TRANSLATION TASKS

Neural Machine Translation System using a Content-equivalently Translated Parallel Corpus for the Newswire Translation Tasks at WAT 2019 (D19-52)

Challenge:	We submitted our transformer-based neural machine translation system to the translation tasks of the 6th workshop on Asian Translation (WAT 2019).
Approach:	They propose a transformer-based neural machine translation system for Chinese-Japanese, English-Japanese, and Korean->Japanoise translation tasks.
Outcome:	The proposed system performed well on the two translation tasks and was ranked first in terms of the BLEU scores in all the JPC2 subtasks.

Copied to clipboard

Hideya Mino, Hitoshi Ito, Isao Goto, Ichiro Yamada, Hideki Tanaka, Takenobu Tokunaga

Tulun: Transparent and Adaptable Low-resource Machine Translation (2025.acl-demo)

Challenge:	In addition to the JIJI Corpus, we developed a corpus of 0.22M sentence pairs by manually, translating Japanese news sentences into English content- equivalently.
Approach:	They propose to use JIJI Corpus and Equivalent-style sentences to translate Japanese news sentences into English content- equivalently.
Outcome:	The proposed translation models achieved the best human evaluation scores in the newswire translation tasks at WAT 2019 . they used the JIJI Corpus, which was provided by the task organizer, and the Equivalent-style translation model to translate Japanese news sentences into English content- equivalently.

Copied to clipboard

Raphael Merx, Hanna Suominen, Lois Yinghui Hong, Nick Thieberger, Trevor Cohn, Ekaterina Vylomova

Hacking Neural Evaluation Metrics with Single Hub Text (2026.eacl-short)

Challenge:	a low-resource language that is the lingua franca in Timor-Leste lacks available corpora in the health domain.
Approach:	They propose a solution that combines neural MT with large language model-based post-editing guided by existing glossaries and translation memories.
Outcome:	The proposed system outperforms both standalone MT and LLM approaches across six low-resource languages on the FLORES dataset.

Copied to clipboard

Hiroyuki Deguchi, Katsuki Chousa, Yusuke Sakai

Language Technologies for the Creation of Multilingual Terminologies. Lessons Learned from the SSHOC Project (2022.lrec-1)

Challenge:	Recent embedding-based neural text evaluation metrics are not reliable due to black-box nature of neural networks.
Approach:	They propose to find a single adversarial text in the discrete space that is consistently evaluated as high-quality regardless of the test cases.
Outcome:	The proposed method outperforms translations generated individually for each source sentence in English-to-Japanese and English- to-German translation tasks.

Copied to clipboard

Federica Gamba, Francesca Frontini, Daan Broeder, Monica Monachini

The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation (2021.eacl-srw)

Challenge:	Language Technologies can help in promoting and facilitating multilingualism in the Social Sciences and Humanities domain.
Approach:	They propose to use Natural Language Processing and Machine Translation to provide tools to foster multilingual access and discovery to SSH content across different languages.
Outcome:	The proposed tools prove to be a valid asset to translation tasks . validation of results by domain experts proficient in the language is an unavoidable phase of the whole workflow.

Copied to clipboard

Jonne Saleva, Constantine Lignos

Evaluating Explanation Methods for Neural Machine Translation (2020.acl-main)

Challenge:	Current NMT systems typically operate at the level of subwords, causing problems of vocabulary sparsity.
Approach:	They compare subword segmentation methods with morphologically-based methods in a low-resource setting . they find that no consistent and reliable differences emerge between the methods .
Outcome:	The proposed methods outperform BPE in a low-resource translation setting.

Copied to clipboard

Jierui Li, Lemao Liu, Huayang Li, Guanlin Li, Guoping Huang, Shuming Shi

A Semantic Uncertainty Sampling Strategy for Back-Translation in Low-Resources Neural Machine Translation (2025.acl-srw)

Challenge:	Neural machine translation (NMT) has seen great success during recent years.
Approach:	They propose a metric that measures the fidelity of explanation methods on translation tasks . they use an efficient approximation to evaluate several explanation methods .
Outcome:	The proposed metric is efficient and can be used on translation tasks.

Copied to clipboard

Yepai Jia, Yatu Ji, Xiang Xue, Shilei@imufe.edu.cn Shilei@imufe.edu.cn, Qing-Dao-Er-Ji Ren, Nier Wu, Na Liu, Chen Zhao, Fu Liu

Improving the Transformer Translation Model with Document-Level Context (D18-1)

Challenge:	Back-translation methods rely on large-scale parallel corpora to enhance performance, but ignore the semantic quality of monolingual data.
Approach:	They propose a method which prioritizes sentences with higher semantic uncertainty as training samples by computationally evaluating the complexity of unannotated monolingual data.
Outcome:	The proposed method improves translation accuracy and fluency by +1.7 on all three translation tasks.

Copied to clipboard

Jiacheng Zhang, Huanbo Luan, Maosong Sun, Feifei Zhai, Jingfang Xu, Min Zhang, Yang Liu

Neural Hidden Markov Model for Machine Translation (P18-2)

Challenge:	Existing models for document-level context translation ignore documentlevel context.
Approach:	They propose a document-level context encoder to represent document- level context and integrate it into the Transformer model.
Outcome:	Experiments on NIST Chinese-English and IWSLT French-English datasets show that the proposed translation model outperforms the Transformer model significantly.

Copied to clipboard

Weiyue Wang, Derui Zhu, Tamer Alkhouli, Zixuan Gan, Hermann Ney

DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms (2024.acl-short)

Challenge:	Attention-based neural machine translation models selectively focus on specific source positions to produce a translation.
Approach:	They propose to replace the attention component with a neural hidden Markov model that selectively focuss on specific source positions to produce a translation.
Outcome:	The proposed model performs better than the state-of-the-art attention-based models on the GermanEnglish and ChineseEnglish translation tasks.

Copied to clipboard

Andong Chen, Lianzhang Lou, Kehai Chen, Xuefeng Bai, Yang Xiang, Muyun Yang, Tiejun Zhao, Min Zhang

Surprisingly Easy Hard-Attention for Sequence to Sequence Learning (D18-1)

Challenge:	Existing self-reflection methods lack effective feedback information, limiting the translation performance of large language models (LLMs).
Approach:	They propose a framework that leverages the dual learning of translation tasks to provide effective feedback, thereby enhancing the models’ self-reflective abilities and improving translation performance.
Outcome:	The proposed framework improves the models’ self-reflective abilities and improves translation accuracy and eliminating ambiguities across translation tasks.

Copied to clipboard

Shiv Shankar, Siddhant Garg, Sunita Sarawagi

Incorporating a Local Translation Mechanism into Non-autoregressive Translation (2020.emnlp-main)

Challenge:	Existing attention mechanisms are hard and hard, but they are more accurate when trained.
Approach:	They propose to use a beam approximation of the joint distribution between attention and output to train sequence to sequence learning.
Outcome:	The proposed method is compared to existing attention mechanisms on five translation tasks and shows consistent gains on the same tasks.

Copied to clipboard

Xiang Kong, Zhisong Zhang, Eduard Hovy

Self-Paced Learning for Neural Machine Translation (2020.emnlp-main)

Challenge:	Existing methods to capture local dependencies among output tokens are not efficient, causing errors of repeated translation.
Approach:	They propose a local autoregressive translation mechanism that predicts a short sequence of tokens for each target decoding position instead of one token.
Outcome:	Empirical results show that the proposed method achieves comparable or better performance with fewer decoding iterations, bringing a 2.5x speedup.

Copied to clipboard

Yu Wan, Baosong Yang, Derek F. Wong, Yikai Zhou, Lidia S. Chao, Haibo Zhang, Boxing Chen

Neural Machine Translation Decoding with Terminology Constraints (N18-2)

Challenge:	Existing studies have shown that the training of neural machine translation (NMT) rely on the quality of artificial schedule drawn up with the handcrafted features, e.g. sentence length or word rarity.
Approach:	They propose to train NMT model using a self-paced learning approach that allows it to quantify the learning confidence over training examples and flexibly govern its learning via regulating the loss in each iteration step.
Outcome:	The proposed model outperforms baseline models and those trained with human-designed curricula on translation quality and convergence speed.

Copied to clipboard

Eva Hasler, Adrià de Gispert, Gonzalo Iglesias, Bill Byrne

Integrating Translation Memories into Non-Autoregressive Machine Translation (2023.eacl-main)

Challenge:	Constrained neural machine translation systems can provide excellent quality but do not strictly enforce terminology.
Approach:	They propose a framework for constrained neural decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans.
Outcome:	The proposed framework performs well on multiple translation tasks and motivates the need for constrained decoding with attentions to reduce misplacement and duplication when translating user constraints.

Copied to clipboard

Jitao Xu, Josep Crego, François Yvon

Combining Character and Word Information in Neural Machine Translation Using a Multi-Level Attention (N18-1)

Challenge:	Non-autoregressive machine translation (NAT) has made great progress, but most studies focus on standard translation tasks.
Approach:	They propose to train an edit-based NAT model with a Translation Memory (TM) they propose to modify the data presentation and introduce an extra deletion operation to reduce decoding load.
Outcome:	The proposed model performs on par with an autoregressive approach while reducing the decoding load.

Copied to clipboard

Huadong Chen, Shujian Huang, David Chiang, Xinyu Dai, Jiajun Chen

CTC Alignments Improve Autoregressive Translation (2023.eacl-main)

Challenge:	Neural machine translation models learn to map from source language sentences to target language sentences via continuous-space intermediate representations.
Approach:	They propose an encoder with character attention which augments the (sub)word-level representation with character-level information and a decoder with multiple attentions that enable the representations from different levels of granularity to control the translation cooperatively.
Outcome:	The proposed model outperforms the standard word-based model, subword-based models, and strong character-based ones on translation tasks.

Copied to clipboard

Brian Yan, Siddharth Dalmia, Yosuke Higuchi, Graham Neubig, Florian Metze, Alan W Black, Shinji Watanabe

Quantifying Appropriateness of Summarization Data for Curriculum Learning (2021.eacl-main)

Challenge:	Connectionist Temporal Classification (CTC) is widely used for automatic speech recognition (ASR) but lags behind attentional decoder approaches in terms of translation quality.
Approach:	They propose to use a CTC/attention framework to validate this hypothesis by modifying the Hybrid CTC-Attention model proposed for automatic speech recognition to support text-to-text translation (MT) and speech-totext translation.
Outcome:	The proposed model outperforms pure-attention baselines across six translation tasks.

Copied to clipboard

Ryuji Kano, Takumi Takahashi, Toru Nishino, Motoki Taniguchi, Tomoki Taniguchi, Tomoko Ohkuma

Information Extraction & Text Mining

Challenge:	Summarization datasets are noisy, and summaries often do not reflect what is written in the source texts.
Approach:	They propose a method of curriculum learning to train summarization models from noisy data.
Outcome:	The proposed method improves the performance of pretrained and non-pretrained models on human evaluation.

Neural Machine Translation for Bilingually Scarce Scenarios: a Deep Multi-Task Learning Approach (N18-1)

Copied to clipboard

Poorya Zaremoodi, Gholamreza Haffari

Target Foresight Based Attention for Neural Machine Translation (N18-1)

Challenge:	Neural machine translation requires large amount of parallel training text to learn a reasonable quality translation model.
Approach:	They propose a multi-task learning approach that leverages monolingual linguistic resources in the source side of a machine translation task.
Outcome:	The proposed approach is effective on three translation tasks: English-to-French, English- to-Farsi, and English-à-Vietnamese.

Copied to clipboard

Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi, Max Meng

Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language (2026.findings-acl)

Challenge:	Empirical experiments on Chinese-to-English and Japanese-to English datasets show that the proposed attention model delivers significant improvements in terms of alignment error rate and BLEU.
Approach:	They propose to explicitly access the target foresight word in the attention model to improve alignment and translation accuracy.
Outcome:	Empirical results show that the proposed model improves alignment error rate and BLEU on Chinese-to-English and Japanese-toEnglish datasets.

Copied to clipboard

Dianqing Lin, Tian Lan, Jiali Zhu, Jiang Li, Wei Chen, Xu Liu, null Aruukhan, Xiangdong Su, Hongxu Hou, Guanglai Gao

Learning Optimal Policy for Simultaneous Machine Translation via Binary Search (2023.acl-long)

Challenge:	Current state-of-the-art LLMs exhibit clear limitations on multiple tasks, while performing well on tasks that involve contextual semantic understanding.
Approach:	They propose a mouse-based benchmark to evaluate LLMs' performance on NLP tasks involving Chouxiang Language.
Outcome:	The proposed benchmark evaluates the performance of LLMs on six NLP tasks involving Chouxiang Language.

Copied to clipboard

SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization (2024.naacl-long)

Challenge:	Simultaneous machine translation model needs a precise translation policy to achieve good latency-quality trade-offs.
Approach:	They propose a method for building the optimal translation policy online via binary search by employing explicit supervision.
Outcome:	Experiments on four translation tasks show that the proposed method exceeds strong baselines across all latency scenarios.

Copied to clipboard

Jacob Parnell, Inigo Jauregi Unanue, Massimo Piccardi

BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation (2022.acl-long)

Challenge:	Existing approaches to cross-lingual summarization are limited due to limited training data.
Approach:	They propose to re-use existing multilingual summarization and translation pipelines to perform cross-lingual summaries in a sequence.
Outcome:	The proposed approach outperforms existing methods in many languages with only 10% of the fine-tuning samples.

Copied to clipboard

Yanling Xiao, Lemao Liu, Guoping Huang, Qu Cui, Shujian Huang, Shuming Shi, Jiajun Chen

A Lightweight Mixture-of-Experts Neural Machine Translation Model with Stage-wise Training Strategy (2024.findings-naacl)

Challenge:	Existing IMT systems relying on lexical constrained decoding (LCD) are limited in translation efficiency and quality due to LCD.
Approach:	They propose a novel interactive neural machine translation system that uses lexical constraints to decode missing words in a manually revised translation.
Outcome:	The proposed system performs significantly better and faster than state-of-the-art IMT on three translation tasks.

Copied to clipboard

Fan Zhang, Mei Tu, Song Liu, Jinyao Yan

Multi-Agent Mutual Learning at Sentence-Level and Token-Level for Neural Machine Translation (2020.findings-emnlp)

Challenge:	Using mixture-of-experts (MoE) to deal with language heterogeneity is a challenge in neural machine translation (NMT).
Approach:	They propose a lightweight MoE-based NMT model that is trained via an elaborate stage-wise training strategy.
Outcome:	The proposed model achieves stable improvements in translation tasks by introducing fewer extra parameters compared to baseline models.

Copied to clipboard

Baohao Liao, Yingbo Gao, Hermann Ney

RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)

Challenge:	Neural machine translation (NMT) has achieved significant progress over recent years.
Approach:	They extend mutual learning to the machine translation task and operate at both the sentence-level and the token-level.
Outcome:	The proposed method improves on the IWSLT’14 German-English task and also on the WMT’14 English-German task.

Copied to clipboard

Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang

Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation (2022.findings-emnlp)

Challenge:	Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks.
Approach:	They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes.
Outcome:	The proposed training framework significantly improves upon translation baselines.

Copied to clipboard

Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization (2025.naacl-long)

Challenge:	Existing methods to perform adaptive and fixed translations lack evaluation before taking actions.
Approach:	They propose a method to perform adaptive translation policy via post-evaluation into fixed policy . their method evaluates rationality of next action by measuring change in source content .
Outcome:	The proposed method exceeds strong baselines under all latency.

Copied to clipboard

Zilu Tang, Rajen Chatterjee, Sarthak Garg

Non-Autoregressive Neural Machine Translation: A Call for Clarity (2022.emnlp-main)

Challenge:	Machine Translation (MT) systems based on fine-tuned large language models (LLMs) are at a higher risk of generating hallucinations, which can severely undermine user’s trust and safety.
Approach:	They propose a method that intrinsically learns to mitigate hallucinations during the model training phase.
Outcome:	The proposed method reduces hallucinations by 89% on an average across three unseen target languages while preserving translation quality.

Copied to clipboard

Robin Schmidt, Telmo Pires, Stephan Peitz, Jonas Lööf

SignAlignLM: Integrating Multimodal Sign Language Processing into Large Language Models (2025.findings-acl)

Challenge:	Non-autoregressive translation models require a single forward pass to generate the output sequence instead of iteratively producing each predicted token.
Approach:	They propose to use a single forward pass to generate the output sequence instead of iteratively producing each predicted token.
Outcome:	The proposed models improve translation quality and speed under third-party testing environments.

Copied to clipboard

Mert Inan, Anthony Sicilia, Malihe Alikhani

Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives (2024.acl-long)

Challenge:	Deaf and Hard-of-Hearing (DHH) users increasingly utilize Large Language Models (LLMs), yet face significant challenges due to these models’ limited understanding of sign language grammar, multimodal sign inputs, and Deafic cultural contexts.
Approach:	They propose to use sign language support in LLMs to integrate sign linguistic rules and conventions into prompting and fine-tuning strategies to address the needs of DHH users.
Outcome:	The proposed model can be generalized interfaces for both spoken and signed languages if trained with a multitasking paradigm.

Copied to clipboard

Wenqi Zhang, Yongliang Shen, Linjuan Wu, Qiuying Peng, Jun Wang, Yueting Zhuang, Weiming Lu

Simultaneous Machine Translation with Tailored Reference (2023.findings-emnlp)

Challenge:	Recent research indicates without external feedback, LLM’s intrinsic reflection is unstable.
Approach:	They propose a method that combines self-evaluated and external feedback to improve LLM's reflection.
Outcome:	The proposed method improves the quality of self-evaluated feedback and can catalyze more accurate and stable reflection.

Copied to clipboard

Uncertainty-Aware Semantic Augmentation for Neural Machine Translation (2020.emnlp-main)

Challenge:	Existing SiMT models are trained using the same reference disregarding the varying amounts of available source information at different latency.
Approach:	They propose a method that provides tailored reference for the SiMT models trained at different latency by rephrasing ground-truth to the tailored reference.
Outcome:	The proposed method achieves state-of-the-art translation performance on three translation tasks.

Copied to clipboard

Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Luxi Xing, Weihua Luo

MQM-Chat: Multidimensional Quality Metrics for Chat Translation (2025.coling-main)

Challenge:	Existing methods for neural machine translation only observe one source sentence at training time . this discrepancy in data distribution leads to a formidable learning challenge .
Approach:	They propose an uncertainty-aware semantic augmentation approach to capture universal semantic information among multiple source sentences and enhance hidden representations with this information.
Outcome:	The proposed approach outperforms baseline and existing methods on translation tasks.

Copied to clipboard

Yunmeng Li, Jun Suzuki, Makoto Morishita, Kaori Abe, Kentaro Inui

Take One Step at a Time to Know Incremental Utility of Demonstration: An Analysis on Reranking for Few-Shot In-Context Learning (2024.naacl-long)

Challenge:	Existing methods for chat translation face challenges due to high levels of ambiguity and stylized contents.
Approach:	They propose a multidimensional quality metric for chat translation that includes seven error types . they use human annotations to analyze chat data generated by five translation models .
Outcome:	The proposed evaluation metric can qualify errors while highlighting chat-specific issues explicitly.

Copied to clipboard

Kazuma Hashimoto, Karthik Raman, Michael Bendersky

Low-Resource NLP

Challenge:	Recent advances of Large Language Models (LLMs) have been pushing the field of Natural Language Processing (NLP) to the next level in many different aspects.
Approach:	They propose a novel labeling method which estimates how much incremental knowledge is brought into LLMs by a demonstration.
Outcome:	The proposed method estimates how much incremental knowledge is brought into the LLMs by a demonstration.

Breaking the Corpus Bottleneck for Context-Aware Neural Machine Translation with Cross-Task Pre-training (2021.acl-long)

Copied to clipboard

Linqing Chen, Junhui Li, Zhengxian Gong, Boxing Chen, Weihua Luo, Min Zhang, Guodong Zhou

Adaptive Weighting for Neural Machine Translation (C18-1)

Challenge:	Context-aware neural machine translation (NMT) remains challenging due to the lack of large-scale document-level parallel corpora.
Approach:	They propose to use large-scale parallel datasets and source-side monolingual documents to improve context-aware neural machine translation.
Outcome:	The proposed model can be used to translate both sentences and documents on four translation tasks.

Copied to clipboard

Yachao Li, Junhui Li, Min Zhang

Recurrent Attention for Neural Machine Translation (2021.emnlp-main)

Challenge:	Existing weighted sum models (WSMs) take inputs and generate one output, but they are independent of each other and are fixed for all inputs.
Approach:	They propose adaptive weighting for WSMs to control the contribution of each input and output state.
Outcome:	The proposed weighting improves translation accuracy by 1.49 and 0.92 BLEU points on Chinese-to-English translation and English-to German translation tasks.

Copied to clipboard

Jiali Zeng, Shuangzhi Wu, Yongjing Yin, Yufan Jiang, Mu Li

Improving Neural Machine Translation by Bidirectional Training (2021.emnlp-main)

Challenge:	Recent research questions the importance of dot-product self-attention in Transformer models and shows that most attention heads learn simple positional patterns.
Approach:	They propose a novel mechanism to replace dot-product self-attention with a recurrent atteNtion mechanism that directly learns attention weights without token-to-token interaction.
Outcome:	The proposed model outperforms the Transformer model on translation tasks with fewer parameters and inference time.

Copied to clipboard

Liang Ding, Di Wu, Dacheng Tao

From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models (2026.acl-long)

Challenge:	Experimental results show that bidirectional training pushes the SOTA neural machine translation performance significantly higher.
Approach:	They propose a bidirectional training strategy that updates model parameters at the early stage and tunes it normally.
Outcome:	The proposed approach pushes the SOTA neural machine translation performance significantly higher on 15 translation tasks on 8 language pairs.

Copied to clipboard

Ling Shi, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Yangyang Liu, Linlong Xu, Longyue Wang, Deyi Xiong, Weihua Luo

Responsible & Trustworthy NLP

Challenge:	Recent research in mechanistic interpretability has revealed that Large Language models contain disentangled, human-understandable components.
Approach:	They propose a framework that first identifies causal task features through frequency recall and interventional filtering, then selects “Feature-Resonant Data” that maximally activates task features for fine-tuning.
Outcome:	The proposed framework outperforms existing models on mathematical reasoning, summarization, and translation tasks while using only 50% of the data.

Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation (P19-1)

Copied to clipboard

Chenze Shao, Yang Feng, Jinchao Zhang, Fandong Meng, Xilin Chen, Jie Zhou

Look Harder: A Neural Machine Translation Model with Hard Attention (P19-1)

Challenge:	Experimental results show that the Reinforce-NAT system surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed.
Approach:	They propose a sequence-level training method and a Transformer decoder to fuse the target sequential information into the top layer of the decoded Transformer.
Outcome:	The proposed model surpasses the baseline NAT system on BLEU without decelerating the decoding speed and achieves comparable translation performance to the autoregressive Transformer model with considerable speedup.

Copied to clipboard

Sathish Reddy Indurthi, Insoo Chung, Sangha Kim

Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios (2021.naacl-main)

Challenge:	Soft-attention based Neural Machine Translation models attend all the words in the source sequence for each target token, which makes them ineffective for long sequence translation.
Approach:	They propose a hard-attention based NMT model which selects a subset of source tokens for each target token to effectively handle long sequence translation.
Outcome:	The proposed model performs better on long sequences and achieves significant improvement on English-German and English-French translation tasks compared to soft-attention based models.

Copied to clipboard

Haipeng Sun, Rui Wang, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translation (2022.emnlp-main)

Challenge:	Existing methods that use monolingual corpora for translation are not suitable for low-resource languages such as Estonian.
Approach:	They propose unsupervised neural machine translation (UNMT) that relies on monolingual corpora to train a robust UNMT system and improve its performance.
Outcome:	The proposed methods outperform conventional UNMT systems on several language pairs.

Copied to clipboard

Huanran Zheng, Wei Zhu, Pengfei Wang, Xiaoling Wang

Competency-Aware Neural Machine Translation: Can Machine Translation Know its Own Translation Quality? (2022.emnlp-main)

Challenge:	Existing methods to improve NAT model's performance but do not fully utilize it.
Approach:	They propose a non-autoregressive translation method which can obtain high-quality translations while maintaining the inference speed of NAT models.
Outcome:	The proposed method outperforms the autoregressive translation model on three translation tasks with 7.6 speedup.

Copied to clipboard

Pei Zhang, Baosong Yang, Hao-Ran Wei, Dayiheng Liu, Kai Fan, Luo Si, Jun Xie

Hybrid-Regressive Paradigm for Accurate and Speed-Robust Neural Machine Translation (2023.findings-acl)

Challenge:	Neural machine translation models are often criticized for failures that happen without competency awareness.
Approach:	They propose a method that extends conventional NMT with a self-estimator to translate a source sentence and estimate its competency.
Outcome:	The proposed method performs on translation tasks intact and on quality estimation tasks better than existing methods.

Copied to clipboard

Qiang Wang, Xinhui Hu, Ming Chen

Robustness in NLP

Challenge:	Autoregressive translation (NAT) is less robust in decoding batch size and hardware settings than NAT.
Approach:	They propose a two-stage translation prototype that prompts a small number of AT predictions and fills in previously skipped tokens at once.
Outcome:	The proposed translation prototype achieves comparable translation quality with AT while having 1.5x faster inference speed regardless of batch size and device.

Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training (2020.coling-main)

Copied to clipboard

Haipeng Sun, Rui Wang, Kehai Chen, Xugang Lu, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao

Responsible & Trustworthy NLP

Challenge:	Unsupervised neural machine translation (UNMT) has attracted great interest in the machine translation community.
Approach:	They propose to explicitly take noisy data into consideration to improve the robustness of UNMT based systems.
Outcome:	The proposed methods significantly improved the robustness of the conventional UNMT systems in noisy scenarios.

Improving Low-Resource NMT through Relevance Based Linguistic Features Incorporation (2020.coling-main)

Copied to clipboard

Abhisek Chakrabarty, Raj Dabre, Chenchen Ding, Masao Utiyama, Eiichiro Sumita

Layer-Wise Multi-View Learning for Neural Machine Translation (2020.coling-main)

Challenge:	Existing studies on incorporating arbitrary syntactic information into neural machine translation (NMT) are lacking.
Approach:	They propose to integrate linguistic knowledge at different levels into neural machine translation framework to improve translation quality for language pairs with extremely limited data.
Outcome:	The proposed methods improve translation quality for all tasks by 3.09 BLEU points . the proposed methods are based on two different approaches .

Copied to clipboard

Qiang Wang, Changliang Li, Yue Zhang, Tong Xiao, Jingbo Zhu

T-Modules: Translation Modules for Zero-Shot Cross-Modal Machine Translation (2022.emnlp-main)

Challenge:	Existing approaches to neural machine translation are limited to the topmost encoder layer’s context representation and cannot perceive the lower encoder layers.
Approach:	They propose a layer-wise multi-view learning approach to solve this problem by incorporating an auxiliary view into the model.
Outcome:	The proposed model can achieve stable results over multiple strong baselines and is agnostic to network architectures.

Copied to clipboard

Paul-Ambroise Duquenne, Hongyu Gong, Benoît Sagot, Holger Schwenk

Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity (2020.coling-main)

Challenge:	Existing approaches to perform zero-shot cross-modal transfer between speech and text are limited to a very small number of language pairs.
Approach:	They propose a method to perform zero-shot cross-modal transfer between speech and text for translation tasks by using a speech decoder.
Outcome:	The proposed model significantly improves state-of-the-art for zero-shot speech translation on Must-C.

Copied to clipboard

Yang Zhao, Lu Xiang, Junnan Zhu, Jiajun Zhang, Yu Zhou, Chengqing Zong

How to Learn in a Noisy World? Self-Correcting the Real-World Data Noise in Machine Translation (2025.findings-naacl)

Challenge:	Existing methods to integrate knowledge graph (KG) with neural machine translation (NMT) have two problems: knowledge under-utilization and granularity mismatch.
Approach:	They propose a multi-task learning method on sub-entity granularity to combine machine translation and knowledge reasoning tasks.
Outcome:	The proposed method significantly outperforms baseline models on translation tasks and handling the entities.

Copied to clipboard

Yan Meng, Di Wu, Christof Monz

MSP: Multi-Stage Prompting for Making Pre-trained Language Models Better Translators (2022.acl-long)

Challenge:	Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems.
Approach:	They propose a process for simulating misalignment controlled by semantic similarity which closely resembles misaligned sentences in real-world web-crawled corpora.
Outcome:	The proposed model significantly improves translation performance in the presence of misalignment noise and when applied to real-world, noisy web-mined datasets, across a range of translation tasks.

Copied to clipboard

Zhixing Tan, Xiangwen Zhang, Shuo Wang, Yang Liu

PartialFormer: Modeling Part Instead of Whole for Machine Translation (2024.findings-acl)

Challenge:	Prompting has been shown to be a promising approach for applying pre-trained language models to perform downstream tasks.
Approach:	They propose a method that divides the translation process into three stages using pre-trained language models.
Outcome:	The proposed method significantly improves translation performance of pre-trained language models on three translation tasks.

Copied to clipboard

Tong Zheng, Bei Li, Huiwen Bao, Jiale Wang, Weiqiao Shan, Tong Xiao, JingBo Zhu

Machine Translation With Weakly Paired Documents (D19-1)

Challenge:	Existing feed-forward neural networks have significant computational and parametric overhead.
Approach:	They propose a parameter-efficient Transformer architecture that utilizes multiple smaller FFNs to reduce parameters and computation while maintaining essential hidden dimensions.
Outcome:	The proposed architecture reduces computational and parameter overhead while maintaining essential hidden dimensions.

Copied to clipboard

Lijun Wu, Jinhua Zhu, Di He, Fei Gao, Tao Qin, Jianhuang Lai, Tie-Yan Liu

Noise-robust Cross-modal Interactive Learning with Text2Image Mask for Multi-modal Neural Machine Translation (2022.coling-1)

Challenge:	Recent studies explore the possibility of unsupervised machine translation with monolingual data only.
Approach:	They propose a method to mine bilingual sentences from weakly paired documents . they use word distribution-level alignments to constrain word distributions of two weakly-paired documents.
Outcome:	The proposed method outperforms previous results on six translation tasks using weakly paired bilingual documents and a large number of bilingual sentences.

Copied to clipboard

Junjie Ye, Junjun Guo, Yan Xiang, Kaiwen Tan, Zhengtao Yu

Responsible & Trustworthy NLP

Challenge:	Existing studies on multi-modal neural machine translation focus on visual information, but text and image may not match exactly, and visual noise is often ignored.
Approach:	They propose a noise-robust multi-modal interactive fusion approach with cross-modal relation-aware mask mechanism for MNMT.
Outcome:	The proposed model achieves state-of-the-art scores in all En-De, En-Fr and En-Cs translation tasks.

Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering (2022.coling-1)

Copied to clipboard

Qian Wang, Jiajun Zhang

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Transfer in Large Language Models (2025.naacl-long)

Challenge:	Existing clustering methods cannot handle asymmetric problem in multilingual NMT . existing models cannot handle the asymmetry problem since there are thousands of languages involved .
Approach:	They propose a fuzzy task clustering method to address the asymmetric problem in multilingual NMT by using task affinity as the clustering criterion.
Outcome:	The proposed method outperforms baselines for a multilingual model and the existing models.

Copied to clipboard

Fei Yuan, Chang Ma, Shuai Yuan, Qiushi Sun, Lei Li

Literary Machine Translation under the Magnifying Glass: Assessing the Quality of an NMT-Translated Detective Novel on Document Level (2020.lrec-1)

Challenge:	Existing studies have shown that a small subset of parameters is highly effective in fine-tuning . prior work shows that there are a few additional parameters corresponding to an intrinsic dimension in a well-trained Large Language Model.
Approach:	They propose a method to identify a small subset of LLM parameters highly effective in multilingual fine-tuning.
Outcome:	The proposed method can find the certified winning tickets in the embedding layer, and fine-tuning on the found parameters is guaranteed to perform as well as full fine- tuning.

Copied to clipboard

Margot Fonteyne, Arda Tezcan, Lieve Macken

Exploring Methods for Building Dialects-Mandarin Code-Mixing Corpora: A Case Study in Taiwanese Hokkien (2022.findings-emnlp)

Challenge:	Several studies have demonstrated that translation quality has improved enormously since the emergence of neural machine translation systems.
Approach:	They performed a document-level evaluation of the raw NMT output of an entire novel and annotated it in two steps: first all fluency errors, then all accuracy errors.
Outcome:	The results show that translation quality has improved enormously since the emergence of neural machine translation systems.

Copied to clipboard

Sin-En Lu, Bo-Han Lu, Chao-Yi Lu, Richard Tzong-Han Tsai

Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation (2022.emnlp-main)

Challenge:	CM is a challenging task when mixed languages include dialects.
Approach:	They propose to construct a Hokkien-Mandarin CM dataset to overcome the limitation . they propose to use a linguistics-based toolkit to train the model for translation tasks .
Outcome:	The proposed model achieves good results on CM data translation while maintaining monolingual translation quality.

Copied to clipboard

Sunzhu Li, Peng Zhang, Guobing Gan, Xiuqing Lv, Benyou Wang, Junqiu Wei, Xin Jiang

Decoder-only Streaming Transformer for Simultaneous Translation (2024.acl-long)

Challenge:	Existing methods to compress Transformer are limited to sub-components, e.g., selfattention networks or embedding layer.
Approach:	They propose a Hybrid Tensor-Train decomposition which retains full rank and meanwhile reduces operations and parameters.
Outcome:	The proposed model outperforms light-weight SOTA methods on three translation tasks and achieves 7.1 points absolute improvement in BLEU and 1.27 X speedup on IWSLT’14 De-En task.

Copied to clipboard

Deterministic Reversible Data Augmentation for Neural Machine Translation (2024.findings-acl)

Challenge:	Existing methods for siMT focus on the Encoder-Decoder architecture, but there are limitations in training and inference.
Approach:	They propose a model that generates translation while reading source tokens . they propose Streaming Self-Attention mechanism tailored for the Decoder-only architecture .
Outcome:	The proposed model achieves state-of-the-art performance on three translation tasks.

Copied to clipboard

Jiashu Yao, Heyan Huang, Zeming Liu, Yuhang Guo

Dynamic Stashing Quantization for Efficient Transformer Training (2023.findings-emnlp)

Challenge:	Recent neural machine translation models have improved translation quality but they also introduce small perturbations like misspelling and paraphrasing.
Approach:	They propose a method that generates multi-granularity subword representations with reversible operations and deterministic segmentations.
Outcome:	The proposed method outperforms strong baselines on several translation tasks with a clear margin and exhibits good robustness in noisy, low-resource, and cross-domain datasets.

Copied to clipboard

Guo Yang, Daniel Lo, Robert Mullins, Yiren Zhao

Cross-lingual neural fuzzy matching for exploiting target-language monolingual corpora in computer-aided translation (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks.
Approach:	They propose a dynamic quantization strategy that reduces the amount of memory operations and reduces arithmetic cost by 20.95 on two translation tasks and three classification tasks.
Outcome:	The proposed model reduces the amount of arithmetic operations by 20.95 and the number of DRAM operations by 2.55 on two translation tasks and three classification tasks.

Copied to clipboard

Miquel Esplà-Gomis, Víctor M. Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez

MT2: Towards a Multi-Task Machine Translation Model with Translation-Specific In-Context Learning (2023.emnlp-main)

Challenge:	CAT tools based on translation memories (TMs) are limited in their use for a number of translation tasks due to the limited availability of in-domain TMs.
Approach:	They propose a neural approach to exploit in-domain TMs and in-target-language (TL) monolingual corpora to exploit CAT tools.
Outcome:	The proposed approach exploits in-domain TMs and in-target-language (TL) monolingual corpora and increases translation proposals on four language pairs.

Copied to clipboard

Chunyou Li, Mingtong Liu, Hongxiao Zhang, Yufeng Chen, Jinan Xu, Ming Zhou

Low-Resource NLP

Challenge:	Sentence-level translation, document-level and terminology constrained translations are important in machine translation.
Approach:	They propose a multi-task machine translation model that integrates translation memory sentences . they propose 'in-context learning' paradigm that allows translation-specific context learning .
Outcome:	The proposed model improves translation memory, document-level translation, and document-constrained translation tasks.

Enhancing Taiwanese Hokkien Dual Translation by Exploring and Standardizing of Four Writing Systems (2024.lrec-main)

Copied to clipboard

Bo-Han Lu, Yi-Hsuan Lin, Annie Lee, Richard Tzong-Han Tsai

Enhancing Translation Ability of Large Language Models by Leveraging Task-Related Layers (2024.lrec-main)

Challenge:	Currently, machine translation systems cater to high-resource languages (HRLs), while low-resourced languages (LRLs) like Taiwanese Hokkien are relatively under-explored.
Approach:	They propose to use a pre-trained LLaMA 2-7B model specialized in Traditional Mandarin Chinese to leverage orthographic similarities between Taiwanese Hokkien Han and Traditional Mandarin China.
Outcome:	The proposed model bridges the gap between Taiwanese Hokkien and other low-resource languages by using a pre-trained LLaMA 2-7B model and a monolingual corpus.

Copied to clipboard

Pei Cheng, Xiayang Shi, Yinlin Li

Improving NMT Models by Retrofitting Quality Estimators into Trainable Energy Loss (2025.coling-main)

Challenge:	Experimental validation shows that adjusting task-related layers significantly improves performance on translation tasks while maintaining stability and accuracy on other tasks.
Approach:	They propose to adjust task-related layers in large models to better harness their machine translation capabilities by revealing the structure and characteristics of attention weights through singular value decomposition.
Outcome:	The proposed method reduces computational resource consumption and catastrophic forgetting while maintaining stability and accuracy on other tasks.

Copied to clipboard

Gahyun Yoo, Jay Yoon Lee

Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization (D19-1)

Challenge:	Reinforcement learning has shown great promise in aligning language models with human preferences in a variety of text generation tasks, including machine translation.
Approach:	They propose a method that employs quality estimators as trainable loss networks to backpropagate to the NMT model.
Outcome:	The proposed method outperforms strong baselines and proximal policy optimizations on English-to-Mongolian translation.

Copied to clipboard

Guanlin Li, Lemao Liu, Guoping Huang, Conghui Zhu, Tiejun Zhao

On the Off-Target Problem of Zero-Shot Multilingual Neural Machine Translation (2023.findings-acl)

Challenge:	Existing studies measure the superiority of DA methods in terms of their performance on a specific test set, but some do not exhibit consistent improvements across translation tasks.
Approach:	They propose to evaluate DA methods from two perspectives to determine their generalization ability . they find that DA method's test performance does not exhibit consistent improvements across translation tasks .
Outcome:	The proposed methods do not exhibit consistent improvements across translation tasks.

Copied to clipboard

Liang Chen, Shuming Ma, Dongdong Zhang, Furu Wei, Baobao Chang

Uncertainty-Aware Curriculum Learning for Neural Machine Translation (2020.acl-main)

Challenge:	Despite its success, multilingual neural machine translation suffers from the off-target issue, where the translation is in the wrong language.
Approach:	They propose a language-aware vocabulary sharing algorithm that can be used to increase the lexical distance between languages by isolating the vocab of different languages in the decoder.
Outcome:	The proposed algorithm reduces off-target rate for 90 translation tasks from 29% to 8%, while improving overall BLEU score by an average of 1.9 points without extra training cost or sacrificing the supervised directions’ performance.

Copied to clipboard

Yikai Zhou, Baosong Yang, Derek F. Wong, Yu Wan, Lidia S. Chao

Simple and Effective Input Reformulations for Translation (2023.emnlp-main)

Challenge:	Neural machine translation (NMT) has proven to be facilitated by curriculum learning which presents examples in an easy-to-hard order at different training stages.
Approach:	They propose to use an uncertainty-aware curriculum learning approach to assess data difficulty and model competence to provide examples in an easy-to-hard order at different training stages.
Outcome:	The proposed approach outperforms baseline and related methods on translation quality and convergence speed.

Copied to clipboard

Brian Yu, Hansen Lillemark, Kurt Keutzer

wav2vec-S: Adapting Pre-trained Speech Models for Streaming (2024.findings-acl)

Challenge:	Foundation language models learn from their finetuning input context in different ways.
Approach:	They propose three different data efficient techniques to improve translation performance . they reformulate inputs during finetuning for challenging translation tasks .
Outcome:	The proposed techniques show significant improvements on the Flores200 translation benchmark.

Copied to clipboard

Biao Fu, Kai Fan, Minpeng Liao, Yidong Chen, Xiaodong Shi, Zhongqiang Huang

BranchNorm: Robustly Scaling Extremely Deep Transformers (2024.findings-acl)

Challenge:	Pre-trained speech models have advanced speech-related tasks, including speech recognition and translation.
Approach:	They propose a pre-trained speech model that incorporates modifications to ensure consistent speech representations during training and inference phases for streaming speech inputs.
Outcome:	The proposed model outperforms baseline models on speech recognition and translation tasks and achieves a superior balance between quality and latency.

Copied to clipboard

Yijin Liu, Xianfeng Zeng, Fandong Meng, Jie Zhou

Robustness in NLP

Challenge:	Recent work on DeepNorm scales Transformers into extremely deep (1000 layers) due to the training instability of Transformers, the depths of these SOTA models are still relatively shallow.
Approach:	They propose a branch-rescaled model which dynamically rescales the non-residual branch of Transformer in accordance with the training period.
Outcome:	The proposed approach significantly outperforms existing shallow models on multiple translation tasks and achieves better training stability and convergent performance.

XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception (2024.acl-long)

Copied to clipboard

HyoJung Han, Mohamed Anwar, Juan Pino, Wei-Ning Hsu, Marine Carpuat, Bowen Shi, Changhan Wang

Multimodality

Challenge:	Speech recognition and translation systems perform poorly on noisy inputs, which are frequent in realistic environments.
Approach:	They propose a cross-lingual audio-visual speech representation model for noise-robust speech recognition and translation in over 100 languages.
Outcome:	The proposed model outperforms the previous state-of-the-art by 18.5% WER and 4.7 BLEU on downstream audio-visual speech recognition and translation tasks.

DiffS2UT: A Semantic Preserving Diffusion Model for Textless Direct Speech-to-Speech Translation (2023.emnlp-main)

Copied to clipboard

Yongxin Zhu, Zhujin Gao, Xinyuan Zhou, Ye Zhongyi, Linli Xu

Multimodality

Challenge:	Existing models for speech generation are not efficient due to low information density of speech data.
Approach:	They propose a method to integrate discrete diffusion models into speech generation tasks . they propose to apply diffusion forward process while employing diffusion backward process .
Outcome:	The proposed model achieves comparable results to the auto-regressive baselines with significantly fewer decoding steps (50 steps).

Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation Refinement (2025.acl-long)

Copied to clipboard

Yichen Dong, Xinglin Lyu, Junhui Li, Daimeng Wei, Min Zhang, Shimin Tao, Hao Yang

Continual Learning for Multilingual Neural Machine Translation via Dual Importance-based Model Division (2023.emnlp-main)

Challenge:	Recent research has shown that large language models (LLMs) can enhance translation quality through self-refinement.
Approach:	They propose to extend translation refinement from sentence-level to document-level by using document-to-document (Doc2Doc) translations.
Outcome:	The proposed method improves translation quality across ten translation tasks with LLaMA-3-8B-Instruct and Mistral-Nemo-Instru.

Copied to clipboard

Junpeng Liu, Kaiyu Huang, Hao Yu, Jiuyi Li, Jinsong Su, Degen Huang

CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Challenge:	Existing methods focus on preventing catastrophic forgetting by making compromises between the original and new language pairs, leading to sub-optimal performance on both translation tasks.
Approach:	They propose a dual importance-based model division method to divide the model parameters into two parts and separate the translation of the original and new tasks.
Outcome:	The proposed method outperforms strong baselines under different incremental translation scenarios.

Copied to clipboard

Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu

LLM-based Translation Inference with Iterative Bilingual Understanding (2025.findings-acl)

Challenge:	End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach:	They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome:	The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.

Copied to clipboard

Andong Chen, Kehai Chen, Yang Xiang, Xuefeng Bai, Muyun Yang, Yang Feng, Tiejun Zhao, Min Zhang

INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation (2023.acl-long)

Challenge:	Existing studies show that the ability of large language models to generate contextual understanding of the sentence can degrade translation quality.
Approach:	They propose a method that generates contextual understanding for both source and target languages separately.
Outcome:	The proposed method outperforms strong comparison methods in multiple domains.

Copied to clipboard

Wenhao Zhu, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen

Women, Infamous, and Exotic Beings: A Comparative Study of Honorific Usages in Wikipedia and LLMs for Bengali and Hindi (2025.emnlp-main)

Challenge:	Neural machine translation models induce a non-smooth representation space, which harms its generalization results.
Approach:	They propose a framework to smooth the representation space by adjusting neighbor representations with a small number of new parameters.
Outcome:	The proposed framework outperforms the state-of-the-art kNN-MT system with average gains of 1.99 COMET and 1.0 BLEU on four benchmark datasets.

Copied to clipboard

Sourabrata Mukherjee, Atharva Mehta, Sougata Saha, Akhil Arora, Monojit Choudhury

Challenge:	Honorifics encode nuanced socio-pragmatic cues such as power, age, gender, fame, and cultural distance.
Approach:	They propose to study third-person honorific usage across 10,000 Hindi and Bengali Wikipedia articles . honorifics are more prevalent in Bengali than in Hindi, while non-honorifics dominate .
Outcome:	The authors show that large language models internalize similar socio-pragmatic norms . their analysis shows that honorifics are more prevalent in Bengali than in Hindi .

MoNMT: Modularly Leveraging Monolingual and Bilingual Knowledge for Neural Machine Translation (2024.lrec-main)

Copied to clipboard

Jianhui Pang, Baosong Yang, Derek F. Wong, Dayiheng Liu, Xiangpeng Wei, Jun Xie, Lidia S. Chao

ETHICA-MT: Introducing a Framework and Dataset for Studying Ethical Orientations in LLM-based Machine Translation (2026.findings-acl)

Challenge:	Existing models for multi-domain translation tasks only use monolingual data, whereas bilingual data is indispensable for improving the models.
Approach:	They propose a modular strategy that facilitates the cooperation of monolingual and bilingual knowledge in translation tasks by avoiding catastrophic forgetting.
Outcome:	The proposed model exhibits superior generalization and robustness over the conventional approach.

Copied to clipboard

Omri Asscher, Arif Ahmad, Ananya Agrawal, Monojit Choudhury

Inductive Linguistic Reasoning with Large Language Models (2025.findings-acl)

Challenge:	Existing models for translation have not been systematically examined for their default ethical tendencies or their ability to employ and prioritize specified ethical approaches in conflicted translation situations.
Approach:	They propose a framework for examining ethical reasoning and implementation in large language models (LLMs) that systematically examines default ethical tendencies and their ability to employ and prioritize specified ethical approaches in conflicted translation situations.
Outcome:	The proposed framework examines the ethical reasoning and implementation of large language models in translation tasks.

Copied to clipboard

Raghav Ramji, Keshav Ramji

When Life Gives You Samples: The Benefits of Scaling up Inference Compute for Multilingual LLMs (2025.emnlp-main)

Challenge:	Evaluating large language models (LLMs) on their linguistic reasoning capabilities is an important task to understand the gaps in their skills that may surface during large-scale adoption.
Approach:	They propose to generate analogical exemplars with a language model and apply them in-context with target language exemplar.
Outcome:	The proposed method can be applied to other tasks present in Linguistics Olympiad competitions and achieves state-of-the-art results across nearly all problem types and difficulty levels in the LINGOLY dataset.

Copied to clipboard

Ammar Khairi, Daniel D’souza, Ye Shen, Julia Kreutzer, Sara Hooker

ConsistencyChecker: Tree-based Evaluation of LLM Generalization Capabilities (2025.acl-long)

Challenge:	Recent advances in large language models have shifted focus toward scaling inference-time compute.
Approach:	They propose to scale inference-time compute in a multilingual, multi-task setting . they propose to use m-ArenaHard-v2.0 prompts to sample multiple outputs in parallel .
Outcome:	The proposed solutions achieve an average +6.8 jump in win-rates for 8B models on m-ArenaHard-v2.0 prompts in non-English languages against proprietary models like Gemini.

Copied to clipboard

Zhaochen Hong, Haofei Yu, Jiaxuan You

Case-Based Decision-Theoretic Decoding with Quality Memories (2025.emnlp-main)

Challenge:	Traditional self-consistency methods fail to capture subtle semantic errors in multi-step tasks.
Approach:	They propose a tree-based evaluation framework that measures LLMs’ ability to preserve semantic consistency during reversible transformations.
Outcome:	The proposed framework measures generalization abilities across models from 1.5B to 72B and can be used to benchmark LLMs without constructing new datasets.

Copied to clipboard

Hiroyuki Deguchi, Masaaki Nagata

Context-Driven and Reference-Guided Data Augmentation for Subtitle Translation (2026.findings-acl)

Challenge:	Minimum Bayes risk (MBR) decoding is a decision rule of text generation . however, it depends on sample texts drawn from the text generation model .
Approach:	They propose a case-based decision-theoretic method to estimate the expected utility using examples of domain data.
Outcome:	The proposed method outperforms MAP decoding in translation tasks and image captioning tasks on MSCOCO and nocaps datasets.

Copied to clipboard

Hitoshi Ito, Naoto Shirai, Kazutaka Kinugawa, Hideya Mino, Rei Endo, Yoshihiko Kawai