependency parser.
Outcome:	The proposed approach outperforms the best CoNLL 2018 systems in all of the shared task’s six truly low-resource languages while using a single system.

Copied to clipboard

Abteen Ebrahimi, Katharina Wense

Zero-shot Cross-lingual Transfer With Learned Projections Using Unlabeled Target-Language Data (2023.acl-short)

Challenge:	lexical gaps exist in a variety of domains, such as QA, but they can only be expressed as a combination of words in another language.
Approach:	They compare the current performance and long-term viability of two approaches to cross-lingual transfer . they leverage lexical gaps to create a multilingual question answering dataset .
Outcome:	The proposed model outperforms zero-shot transfer and machine translation (MT) lexical gaps exist in a variety of domains, including linguistics, linguistic coding, and linguistic analysis.

Copied to clipboard

Ujan Deb, Ridayesh Parab, Preethi Jyothi

Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases (2023.findings-eacl)

Challenge:	Zero-shot cross-lingual transfer is enabled by pairing the language adapter in the target language with an appropriate task adapter within a source language.
Approach:	They propose to use unlabeled text to enhance zero-shot transfer by pairing language adapters with task adapters in a target language.
Outcome:	The proposed framework improves on three cross-lingual tasks with up to 11% relative improvement in Named Entity Recognition (NER), Question Answering (QA) and Natural Language Inference (NLI).

Copied to clipboard

Santosh T.y.s.s, Oana Ichim, Matthias Grabmair

ColorBrowserAgent: Complex Long-Horizon Browser Agent with Adaptive Knowledge Evolution (2026.acl-industry)

Challenge:	Legal Judgment Prediction (LJP) is a classification task that uses textual descriptions of case facts as the input.
Approach:	They propose to use legal reasoning to map article text to specific case fact text to improve the model's generalization to zero-shot settings.
Outcome:	The proposed model outperforms straightforward fact classification and improves zero-shot transfer performance.

Copied to clipboard

Jihong Wang, Jiamu Zhou, Weiming Zhang, Teng Wang, Weiwen Liu, Zhuosheng Zhang, Xingyu Lou, Weinan Zhang, Huarong Deng, Jun Wang

Robustness in NLP

Challenge:	Xue et al., 2025): deploying autonomous web agents in production remains difficult due to site heterogeneity and long-horizon instability.
Approach:	They propose a knowledge-evolving agent that can be used to automate web workflows . they use human-in-the-loop knowledge adaptation and knowledge-aligned progressive summarization .
Outcome:	Experiments on WebArena, WebChoreAren and industrial deployment show it outperforms baselines.

Compositional Zero-Shot Domain Transfer with Text-to-Text Models (2023.tacl-1)

Copied to clipboard

Fangyu Liu, Qianchu Liu, Shruthi Bannur, Fernando Pérez-García, Naoto Usuyama, Sheng Zhang, Tristan Naumann, Aditya Nori, Hoifung Poon, Javier Alvarez-Valle, Ozan Oktay, Stephanie L. Hyland

DeepStruct: Pretraining of Language Models for Structure Prediction (2022.findings-acl)

Challenge:	Existing approaches to zero-shot domain transfer are limited by domain gap and lack of in-domain labels.
Approach:	They propose a compositional transfer learning framework (DoT51) that learns domain knowledge and task knowledge in a multi-task manner without access to in-domain labels.
Outcome:	The proposed framework outperforms the current state-of-the-art in zero-shot domain transfer by over 7 absolute points in accuracy on RadNLI.

Copied to clipboard

Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song

Language-Independent Representations Improve Zero-Shot Summarization (2024.naacl-short)

Challenge:	Pretrained language models perform structural understanding tasks that focus on understanding one aspect of the text.
Approach:	They propose a method for improving the structural understanding abilities of language models by pretraining them to generate structures from the text on task-agnostic corpora.
Outcome:	The proposed model performs state-of-the-art on 21 of 28 datasets.

Copied to clipboard

Vladimir Solovyev, Danni Liu, Jan Niehues

Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension (2022.acl-long)

Challenge:	Pretrained models can be fine tuned on downstream generation tasks, but they can fail in zero-shot conditions.
Approach:	They propose query-key finetuning to decouple task-specific knowledge from pretrained models . they propose a variant that more directly enforces language-agnostic representations .
Outcome:	The proposed model decouples task-specific knowledge from pretrained language generation abilities.

Copied to clipboard

Linjuan Wu, Shaojuan Wu, Xiaowang Zhang, Deyi Xiong, Shizhan Chen, Zhiqiang Zhuang, Zhiyong Feng

”Diversity and Uncertainty in Moderation” are the Key to Data Selection for Multilingual Few-shot Transfer (2022.findings-naacl)

Challenge:	Existing methods to zero-shot transfer knowledge from rich-resource to low-resourced languages are limited due to linguistic discrepancies in different languages.
Approach:	They propose a multilingual MRC framework equipped with a Siamese Semantic Disentanglement Model to disassociate semantics from syntax in models learned by multilingual pre-trained models.
Outcome:	The proposed model disassociates semantics from syntax in multilingual models.

Copied to clipboard

Shanu Kumar, Sandipan Dandapat, Monojit Choudhury

ChatGPT for Zero-shot Dialogue State Tracking: A Solution or an Opportunity? (2023.acl-short)

Challenge:	Existing approaches for few-shot transfer show significant gain over zero-shot transfers . language resource distribution is skewed across the world's languages . proposed methods use multiple measures such as data entropy and gradient embedding .
Approach:	They propose a loss embedding method for sequence labeling tasks that induces diversity and uncertainty sampling similar to gradient embeddment.
Outcome:	The proposed methods outperform baseline methods for POS tagging, NER, and NLI tasks for up to 20 languages.

Copied to clipboard

Michael Heck, Nurul Lubis, Benjamin Ruppik, Renato Vukovic, Shutong Feng, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Milica Gasic

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue (2022.tacl-1)

Challenge:	Recent research on dialog state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas.
Approach:	They propose to use schema descriptions to facilitate zero-shot transfer to new domains . they argue that general purpose language models lack the ability to replace specialized systems .
Outcome:	The proposed method achieves state-of-the-art in zero-shot DST with in-context learning capabilities.

Copied to clipboard

Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Osmar Zaiane, Mo Yu, Edoardo M. Ponti, Siva Reddy

Dialogue Systems & Conversational Agents

Challenge:	a new benchmark for hallucination-free dialogues is based on knowledge-based conversational models that generate unsupported utterances . a recent study shows that models that are trustworthy generate unverifiable or factually incorrect statements .
Approach:	They propose a data-centric solution to edit hallucinated responses in the Wizard of Wikipedia benchmark.
Outcome:	The proposed model improves on the Wizard of Wikipedia benchmark while maintaining engaging conversations.

Parameter-Efficient Neural Reranking for Cross-Lingual and Multilingual Retrieval (2022.coling-1)

Copied to clipboard

Robert Litschko, Ivan Vulić, Goran Glavaš

Zero-Shot Information Extraction as a Unified Text-to-Triple Translation (2021.emnlp-main)

Challenge:	State-of-the-art neural rankers are notoriously data-hungry and rarely used in multilingual and cross-lingual retrieval settings.
Approach:	They propose to use Sparse Fine-Tuning Masks and Adapters to transfer rankers trained on English data to other languages and cross-lingual setups by means of multilingual encoders.
Outcome:	The proposed methods outperform standard zero-shot transfer with full MMT fine-tuning while being more modular and reducing training times.

Copied to clipboard

Chenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang, Dawn Song

Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual Alignment (2025.acl-long)

Challenge:	a number of information extraction tasks require task-specific training.
Approach:	They propose a text-to-triple translation framework for information extraction tasks . they propose enabling task-agnostic translation by leveraging latent knowledge of a pre-trained language model .
Outcome:	The proposed framework outperforms the existing methods on open information extraction tasks.

Copied to clipboard

Yongxin Huang, Kexin Wang, Goran Glavaš, Iryna Gurevych

A Transformational Biencoder with In-Domain Negative Sampling for Zero-Shot Entity Linking (2022.findings-acl)

Challenge:	Multilingual sentence encoders are often trained to map sentences from different languages into a shared semantic vector space . cross-lingual alignment training distorts optimal monolingual structure of semantic spaces of individual languages . a modular solution can be used for cross-linguistic tasks such as cross-language semantic similarity and zero-shot transfer .
Approach:	They propose a modular training system that embeds sentences from different languages into a shared semantic vector space.
Outcome:	The proposed solution achieves better performance across all tasks compared to monolithic models.

Copied to clipboard

Kai Sun, Richong Zhang, Samuel Mensah, Yongyi Mao, Xudong Liu

𝜇PLAN: Summarizing using a Content Plan as Cross-Lingual Bridge (2024.eacl-long)

Challenge:	Recent work on entity linking has focused on the zero-shot scenario where at test time the entity mention to be labelled is never seen during training.
Approach:	They propose a transformational biencoder that integrates a transform into BERT to perform a zero-shot transfer from the source domain to the target domain.
Outcome:	The proposed model performs a zero-shot transfer from the source domain to the target domain on a benchmark dataset and achieves new state-of-the-art.

Copied to clipboard

Fantine Huot, Joshua Maynez, Chris Alberti, Reinald Kim Amplayo, Priyanka Agrawal, Constanza Fierro, Shashi Narayan, Mirella Lapata

Text Generation

Challenge:	Recent advances in abstractive summarization have focused on English, but more recently, with the advent of large pre-trained models, the task is becoming more complex.
Approach:	They propose an approach to cross-lingual summarization that uses an intermediate planning step as a cross-linguistic bridge.
Outcome:	The proposed approach achieves state-of-the-art in terms of informativeness and faithfulness on the XWikis dataset.

mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations (2023.findings-emnlp)

Copied to clipboard

Jonas Pfeiffer, Francesco Piccinno, Massimo Nicosia, Xinyi Wang, Machel Reid, Sebastian Ruder

Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text (2026.findings-eacl)

Challenge:	Recent large language models display surprising multilingual capabilities despite being pre-trained on English data.
Approach:	They propose a multilingual sequence-to-sequence model that disentangles language-specific information from language-agnostic information.
Outcome:	The proposed model outperforms existing models on representative natural language understanding and generation tasks in 40+ languages.

Copied to clipboard

Piyush Singh Pasi

Multimodality

Challenge:	Existing multimodal models rely on machine translation, but performance drops for other languages due to limited multilingual multimodal resources.
Approach:	They propose a lightweight alignment method that learns only a few linear layers using English text alone to map multilingual text embeddings into multimodal space.
Outcome:	M2M achieves strong zero-shot transfer on XTD Text-to-Image retrieval in English and spanish . it learns only a few linear layers to map multilingual text embeddings into multimodal space .

NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive Pretraining (2025.findings-emnlp)

Copied to clipboard

Sicheng Wang, Wenyi Wu, Zibo Zhang

Delving Deeper into Cross-lingual Visual Question Answering (2023.findings-eacl)

Challenge:	NeighXLM is a neighbor-augmented contrastive pretraining framework . it exploits intra-language semantic relationships captured during pretraining to construct high-quality positive pairs.
Approach:	They propose a neighbor-augmented contrastive pretraining framework that mines semantic neighbors from unlabeled corpora to enrich target-language supervision.
Outcome:	The proposed framework enriches target-language supervision by mining semantic neighbors from unlabeled corpora.

Copied to clipboard

Chen Liu, Jonas Pfeiffer, Anna Korhonen, Ivan Vulić, Iryna Gurevych

Multimodality

Challenge:	Existing studies on cross-lingual VQA have reported poor zero-shot transfer performance of current multilingual multimodal Transformers . lack of multilingual resources has hindered development and evaluation of VQA methods beyond the English language .
Approach:	They analyze cross-lingual VQA across different question types of varying complexity . they show that simple modifications to the standard training setup can substantially reduce the transfer gap to monolingual English performance.
Outcome:	The proposed model significantly reduces the transfer gap to monolingual English performance . the proposed model also improves on question types and languages .

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale (2020.emnlp-main)

Copied to clipboard

Andreas Rücklé, Jonas Pfeiffer, Iryna Gurevych

Low-Resource NLP

Challenge:	a new study examines the zero-shot transfer capabilities of text matching models on a massive scale.
Approach:	They propose to integrate self-supervised with supervised multi-task learning on all available source domains to study the zero-shot transfer capabilities of text matching models on a massive scale.
Outcome:	The proposed model outperforms in-domain BERT and the previous state of the art on six benchmarks.

MetaICL: Learning to Learn In Context (2022.naacl-main)

Copied to clipboard

Sewon Min, Mike Lewis, Luke Zettlemoyer, Hannaneh Hajishirzi

Subword Mapping and Anchoring across Languages (2021.findings-emnlp)

Challenge:	Large language models can do in-context learning by conditioning on a few training examples with no parameter updates or task-specific templates.
Approach:	They propose a meta-training framework where a pretrained language model is tuned to do in-context learning on a large set of training tasks.
Outcome:	The proposed framework outperforms baseline models on 142 NLP datasets and a range of target tasks with domain shifts.

Copied to clipboard

Giorgos Vernikos, Andrei Popescu-Belis

Lost in Translation, Found in Spans: Identifying Claims in Multilingual Social Media (2023.emnlp-main)

Challenge:	State-of-the-art multilingual systems rely on shared vocabularies that cover all considered languages.
Approach:	They propose a method to construct bilingual subword vocabularies by mapping and anchoring subwords together over multiple languages.
Outcome:	The proposed method improves zero-shot transfer to an unseen language without task-specific data, but only by sharing subword embeddings.

Copied to clipboard

Shubham Mittal, Megha Sundriyal, Preslav Nakov

When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer (2022.naacl-main)

Challenge:	Claim span identification (CSI) is an important step in fact-checking pipelines . despite its importance to journalists and fact-seekers, it remains a understudied problem .
Approach:	They propose to use social media claims to identify text segments that contain a check-worthy claim or assertion in a social media post.
Outcome:	The proposed dataset outperforms other cross-lingual transfer methods on multiple languages.

Copied to clipboard

Ameet Deshpande, Partha Talukdar, Karthik Narasimhan

Know your audience: specializing grounded language models with listener subtraction (2023.eacl-main)

Challenge:	Recent work on multilingual language models has demonstrated their capacity for cross-lingual zero-shot transfer on downstream tasks.
Approach:	They conduct a large-scale empirical study to isolate the effects of various linguistic properties by measuring zero-shot transfer between four different natural languages.
Outcome:	The proposed model exhibits decent cross-lingual zero-shot transfer, with no significant differences in word order and embedding alignment.

Copied to clipboard

Aaditya K Singh, David Ding, Andrew Saxe, Felix Hill, Andrew Lampinen

Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents (2022.acl-long)

Challenge:	Effective communication requires adapting to the idiosyncrasies of each communicative context.
Approach:	They propose a method for specializing grounded language models without supervision . they fine-tune an attention-based adapter between a CLIP vision encoder and a large language model .
Outcome:	The proposed method allows a speaker to adapt to the idiosyncracies of the listeners without supervision.

Copied to clipboard

Biao Zhang, Ankur Bapna, Melvin Johnson, Ali Dabirmoghaddam, Naveen Arivazhagan, Orhan Firat

CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding (2022.findings-acl)

Challenge:	Document-level neural machine translation (DocNMT) is a powerful tool for integrating cross-sentence context into translations.
Approach:	They explore whether and how contextual modeling in DocNMT is transferable via multilingual modeling.
Outcome:	The proposed model can be used to transfer from teacher languages to student languages with no documents but sentence level data.

Copied to clipboard

Milan Gritta, Ruoyu Hu, Ignacio Iacobacci

Low-Resource NLP

Challenge:	Task-oriented personal assistants enable people to interact with devices and services using natural language.
Approach:	They propose a method to acquire task knowledge in a high-resource language and then transfer it to the low-resourced language(s) they use unlabelled parallel data to perform a quantitative analysis of the methods.
Outcome:	The proposed methods exceed state-of-the-art (SOTA) scores across nine languages, fifteen test sets and three benchmark multilingual datasets.

A Multilingual BPE Embedding Space for Universal Sentiment Lexicon Induction (P19-1)

Copied to clipboard

Mengjie Zhao, Hinrich Schütze

End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs (2021.emnlp-main)

Challenge:	Existing methods for sentiment lexicon induction are limited to low-resource languages.
Approach:	They propose a method for sentiment lexicon induction that is applicable to the entire range of typological diversity of the world's languages.
Outcome:	The proposed method is applicable to the entire range of typological diversity of the world's languages.

Copied to clipboard

Dinesh Raghu, Shantanu Agarwal, Sachindra Joshi, null Mausam

Natural Language Interfaces

Challenge:	Existing systems that use human-to-human dialogs to help users with specific tasks are still unexplored.
Approach:	They propose a problem in which a dialog system mimics a troubleshooting agent . they use a dataset grounded on 12 different troubleshooking flowcharts to train the agent a neural model .
Outcome:	The proposed model can do zero-shot transfer to unseen flowcharts and sets a strong baseline for future research.

Identifying Elements Essential for BERT’s Multilinguality (2020.emnlp-main)

Copied to clipboard

Philipp Dufter, Hinrich Schütze

Multi Task Learning For Zero Shot Performance Prediction of Multilingual Models (2022.acl-long)

Challenge:	Multilingual BERT (mBERT) does not use any crosslingual signal during training.
Approach:	They propose a multilingual pretraining setup that modifies the masking strategy using VecMap to allow for fast experimentation.
Outcome:	The proposed setup with pretrained models with three languages shows that it works well.

Copied to clipboard

Kabir Ahuja, Shanu Kumar, Sandipan Dandapat, Monojit Choudhury

Adversarial Learning for Zero-Shot Stance Detection on Social Media (2021.naacl-main)

Challenge:	Massively Multilingual Transformer based Language Models have been shown to be effective on zero-shot transfer across languages, though performance varies from language to language depending on pivot language(s) used for fine-tuning.
Approach:	They propose to combine multi-task learning problems with multi-lingual Transformers to model zero-shot transfer across languages.
Outcome:	The proposed model can predict zero-shot transfer across languages with a multi-task learning problem with pretraining data in very few languages.

Copied to clipboard

Emily Allaway, Malavika Srikanth, Kathleen McKeown

Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes (2022.findings-emnlp)

Challenge:	a new model for zero-shot stance detection on Twitter uses adversarial learning to generalize across topics . previous work on zero- shot stance detector on English social media focuses on cross-target stances .
Approach:	They propose a model that uses adversarial learning to generalize across topics on Twitter . their model achieves state-of-the-art performance on unseen test topics .
Outcome:	The proposed model achieves state-of-the-art performance on unseen topics with minimal computational costs.

Copied to clipboard

Louis Clouatre, Prasanna Parthasarathi, Amal Zouaq, Sarath Chandar

Applying Natural Annotation and Curriculum Learning to Named Entity Recognition for Under-Resourced Languages (2022.coling-1)

Challenge:	Recent advances in multilingual pretrained models have proven effective at zero-shot transfer to a wide variety of languages, but this transfer is not universal, with many languages not currently understood by multilingual approaches.
Approach:	They propose a general approach that requires only unlabelled text to detect which languages are not well understood by a cross-lingual model.
Outcome:	The proposed model can detect which languages are not well understood by a multilingual model on 350 low-resource languages.

Copied to clipboard

Valeriy Lobov, Alexandra Ivoylova, Serge Sharoff

Detecting Urgency Status of Crisis Tweets: A Transfer Learning Approach for Low Resource Languages (2020.coling-main)

Challenge:	Existing approaches to build NLP models for low-resourced languages rely on machine translation or cross-lingual transfer.
Approach:	They propose to use natural annotations to build synthetic training sets from resources not originally designed for the target downstream task.
Outcome:	The proposed model achieves the F1 score of 0.78 for Belarusian starting from zero resources compared to the baseline of 0.63 for English . the proposed model can be fine-tuned to reflect linguistic properties, such as the grammatical case and gender, for the Slavic languages.

Copied to clipboard

Efsun Sarioglu Kayi, Linyong Nan, Bohan Qu, Mona Diab, Kathleen McKeown

MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER (2021.acl-long)

Challenge:	We train monolingual and cross-lingual classifiers on the extracted features of tweets . we use a few state-of-the-art contextual embeddings to extract features of the tweets.
Approach:	They propose to use tweets to train a dataset of English and two low-resource languages to train zero-shot transfer models.
Outcome:	The proposed model performs well in English and in low-resource languages . the proposed model is based on state-of-the-art embeddings and semi-supervised methods .

Copied to clipboard

Linlin Liu, Bosheng Ding, Lidong Bing, Shafiq Joty, Luo Si, Chunyan Miao

Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer (2022.emnlp-main)

Challenge:	Existing approaches to cross-lingual NER are labeled sequence translation and instance-based transfer via machine translation (MT) Existing methods to cross NER include label projection and labeling, but they are expensive and time-consuming.
Approach:	They propose a simple but effective labeled sequence translation method to translate source-language training data to target languages and avoids word order change and entity span determination.
Outcome:	The proposed method avoids word order change and entity span determination and can be generalized with the language-specific features from the target-language synthetic data and the language independent features from multilingual synthetic data.

Copied to clipboard

Ahmet Üstün, Arianna Bisazza, Gosse Bouma, Gertjan van Noord, Sebastian Ruder

Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer? (2022.emnlp-main)

Challenge:	Existing multilingual models cannot fully leverage training data when it is available in different task-language combinations.
Approach:	They propose a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation.
Outcome:	The proposed model achieves the best or competitive gain when a mixture of multiple resources is available while being significantly more efficient than existing models.

Copied to clipboard

Ningyu Xu, Tao Gui, Ruotian Ma, Qi Zhang, Jingting Ye, Menghan Zhang, Xuanjing Huang

MultiEURLEX - A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer (2021.emnlp-main)

Challenge:	Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, but it is not well understood what leads to this variation and whether it fairly reflects difference between languages.
Approach:	They propose to use multilingual BERT to enable zero-shot cross-lingual transfer of syntactic knowledge between different languages by generating grammatical relations in 24 different languages.
Outcome:	The results show that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms.

Copied to clipboard

Ilias Chalkidis, Manos Fergadiotis, Ion Androutsopoulos

DaNE: A Named Entity Resource for Danish (2020.lrec-1)

Challenge:	MULTI-EURLEX is a dataset for topic classification of EU legal documents . fine-tuning a multilingually pretrained model in a single source language leads to catastrophic forgetting of multilingual knowledge and poor zero-shot transfer to other languages.
Approach:	They propose to use the dataset as a testbed for zero-shot cross-lingual transfer to exploit annotated training documents in one language to classify documents in another language.
Outcome:	The proposed model can be used to classify EU legal documents in other languages without a single source language and retain multilingual knowledge.

Copied to clipboard

Rasmus Hvingelby, Amalie Brogaard Pauli, Maria Barrett, Christina Rosted, Lasse Malm Lidegaard, Anders Søgaard

Meta-Tuning LLMs to Leverage Lexical Knowledge for Generalizable Language Style Understanding (2024.acl-long)

Challenge:	a named entity annotation for the Danish Universal Dependencies treebank is the largest publicly available named entity gold annotation.
Approach:	They propose a named entity annotation for the Danish Universal Dependencies treebank using the CoNLL-2003 annotation scheme DaNE.
Outcome:	The proposed annotations improve Danish named entity recognition over a recent cross-lingual approach and over norwegian training set.

Copied to clipboard

Ruohao Guo, Wei Xu, Alan Ritter

SLICER: Sliced Fine-Tuning for Low-Resource Cross-Lingual Transfer for Named Entity Recognition (2022.emnlp-main)

Challenge:	Existing large language models struggle to capture some language styles without fine-tuning.
Approach:	They propose to meta-trained LLMs based on representative lexicons to recognize new styles they have not been fine-tuned on.
Outcome:	The proposed method improves zero-shot transfer across styles on 13 established and 63 novel tasks generated with LLMs.

Copied to clipboard

Fabian David Schmidt, Ivan Vulić, Goran Glavaš

Cross-Domain Argument Quality Estimation (2023.findings-acl)

Challenge:	Large multilingual models fail to successfully transfer to low-resource languages for zero-shot cross-lingual transfer . sliced fine-tuning for named entity recognition (SLICER) forces stronger token contextualization in the Transformer.
Approach:	They propose a simple yet highly effective approach for improving zero-shot cross-lingual transfer for named entity recognition to low-resource languages.
Outcome:	The proposed approach reduces decontextualization of token representations and classifiers . it yields consistent transfer gains for low-resource languages, the authors show .

Copied to clipboard

Michael Fromm, Max Berrendorf, Evgeniy Faerman, Thomas Seidl

Reasoning

Challenge:	Argument mining is a field of automated discovery and organization of arguments.
Approach:	They propose to generalize argument quality estimation from multiple angles by combining empirical results with a training part.
Outcome:	The proposed method combines the results of two empirical evaluations with a training part to show that argument quality is among the more challenging tasks but can improve others.

FACTrial: Factorized Clinical Contrastive Training for Scalable Patient-Trial Retrieval (2026.acl-long)

Copied to clipboard

Xuanren Chen, Chongyang Tao, Tao Shen, Shuai Ma

Information Retrieval

Challenge:	Existing approaches to patient–trial retrieval rely on generic semantic matching and zero-shot transfer.
Approach:	They propose a factorized contrastive training framework that synthesizes diagnosis-aware supervision for scalable patient–trial retrieval.
Outcome:	Experiments show that the proposed framework improves quality and recall coverage.

AnyTOD: A Programmable Task-Oriented Dialog System (2023.emnlp-main)

Copied to clipboard

Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, Yonghui Wu

BERTwich: Extending BERT’s Capabilities to Model Dialectal and Noisy Text (2023.findings-emnlp)

Challenge:	a neuro-symbolic approach allows zero-shot adaptation to unseen tasks and domains . a neural LM keeps track of events that occur during a conversation and a symbolic program implements dialog policy is executed to recommend actions.
Approach:	They propose an end-to-end, zero-shot task-oriented dialog system . it is designed to adapt to unseen tasks or domains without prior training .
Outcome:	The proposed system can be programmed to adapt to unseen tasks without training . it reduces data collection and training requirements for enabling new TOD 1 16189 tasks .

Copied to clipboard

Aarohi Srivastava, David Chiang

IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning (2024.emnlp-main)

Challenge:	Pre-trained language models like BERT deteriorate in the face of dialect variation or noise.
Approach:	They propose to sandwich BERT's encoder stack between additional encoder layers trained to perform masked language modeling on noisy text.
Outcome:	The proposed approach promotes zero-shot transfer to dialectal text and reduces embedding space between words and noisy counterparts.

Copied to clipboard

Soumya Suvra Ghosal, Samyadeep Basu, Soheil Feizi, Dinesh Manocha

CaRL-EM: Cost-Aware Reinforcement Learning for Entity Matching with LLMs (2026.acl-long)

Challenge:	Existing prompt-tuning frameworks lack interpretability, limiting their ability to understand compositional nature of images.
Approach:	They propose a prompt-tuning method that integrates compositional attributes into manual prompts to enhance image-text alignment scores.
Outcome:	The proposed method improves CoOp performance by 7.35% across 10 diverse datasets.

Copied to clipboard

Chaohui Guo, Michel C. A. Klein, Zhisheng Huang

Challenge:	Entity matching (EM) requires fine-grained contextual understanding and domain knowledge.
Approach:	They propose a reinforcement learning controller that manages LLM operations by combining multiple operators and a set of model capacities.
Outcome:	The proposed controller can be reused with different LLM backends at inference time without retraining.

Open-DeBias: Toward Mitigating Open-Set Bias in Language Models (2025.findings-emnlp)

Copied to clipboard

Arti Rani, Shweta Singh, Nihar Ranjan Sahoo, Gaurav Kumar Nayak

microCLIP: Unsupervised CLIP Adaptation via Coarse-Fine Token Fusion for Fine-Grained Image Classification (2026.findings-acl)

Challenge:	Existing approaches to addressing harmful biases in LLMs are limited to predefined categories . a novel, data-efficient, and parameter-efficient debiasing method is proposed to mitigate existing social and stereotypical biase .
Approach:	They propose an open-set bias detection and mitigation method to address harmful biases in text-based QA.
Outcome:	The proposed method improves QA accuracy on Korean BBQ dataset by nearly 48% on ambiguous subsets and 6% on disambiguated ones.

Copied to clipboard

Sathira Silva, Eman Ali, Chetan Arora, Muhammad Haris Khan

Information Retrieval

Challenge:	Existing UA methods for fine-grained image classification rely on coarse-grain visual tokens, which misses fine spatial details.
Approach:	They propose a label-free self-training framework that adapts visual features and LLMderived text prototypes using fine-grained cues.
Outcome:	The proposed framework improves alignment between finegrained visual regions and rich textual descriptions while updating only layer norms and a tiny head.

One Pair Suffices: Unlocking Universal Zero-Shot Translation via Cross-Architecture Alignment (2026.acl-long)

Copied to clipboard

Hao Zong, Cong Hu Yuan, Chao Bei, Wentao Chen, Huan Liu, Kaiyu Huang, Degen Huang