Papers by Xiaoyu Chen

Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning (2025.findings-acl)

Challenge:	Large Language Models (LLMs) are obstructed by their opaque and often unreliable reasoning.
Approach:	They propose a framework for trustworthy clinical argumentation by adapting the Toulmin model to the diagnostic process.
Outcome:	The proposed method achieves diagnostic accuracy comparable to resource-intensive RL methods while offering a more stable and efficient training pipeline.

Copied to clipboard

Xinghao Chen, Zhijing Sun, Guo Wenjin, Miaoran Zhang, Yanjun Chen, Yirong Sun, Hui Su, Yijie Pan, Dietrich Klakow, Wenjie Li, Xiaoyu Shen

Generative Annotation for ASR Named Entity Correction (2025.emnlp-main)

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

Yuanchang Luo, Daimeng Wei, Shaojun Li, Hengchao Shang, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Xiaoyu Chen, Zhiqiang Rao, Jinlong Yang, Hao Yang

MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Bandits (2026.acl-long)

Challenge:	Existing named entity correction models fail to transcribe domain-speciffcnamed entities when theforms of the wrongly-transcribed words and the ground-truth entity are signiffcantly different.
Approach:	They propose a method that utilizes speech sound features to retrieve candidate entities . it uses speech sound feature to annotate entityerrors in ASR transcripts .
Outcome:	The proposed method can bring signiffcant improvement to entity accuracy.

Copied to clipboard

Yixin Xiang, Yunshan Ma, Xiaoyu Du, Yibing Chen, Yanxin Zhang, Jinhui Tang

CondenseFlow: Scalable Latent Space Collaboration via Semantic Compression for Multi-Agent Systems (2026.findings-acl)

Challenge:	Document Question Answering (DQA) requires interpreting visual layouts, which has prompted recent studies to adopt multimodal Retrieval-Augmented Generation (RAG) that processes page images for answer generation.
Approach:	They propose a multi-armed bandit-based DQA framework that explicitly models the varying importance of multiple implicit aspects in a query.
Outcome:	The proposed framework shows an improvement of 5%-18% over the state-of-the-art method on four benchmarks.

Copied to clipboard

Xiaoyu Chen, Fengge Wu, Zhao Junsuo, Yun Fan

Challenge:	Full-state latent communication in LLMs suffers from memory overhead scaling linearly with collaboration rounds.
Approach:	They propose a lightweight module that uses learnable semantic probes to compress KV caches into fixed-size representations.
Outcome:	The proposed module reduces KV cache memory by over 99% and inference latency by approximately 20% on seven benchmarks spanning six models . it outperforms text-based methods by 1.7 percentage points on average across all configurations while outperforming existing methods by 1.7%.

Multi-Granularity Semantic Revision for Large Language Model Distillation (2026.acl-long)

Copied to clipboard

Xiaoyu Liu, Yun Zhang, Wei Li, Simiao Li, Xudong Huang, Hanting Chen, Yehui Tang, Jie Hu, Zhiwei Xiong, Yunhe Wang

DocumentNet: Bridging the Data Gap in Document Pre-training (2023.emnlp-industry)

Challenge:	Existing methods for generating large language models rely on student-generated outputs, which introduce generation errors and misguide the distillation process.
Approach:	They propose a multi-granularity semantic revision method for LLM distillation that corrects errors using teacher-generated tokens and re-generates the sequence to minimize errors.
Outcome:	The proposed method reduces errors and misguides distillation on student models and improves consistency between teacher and student outputs.

Copied to clipboard

Lijun Yu, Jin Miao, Xiaoyu Sun, Jiayi Chen, Alexander Hauptmann, Hanjun Dai, Wei Wei

Circuit Complexity Bounds for RoPE-based Transformer Architecture (2025.emnlp-main)

Challenge:	Document understanding tasks are a tedious task that requires extensive training and privacy constraints.
Approach:	They propose a method to collect weakly labeled data from the web to benefit VDER training . the collected dataset does not depend on specific document types or entity sets .
Outcome:	The proposed method does not depend on specific document types or entity sets, making it universally applicable to all VDER tasks.

Copied to clipboard

Bo Chen, Xiaoyu Li, Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Jiahao Zhang

Semantic Text Processing

Challenge:	Recent studies provide the circuit complexity bounds to Transformer-like architectures. position embedding has emerged as a crucial technique in modern large language models.
Approach:	They propose to use position embedding to improve Transformer-like architectures by analyzing their circuits and analyzing the results.
Outcome:	The proposed model is able to solve canonical tasks without embedding positional information.

SceneLM: 3D-Aware Language Models for Editable 3D Scene Synthesis (2026.findings-acl)

Copied to clipboard

Xingbo Yao, Xiaoyu Chen, Doudou Zhang, Mingzhi Sheng, Boyuan Cao, Ying-Cong Chen, Hui Xiong

Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce (2022.findings-emnlp)

Challenge:	Existing methods for synthesising 3D scenes from a single image are text-driven and lack precise metric understanding from images.
Approach:	They propose a language-model-based framework that grounds 3D scene synthesis in visual evidence by recovering an executable metric 3D layout directly from a single image.
Outcome:	The proposed framework recovers an executable metric 3D layout directly from an RGB image and instantiates, places, and edits objects for iterative refinement.

Copied to clipboard

Yincen Qu, Ningyu Zhang, Hui Chen, Zelin Dai, Chengming Wang, Xiaoyu Wang, Qiang Chen, Huajun Chen

Commonsense Reasoning

Challenge:	Existing models rank statements solely by confidence scores, and there is no information about which ones are salient from a human perspective.
Approach:	They propose a task where a model is required to learn whether a triple is salient . they propose supervised salience evaluation using a new Benchmark dataset .
Outcome:	The proposed task is based on a new Benchmark dataset of salience evaluation in e-commerce . it shows that saliency evaluation is hard, where models perform poorly on evaluation set .

Convert Language Model into a Value-based Strategic Planner (2025.acl-industry)

Copied to clipboard

Xiaoyu Wang, Yue Zhao, Qingqing Gu, Zhonglin Jiang, Yong Chen, Luo Ji

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

Challenge:	Emotional support conversation (ESC) aims to alleviate the emotional distress of individuals through effective conversations.
Approach:	They propose a framework that bootstraps the planning during ESC and determines the optimal strategy based on long-term returns.
Outcome:	The proposed framework outperforms baseline models on ESC datasets and can be used to guide the LLM to response.

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.

INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion (2023.findings-emnlp)

Copied to clipboard

Hengchao Shang, Zongyao Li, Daimeng Wei, Jiaxin Guo, Minghan Wang, Xiaoyu Chen, Lizhi Lei, Hao Yang

Text Generation

Challenge:	Existing models for word-level autocompletion (WLAC) only use human typed sequences as prefixes in decoding module.
Approach:	They propose a novel iterative nonautoregressive instruct generation model for WLAC task . it uses human typed sequences and iterating decoding with subwords to fully utilize input information.
Outcome:	The proposed model is more competent in dealing with low-frequency words, and achieves state-of-the-art results on the WMT22 and benchmark datasets.

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

Semantic Text Processing

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.

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

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.

Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling (2025.findings-emnlp)

Copied to clipboard

Yue Zhao, Xiaoyu Wang, Dan Wang, Zhonglin Jiang, Qingqing Gu, Teng Chen, Ningyuan Xi, Jinxian Qu, Yong Chen, Luo Ji

Dialogue Systems & Conversational Agents

Challenge:	a framework for constructing dialogue world models for natural language tasks is currently lacking.
Approach:	They propose a framework that can be used to train a dialogue world model.
Outcome:	The proposed framework can predict future utterances and user beliefs . it can achieve state-of-the-art performance on emotion classification and sentiment identification .

Program Enhanced Fact Verification with Verbalization and Graph Attention Network (2020.emnlp-main)

Copied to clipboard

Xiaoyu Yang, Feng Nie, Yufei Feng, Quan Liu, Zhigang Chen, Xiaodan Zhu

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Existing methods for fact verification based on structured data are challenging and require further study.
Approach:	They propose a program-enhanced verbalization and a graph attention network to integrate programs and execution into textual inference models.
Outcome:	The proposed framework achieves a new state-of-the-art accuracy on a benchmark dataset . it is compared with existing frameworks on symbolic and informal inference models .

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

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

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

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

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

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 .

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

KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server (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

WenHao Wang, Xiaoyu Liang, Rui Ye, Jingyi Chai, Siheng Chen, Yanfeng Wang

Text Style Transfer Back-Translation (2023.acl-long)

Challenge:	Existing methods to train large language models on private data are not effective because they rely on a local model for generation, resulting in a performance decline, or expose private data to API servers.
Approach:	They propose a client-server framework which enhances synthetic data quality and improves model performance while ensuring privacy.
Outcome:	The proposed framework improves model performance and privacy while learning local knowledge from the private data with differential privacy (DP) and distilling professional knowledge from server.

Copied to clipboard

Daimeng Wei, Zhanglin Wu, Hengchao Shang, Zongyao Li, Minghan Wang, Jiaxin Guo, Xiaoyu Chen, Zhengzhe Yu, Hao Yang

Text Generation

Challenge:	Current methods require large amount of bilingual training data, which is challenging and sometimes impossible task.
Approach:	They propose a method to modify the style of inputs by modifying the source side of BT data.
Outcome:	The proposed method significantly improves translation quality against popular BT benchmarks on high-resource and low-resourced language pairs.

A Novel Paradigm Boosting Translation Capabilities of Large Language Models (2024.findings-naacl)

Copied to clipboard

Jiaxin Guo, Hao Yang, Zongyao Li, Daimeng Wei, Hengchao Shang, Xiaoyu Chen

Multilinguality

Challenge:	Existing studies on LLMs focused on supervised fine-tuning but their effectiveness has been limited.
Approach:	They propose a paradigm consisting of three stages: Secondary Pre-training using extensive monolingual data, Continual Pre- training with interlinear text format documents, and Leveraging source-language consistent instruction for supervised fine-tuning.
Outcome:	The proposed approach surpasses previous work and achieves superior performance compared to models such as NLLB-54B(CITATION) and GPT3.5-text-davinci-003.

SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026.findings-acl)

Copied to clipboard

Jiaming Wang, Zhe Tang, Zehao Jin, Hefei Chen, Yilin Jin, Peng Ding, Xiaoyu Li, Xuezhi Cao

Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similarities (2025.emnlp-main)

Challenge:	Large language models (LLMs) are widely deployed as domain-specific agents, but evaluation of their capabilities in such contexts has not been fully explored.
Approach:	They propose a benchmark to evaluate LLMs' ability to follow instructions and make decisions in real-world scenarios.
Outcome:	The proposed benchmark is constructed from real-world business data and adapted into 23 complex SOP scenarios.

Copied to clipboard

Xiaoyu Luo, Yiyi Chen, Johannes Bjerva, Qiongxiu Li

Multilinguality

Challenge:	Using multilingual models, we find that treating languages in isolation obscures the true patterns of memorization.
Approach:	They propose a graph-based correlation metric that incorporates language similarity to analyze cross-lingual memorization.
Outcome:	The proposed model incorporates language similarity to analyze cross-lingual memorization in 95 languages.

Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework (2026.acl-long)

Copied to clipboard

Xiaoyu Luo, Yiyi Chen, Qiongxiu Li, Johannes Bjerva

Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have been reported to “leak” Personally Identifiable Information (PII) successful PII reconstruction often interpreted as evidence of memorization.
Approach:	They propose a principled revision of memorization evaluation for Large Language Models . they propose PII leakage should be evaluated under low lexical cue conditions .
Outcome:	The proposed method is based on a multilingual re-evaluation of PII leakage across 32 languages and multiple memorization paradigms.

Copied to clipboard

Xiaoshu Chen, Sihang Zhou, Ke Liang, Xiaoyu Sun, Xinwang Liu

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

Challenge:	Existing methods train small language models to learn long rationales in one iteration.
Approach:	They propose a method that uses a heuristic search to divide rationale into internal chunks . they propose CWT, which uses CWt to focus SLM on learning from only one chunk per iteration.
Outcome:	The proposed method can guide a large language model (LLM) in reasoning tasks.

Copied to clipboard

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

Combining the Best of Both Worlds: A Method for Hybrid NMT and LLM Translation (2025.findings-acl)

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

Zhanglin Wu, Daimeng Wei, Xiaoyu Chen, Hengchao Shang, Jiaxin Guo, Zongyao Li, Yuanchang Luo, Jinlong Yang, Zhiqiang Rao, Hao Yang

Multilinguality

Challenge:	Large language models have advantages over neural machine translation systems, but they suffer from high computational costs and significant latency.
Approach:	They propose a scheduling policy that optimizes translation result while ensuring fast speed and as little LLM usage as possible.
Outcome:	The proposed model achieves optimal translation performance with less LLM usage on multilingual test sets.

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

Copied to clipboard

Junyan Lin, Haoran Chen, Dawei Zhu, Xiaoyu Shen