Papers by Xiaoyu Shen

NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation (D18-1)

Challenge:	Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought prompting.
Approach:	They examine the factors influencing CoT distillation including granularity, format and teacher model.
Outcome:	The proposed model is based on four teacher models and seven student models across seven mathematical and commonsense reasoning datasets.

Copied to clipboard

Xiaoyu Shen, Hui Su, Wenjie Li, Dietrich Klakow

Dialogue Systems & Conversational Agents

Challenge:	Sequence-to-Sequence models favor short generic responses . however, the model is not suitable for modeling dialogues .
Approach:	They propose a model that connects preceding and following conversations to a prior distribution to avoid non-differentiability of discrete natural language tokens.
Outcome:	The proposed model is highly efficient in learning the backbone of human-computer communications, but favors short generic responses.

Improving Multi-turn Dialogue Modelling with Utterance ReWriter (P19-1)

Copied to clipboard

Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, Jie Zhou

Paraphrasing

Challenge:	Recent research has achieved impressive results in single-turn dialogue modelling, but multi-turn models still remain challenging.
Approach:	They propose to rewrite human utterances as a pre-process to help multi-turn dialgoue modelling.
Outcome:	The proposed architecture achieves remarkably good performance on the utterance rewriting task.

VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs (2025.emnlp-main)

Copied to clipboard

Yingqi Fan, Anhao Zhao, Jinlan Fu, Junlong Tong, Hui Su, Yijie Pan, Wei Zhang, Xiaoyu Shen

Multimodality

Challenge:	Multimodal Large Language Models (MLLMs) suffer from significant computational overhead due to the quadratic growth of attention computations with the number of multimodal tokens.
Approach:	They propose a training-free pruning framework that prunes multimodal tokens without a trained pruning method.
Outcome:	The proposed pruning framework outperforms existing token pruning methods and generalizes across diverse MLLMs.

Weaker Than You Think: A Critical Look at Weakly Supervised Learning (2023.acl-long)

Copied to clipboard

Dawei Zhu, Xiaoyu Shen, Marius Mosbach, Andreas Stephan, Dietrich Klakow

A Preference-driven Paradigm for Enhanced Translation with Large Language Models (2024.naacl-long)

Challenge:	Weakly supervised learning is a popular approach for training machine learning models in low-resource settings.
Approach:	They propose to use weakly supervised learning to train models with noisy labels from weak sources instead of collecting expensive human annotations.
Outcome:	The proposed methods outperform weakly supervised methods on various NLP datasets and tasks on the test sets.

Copied to clipboard

Dawei Zhu, Sony Trenous, Xiaoyu Shen, Dietrich Klakow, Bill Byrne, Eva Hasler

On Training Instance Selection for Few-Shot Neural Text Generation (2021.acl-short)

Challenge:	Recent research shows that large language models (LLMs) can achieve remarkable translation performance through supervised fine-tuning (SFT) however, SFT simply instructs the model to imitate reference translations token by token, making it vulnerable to the noise present in the data.
Approach:	They propose a preference-based approach to supervised fine-tuning that trains the model to imitate reference translations token by token, making it vulnerable to noise.
Outcome:	The proposed approach overcomes the plateau associated with imitation-based SFT and is more resilient in the absence of gold translations.

Copied to clipboard

Ernie Chang, Xiaoyu Shen, Hui-Syuan Yeh, Vera Demberg

Meta Self-Refinement for Robust Learning with Weak Supervision (2023.eacl-main)

Challenge:	Pretraining large neural networks with a language modeling objective has led to dramatic improvements in text generation.
Approach:	They propose a selection strategy to select few-shot training instances based on unlabeled data to identify the most worthwhile data points that should be annotated under some budget of labeling cost.
Outcome:	The proposed strategy outperforms random sampling on three text generation tasks.

Copied to clipboard

Dawei Zhu, Xiaoyu Shen, Michael Hedderich, Dietrich Klakow

Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence (2020.acl-main)

Challenge:	Recent methods leverage self-training to build noise-resistant models . however, the teacher trained under weak supervision may have fitted a substantial amount of noise and therefore produce incorrect pseudo-labels.
Approach:	They propose a framework that encourages teacher to refine its pseudo-labels to effectively combat label noise from weak supervision.
Outcome:	The proposed framework outperforms state-of-the-art methods by 11.4% in accuracy and 9.26% in F1 score on eight NLP benchmarks.

Copied to clipboard

Xiaoyu Shen, Ernie Chang, Hui Su, Cheng Niu, Dietrich Klakow

Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant (2025.findings-emnlp)

Challenge:	Recent neural attention models conflate all steps into a single end-to-end system and simplify training process.
Approach:	They propose to explicitly segment target text into fragment units and align them with their data correspondences.
Outcome:	The proposed model outperforms neural attention models on E2E and WebNLG benchmarks.

Copied to clipboard

Lei Shen, Xiaoyu Shen

Challenge:	Auto-SLURP is a benchmark dataset for evaluating multi-agent frameworks powered by large language models.
Approach:	Auto-SLURP is a benchmark dataset aimed at evaluating LLM-based multi-agent frameworks . authors propose it extends original SLURP dataset by relabeling data and integrating simulated servers and external services.
Outcome:	The proposed dataset extends the original SLURP dataset for natural language understanding tasks.

DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool (2020.coling-demos)

Copied to clipboard

Ernie Chang, Jeriah Caplinger, Alex Marin, Xiaoyu Shen, Vera Demberg

Structured Data in NLP

Challenge:	Neural data-to-text generation systems require large-scale labeled data to generate sentences.
Approach:	They propose to create an interactive annotation tool that iteratively analyzes annotated structured data to better sample unlabeled data.
Outcome:	The proposed tool reduces the number of annotations needed with active learning and automatically suggests relevant labels.

Logical Fallacy Detection (2022.findings-emnlp)

Copied to clipboard

Zhijing Jin, Abhinav Lalwani, Tejas Vaidhya, Xiaoyu Shen, Yiwen Ding, Zhiheng Lyu, Mrinmaya Sachan, Rada Mihalcea, Bernhard Schoelkopf

Data Augmentation for Multiclass Utterance Classification – A Systematic Study (2020.coling-main)

Challenge:	Existing language models perform poorly on logical fallacy detection . fallacious arguments can lead to disagreements, conflicts, endless debates, and a lack of consensus .
Approach:	They propose a task of logical fallacy detection and propose LogicClimate to detect fallacies in text.
Outcome:	The proposed task outperforms the best language model on Logic and LogicClimate . human reasoning is marred by logical fallacies, and some exacerbate misinformation .

Copied to clipboard

Binxia Xu, Siyuan Qiu, Jie Zhang, Yafang Wang, Xiaoyu Shen, Gerard de Melo

Information Extraction & Text Mining

Challenge:	a lack of sufficient training data for some categories can cause imbalanced data distributions . a weak classifier may miscategorize a request, resulting in customer dissatisfaction .
Approach:	They propose to use random resampling, word-level transformations and neural text generation to augment existing data to cope with imbalanced data.
Outcome:	The proposed methods improve utterance classification results by drawing on utterant variation.

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

Reasoning

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models (2026.acl-long)

Copied to clipboard

Weipeng Jiang, Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Yang Liu

Select and Attend: Towards Controllable Content Selection in Text Generation (D19-1)

Challenge:	Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs) remain largely unexplored.
Approach:	They propose to use ASCII-based emoticons to perform unintended actions in large language models (LLMs) This vulnerability is pervasive, with an average confusion ratio exceeding 38%, and 90% of confused responses yield 'silent failures' authors call on the community to recognize this emerging vulnerability and develop effective mitigation methods to uphold the safety and reliability of human-LLM interactions.
Outcome:	The proposed framework exploits emoticon semantic confusion in six LLMs and demonstrates that existing prompt-based mitigations are ineffective.

Copied to clipboard

Xiaoyu Shen, Jun Suzuki, Kentaro Inui, Hui Su, Dietrich Klakow, Satoshi Sekine

MovieChats: Chat like Humans in a Closed Domain (2020.emnlp-main)

Challenge:	Recent neural network models conflate content selection and surface realization into a black-box architecture, resulting in content to be described in text cannot be explicitly controlled.
Approach:	They propose to decouple content selection from the decoder to allow finer-grained control over the generation.
Outcome:	The proposed model can be trained end-to-end without human annotations and achieves promising results in data-totext and headline generation tasks.

Copied to clipboard

Hui Su, Xiaoyu Shen, Zhou Xiao, Zheng Zhang, Ernie Chang, Cheng Zhang, Cheng Niu, Jie Zhou

Natural Language Interfaces

Challenge:	Currently, open-domain chatbots are far from satisfactory.
Approach:	They propose a unified, readily scalable neural approach which reconciles all subtasks like intent prediction and knowledge retrieval.
Outcome:	The proposed approach outperforms commercial systems replying on complex rules on static and interactive tests and shows that the results are remarkably good.

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling (2025.emnlp-industry)

Copied to clipboard

Xiaoyu Liu, Di Liang, Hongyu Shan, Peiyang Liu, Yonghao Liu, Muling Wu, Yuntao Li, Xianjie Wu, Li Miao, Jiangrong Shen, Minlong Peng

Neural Ranking with Weak Supervision for Open-Domain Question Answering : A Survey (2023.findings-eacl)

Challenge:	Generative RMs (GRMs) lack contextual and background information during inference, leading to incomplete evaluations.
Approach:	They propose a modular and interpretable framework that integrates side-branch models as auxiliary feature generators.
Outcome:	The proposed framework outperforms scalar and saline reward models in robustness and alignment with human preferences.

Copied to clipboard

Xiaoyu Shen, Svitlana Vakulenko, Marco del Tredici, Gianni Barlacchi, Bill Byrne, Adria de Gispert

Question Answering

Challenge:	Neural ranking models require substantial amounts of relevance annotations, which is costly to scale.
Approach:	They propose to train a NR model with weak supervision instead of annotations . they use a structured overview of standard WS signals used for training a model .
Outcome:	The proposed approach reduces the cost of annotations by using weak supervision instead of a parametric model.

FocusQA: Open-Domain Question Answering with a Context in Focus (2022.findings-emnlp)

Copied to clipboard

Gianni Barlacchi, Ivano Lauriola, Alessandro Moschitti, Marco Del Tredici, Xiaoyu Shen, Thuy Vu, Bill Byrne, Adrià de Gispert

Natural Language Interfaces

Challenge:	a new method for question answering with a context in focus simulates a free interaction with QA systems.
Approach:	They introduce question answering with a cotext in focus task that simulates a free interaction with QA systems.
Outcome:	The proposed model outperforms state-of-the-art models for question answering with a context in focus up to 21.3% absolute points.

Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework (2026.acl-industry)

Copied to clipboard

Ziqiang Zhang, Jing Ma, Zilong Wang, Jiayuan Chen, Yi Qiao, Yu He, Wei Zhang, Dai Cheng, Xiaoyu Shen

MultiConIR: Towards Multi-Condition Information Retrieval (2025.findings-emnlp)

Challenge:	a production-grade pricing system for tourism is challenging due to unstructured nature of travel orders and ever-evolving pricing policies.
Approach:	They propose a production-grade pricing system with a strict decision boundary . they propose to combine structured extraction and bounded policy/path selection with interpretable condition trees .
Outcome:	The proposed system processed 3,960 orders in six months and reduced the order management team from 15-20 to 3 . the system reduced the per-order handling time from 10 minutes to 2 minutes.

Copied to clipboard

Xuan Lu, Sifan Liu, Bochao Yin, Yongqi Li, Xinghao Chen, Hui Su, Yaohui Jin, Wenjun Zeng, Xiaoyu Shen

Information Retrieval

Challenge:	MultiConIR is a benchmark designed to evaluate retrieval and reranking models under nuanced multi-condition query scenarios.
Approach:	They propose a benchmark to evaluate retrieval and reranking models under nuanced multi-condition query scenarios.
Outcome:	The proposed benchmark evaluates retrieval and reranking models under nuanced multi-condition query scenarios across five domains.

Improving Latent Alignment in Text Summarization by Generalizing the Pointer Generator (D19-1)

Copied to clipboard

Xiaoyu Shen, Yang Zhao, Hui Su, Dietrich Klakow

RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining (2022.acl-long)

Challenge:	Modern pointer generators only capture exact word matches, ignoring possible inflections or abstractions, which restricts its power of capturing richer latent alignment.
Approach:	They propose a pointer generator architecture that allows the model to "edit" pointed tokens instead of always copying them.
Outcome:	The proposed model captures more latent alignment relations than exact word matches and generates higher-quality summaries validated by both qualitative and quantitative evaluations.

Copied to clipboard

Hui Su, Weiwei Shi, Xiaoyu Shen, Zhou Xiao, Tuo Ji, Jiarui Fang, Jie Zhou

Neural Data-to-Text Generation with LM-based Text Augmentation (2021.eacl-main)

Challenge:	Large-scale pretrained language models have achieved SOTA results on NLP tasks but are vulnerable to adversarial attacks especially for logographic languages like Chinese.
Approach:	They propose a pretrained Chinese Bert that is robust to various forms of adversarial attacks like word perturbation, synonyms, typos, etc.
Outcome:	The proposed model outperforms baselines on 5 Chinese NLU tasks without sacrificing performance on clean testsets.

Copied to clipboard

Ernie Chang, Xiaoyu Shen, Dawei Zhu, Vera Demberg, Hui Su

Diversifying Dialogue Generation with Non-Conversational Text (2020.acl-main)

Challenge:	Neural data-to-text generation is a difficult task for many new applications because of a lack of training data.
Approach:	They propose a few-shot approach that augments the data available for training by generating new text samples based on replacing specific values by alternative ones from the same category and pairing the new text with data samples.
Outcome:	The proposed approach outperforms fully supervised sequence-to-sequence models with less than 10% of the training set on both datasets.

Copied to clipboard

Hui Su, Xiaoyu Shen, Sanqiang Zhao, Zhou Xiao, Pengwei Hu, Randy Zhong, Cheng Niu, Jie Zhou

Dialogue Systems & Conversational Agents

Challenge:	Neural network-based sequence-to-sequence models suffer from low diversity in open-domain dialogue generation.
Approach:	They propose a way to diversify dialogue generation by leveraging non-conversational text . they collect large-scale corpus from forum comments, idioms and book snippets .
Outcome:	The proposed model produces significantly more diverse responses without sacrificing relevance with context.

The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis (2024.findings-acl)

Copied to clipboard

Miaoran Zhang, Vagrant Gautam, Mingyang Wang, Jesujoba Alabi, Xiaoyu Shen, Dietrich Klakow, Marius Mosbach

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

Challenge:	In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without updating the model parameters.
Approach:	They conduct multidimensional analysis of multilingual in-context learning using 5 models from different model families and 9 datasets covering classification and generation tasks.
Outcome:	The results show that demonstrations vary significantly across models, tasks, and languages.

Copied to clipboard

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

Low-Resource NLP

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

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models (2026.findings-acl)

Copied to clipboard

Junlong Tong, Zilong Wang, YuJie Ren, Peiran Yin, Hao Wu, Wei Zhang, Xiaoyu Shen

Multimodal Language Models See Better When They Look Shallower (2025.emnlp-main)

Challenge:	Existing definitions of streaming LLMs are fragmented and lack a systematic taxonomy . large language models are pre-trained on static and full-context corpora .
Approach:	They propose a systematic taxonomy of current streaming Large Language Models and propose underlying methodologies for streaming LLMs.
Outcome:	The proposed model is based on data flow and dynamic interaction to clarify existing ambiguities.

Copied to clipboard

Haoran Chen, Junyan Lin, Xinghao Chen, Yue Fan, Jianfeng Dong, Xin Jin, Hui Su, Jinlan Fu, Xiaoyu Shen

Multimodality

Challenge:	Existing studies show that multimodal large language models extract visual features from the final layers of a pretrained Vision Transformer.
Approach:	They propose a feature fusion method that strategically incorporates shallower layers . they propose MLLMs that extract visual features from the final layers of a pretrained Vision Transformer .
Outcome:	The proposed method outperforms deep layers on fine-grained visual tasks . it is the first comprehensive study of visual layer selection for MLLMs .

LawBench: Benchmarking Legal Knowledge of Large Language Models (2024.emnlp-main)

Copied to clipboard

Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Alan Huang, Songyang Zhang, Kai Chen, Zhixin Yin, Zongwen Shen, Jidong Ge, Vincent Ng

Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice? (2024.emnlp-main)

Challenge:	LegalBench evaluated 20 LLMs in 162 legal tasks in 20 countries and jurisdictions.
Approach:	They present a comprehensive evaluation of 21 popular Large Language Models and the first comparative analysis of the empirical results.
Outcome:	The proposed benchmarks are based on the Bloom’s cognitive taxonomy and are compared to 21 popular LLMs.

Copied to clipboard

Dawei Zhu, Pinzhen Chen, Miaoran Zhang, Barry Haddow, Xiaoyu Shen, Dietrich Klakow

Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism (2024.emnlp-main)

Challenge:	Traditionally, success in multilingual machine translation depends on large volume, diverse directions, and high quality of training data.
Approach:	They revisit the importance of large language models for translation by fine-tuning on 32 parallel sentences.
Outcome:	The proposed model can be fine-tuned on as few as 32 parallel sentences . however, the choice of direction is critical to avoid misinterpretation, the authors say .

Copied to clipboard

Anhao Zhao, Fanghua Ye, Jinlan Fu, Xiaoyu Shen

Low-Resource NLP

Challenge:	Large language models exhibit remarkable in-context learning (ICL) capabilities, but the underlying working mechanism of ICL remains unclear.
Approach:	They propose a Two-Dimensional Coordinate System that unifies both views into a systematic framework that explains the behavior of ICL through two orthogonal variables: whether similar examples are presented in the demonstrations and whether LLMs can recognize the task.
Outcome:	The proposed method can interpret ICL for generation tasks effectively.

Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)

Copied to clipboard

Jiaming Wang, Yunke Zhao, Peng Ding, Jun Kuang, Yibin Shen, Zhe Tang, Yilin Jin, ZongYu Wang, Xiaoyu Li, Xuezhi Cao

Unsupervised Rewriter for Multi-Sentence Compression (P19-1)

Challenge:	Existing models lack the ability to adhere to instructions, resulting in suboptimal performance.
Approach:	They propose an automated iterative instruction-following benchmark with integrated feedback mechanism.
Outcome:	The proposed benchmark identifies erroneous components in model responses and provides feedback accurately.

Copied to clipboard

Yang Zhao, Xiaoyu Shen, Wei Bi, Akiko Aizawa

The Accuracy Paradox in RLHF: When Better Reward Models Don’t Yield Better Language Models (2024.emnlp-main)

Challenge:	Multi-sentence compression aims to generate a grammatical but reduced compression from multiple input sentences while retaining key information.
Approach:	They propose a neural rewriter for multi-sentence compression that does not need any parallel corpus.
Outcome:	Empirical studies show that the proposed approach achieves comparable results upon automatic evaluation and improves the grammaticality of compression based on human evaluation.

Copied to clipboard

Yanjun Chen, Dawei Zhu, Yirong Sun, Xinghao Chen, Wei Zhang, Xiaoyu Shen

InternLM-Law: An Open-Sourced Chinese Legal Large Language Model (2025.coling-main)

Challenge:	Reinforcement Learning from Human Feedback (RLHF) significantly enhances Natural Language Processing by aligning language models with human expectations.
Approach:	They propose to integrate feedback from humans into RLHF to improve language models by capturing human-like preferences.
Outcome:	The proposed model outperforms models trained with moderately accurate reward models on relevance, factuality, and completeness tasks.

Copied to clipboard

Zhiwei Fei, Songyang Zhang, Xiaoyu Shen, Dawei Zhu, Xiao Wang, Jidong Ge, Vincent Ng

To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models (2024.emnlp-main)

Challenge:	InternLM-Law is a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Approach:	They introduce a large language model (LLM) tailored for addressing diverse legal tasks related to Chinese laws.
Outcome:	The proposed model performs better than existing models in a variety of legal tasks related to Chinese laws.

Copied to clipboard

Junyan Lin, Haoran Chen, Dawei Zhu, Xiaoyu Shen

Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning (2024.findings-emnlp)

Challenge:	Recent multimodal large language models (MLLMs) have attracted widespread attention from both industry and academia due to their potential to handle multiple modalities in a unified framework.
Approach:	They propose to classify connectors into feature-preserving and feature-compressing types and categorize tasks into three task types: coarse-grained perception, fine-grain perception, and reasoning.
Outcome:	The proposed architectures perform better on tasks with varying granularities than on external fusion architectures.

Copied to clipboard

Qingyu Yin, Xuzheng He, Chak Tou Leong, Fan Wang, Yanzhao Yan, Xiaoyu Shen, Qiang Zhang

A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation (2022.naacl-main)

Challenge:	Fine-tuning and in-context learning are two prevalent methods in imbuing large language models with task-specific knowledge.
Approach:	They propose to use a circuit shift theory to explain why in-context learning is superior to fine-tuning for tasks with implicit patterns.
Outcome:	The proposed method can grasp deep patterns and significantly improve accuracy on implicit patterns, compared with fine-tuning and in-context learning.

Copied to clipboard

David Adelani, Jesujoba Alabi, Angela Fan, Julia Kreutzer, Xiaoyu Shen, Machel Reid, Dana Ruiter, Dietrich Klakow, Peter Nabende, Ernie Chang, Tajuddeen Gwadabe, Freshia Sackey, Bonaventure F. P. Dossou, Chris Emezue, Colin Leong, Michael Beukman, Shamsuddeen Muhammad, Guyo Jarso, Oreen Yousuf, Andre Niyongabo Rubungo, Gilles Hacheme, Eric Peter Wairagala, Muhammad Umair Nasir, Benjamin Ajibade, Tunde Ajayi, Yvonne Gitau, Jade Abbott, Mohamed Ahmed, Millicent Ochieng, Anuoluwapo Aremu, Perez Ogayo, Jonathan Mukiibi, Fatoumata Ouoba Kabore, Godson Kalipe, Derguene Mbaye, Allahsera Auguste Tapo, Victoire Memdjokam Koagne, Edwin Munkoh-Buabeng, Valencia Wagner, Idris Abdulmumin, Ayodele Awokoya, Happy Buzaaba, Blessing Sibanda, Andiswa Bukula, Sam Manthalu

Multilinguality

Challenge:	Low-resource languages are left out of large-scale pretraining datasets . authors explore how to leverage existing pre-trained models to create low-resourced translation systems for 16 African languages.
Approach:	They investigate how large-scale pre-trained models can be used to create low-resource translation systems for 16 African languages.
Outcome:	The proposed models can translate between hundreds of languages even though there is little parallel data available for training.

Reasoning Fails Where Step Flow Breaks (2026.acl-long)

Copied to clipboard

Xiaoyu Xu, Yulan Pan, Xiaosong Yuan, Zhihong Shen, Minghao Su, Yuanhao Su, Xiaofeng Zhang

Reasoning

Challenge:	Existing analysis tools struggle with long chain of thought traces.
Approach:	They propose a saliency-inspired test-time intervention that adjusts shallow saliencies to improve accuracy on math, science, and coding tasks.
Outcome:	The proposed model improves accuracy on math, science, and coding tasks without retraining.

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation (2025.acl-long)

Copied to clipboard

Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Weipeng Jiang, Qian Wang, Chao Shen, Yang Liu

Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation (2025.naacl-srw)

Challenge:	Large Language Models (LLMs) have emerged as the new recommendation engines, surpassing traditional methods in both capability and scope, particularly in code generation.
Approach:	They propose to use a dataset to investigate a new type of bias in Large Language Models for code generation, provider bias, to determine whether the model favors specific providers.
Outcome:	The proposed model favors services from Google and Amazon, but without explicit directives, and can modify input code to incorporate their preferred providers without user requests.

Copied to clipboard

Yirong Sun, Dawei Zhu, Yanjun Chen, Erjia Xiao, Xinghao Chen, Xiaoyu Shen

Machine Translation

Challenge:	Large language models excel in machine translation, but most studies focus on sentence-level translation.
Approach:	They propose to use LLMs as a judge paradigm to evaluate document-level translations by directly prompting them to translate entire documents in a single pass.
Outcome:	The proposed method improves translation quality even without document-level fine-tuning compared to translating sentences separately .

xPQA: Cross-Lingual Product Question Answering in 12 Languages (2023.acl-industry)

Copied to clipboard

Xiaoyu Shen, Akari Asai, Bill Byrne, Adria De Gispert

Multilinguality

Challenge:	Existing work on product question answering systems focuses mainly on English, but in practice there is need to support multiple customer languages while leveraging product information available in English.
Approach:	They present a large-scale annotated cross-lingual PQA dataset in 12 languages and evaluate three approaches to generating a natural-sounding non-English answer.
Outcome:	The proposed dataset supports crosslingual product question answering (PQA) systems that provide answers to customers’ questions as they shop for products.

Assessing “Implicit” Retrieval Robustness of Large Language Models (2024.emnlp-main)

Copied to clipboard

Xiaoyu Shen, Rexhina Blloshmi, Dawei Zhu, Jiahuan Pei, Wei Zhang