Papers by Fan Shi

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

Challenge:	Existing approaches to align large language models with human preferences lack flexibility . static alignment preferences lack the ability to correct misaligned behaviors as they emerge .
Approach:	They propose a framework that enables dynamic and continuous alignment of large language models with human preferences.
Outcome:	The proposed framework improves safety and accuracy of a 7B model with human annotations.

Copied to clipboard

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

Text Generation

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.

On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions (2025.findings-emnlp)

Copied to clipboard

Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, Yangqiu Song

UniLG: A Unified Structure-aware Framework for Lyrics Generation (2023.acl-long)

Challenge:	Conceptualization is a fundamental element of human cognition and plays a pivotal role in generalizable reasoning.
Approach:	They propose to categorize different types of conceptualizations into four levels based on the types of instances being conceptualized.
Outcome:	The proposed categorization of different types of conceptualizations into four levels based on the types of instances being conceptualized .

Copied to clipboard

Tao Qian, Fan Lou, Jiatong Shi, Yuning Wu, Shuai Guo, Xiang Yin, Qin Jin

LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline (2025.findings-acl)

Challenge:	Existing works ignore musical attributes hidden behind lyrics and structure of lyrics . existing works ignore structure of generated lyrics and do not consider structure of songs .
Approach:	They propose a framework for conditional lyrics generation that considers structure and relationship between lyrics and music.
Outcome:	The proposed framework improves the structure modeling and unifies different conditions for different types of lyrics generation.

Copied to clipboard

Biao Fu, Minpeng Liao, Kai Fan, Chengxi Li, Liang Zhang, Yidong Chen, Xiaodong Shi

iMOVE : Instance-Motion-Aware Video Understanding (2025.findings-acl)

Challenge:	Large language models perform well in offline machine translation when the complete source sentence is provided . however, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation is required .
Approach:	They propose a new paradigm that includes constructing supervised fine-tuning data for simultaneous machine translation (SiMT) to achieve SiMT, source and target tokens are rearranged into interleaved sequences, separated by special tokens according to varying latency requirements.
Outcome:	The proposed approach achieves state-of-the-art performance across various SiMT benchmarks and evaluation metrics while maintaining efficient auto-regressive decoding.

Copied to clipboard

Jiaze Li, Yaya Shi, Zongyang Ma, Haoran Xu, Yandong.bai Yandong.bai, Huihui Xiao, Ruiwen Kang, Fan Yang, Tingting Gao, Di Zhang

Visual Data in NLP

Challenge:	Recent advances in Video Large Language Models have led to rapid development, significantly enhancing the capture of overall video semantics and achieving remarkable performance in general video understanding tasks.
Approach:	They propose a large-scale instance-motion-aware video instruction-tuning dataset iMOVE that utilizes Event-awful Spatiotemporal Efficient Modeling to retain informative instance spatiotemporal motion details while maintaining computational efficiency.
Outcome:	The proposed model excels in video temporal understanding and general video understanding.

Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing (2020.findings-emnlp)

Copied to clipboard

Ke Wang, Jiayi Wang, Niyu Ge, Yangbin Shi, Yu Zhao, Kai Fan

Machine Translation

Challenge:	Using neural machine translation to approximate human parity is difficult due to the lack of parallel training corpora.
Approach:	They propose an end-to-end deep learning framework for quality estimation and automatic post-editing of machine translation output.
Outcome:	The proposed framework achieves state-of-the-art performance on the English–German dataset and human translators can significantly expedite their post-editing processing with the model.

Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning (2026.findings-acl)

Copied to clipboard

Haiyang Yu, Yuchuan Wu, Fan Shi, Jinghui Lu, Ke Niu, Xiaodong Ge, Minghan Zhuo, Jingqun Tang, Bin Li

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models (2026.findings-acl)

Challenge:	Existing document benchmarks focus on English printed texts or simplified Chinese . current vision-language models struggle with visual complexity and poor adaptability .
Approach:	They propose a benchmark to evaluate Chinese ancient documents' visual/linguistic complexity . ancient documents are valuable cultural heritage, but they face challenges in digitization and understanding .
Outcome:	the first benchmark for Chinese ancient documents evaluates VLMs from OCR to knowledge reasoning . ancient documents carry thousands of years of Chinese history and culture . traditional methods only scan images, while current models struggle with visual complexity .

Copied to clipboard

Junjie Ye, Caishuang Huang, Zhuohan Chen, Wenjie Fu, Chenyuan Yang, Leyi Yang, Yilong Wu, Peng Wang, Meng Zhou, Xiaolong Yang, Tao Gui, Qi Zhang, Zhongchao Shi, Jianping Fan, Xuanjing Huang

An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing (2021.emnlp-main)

Challenge:	Existing research has focused on constraint categories, offering little guidance for improving instruction following abilities.
Approach:	They propose a multi-dimensional constraint framework that allows for instruction following . they construct 9,106 code-verifiable samples and evaluate 18 LLMs .
Outcome:	The proposed framework improves instruction following performance without compromising general performance.

Copied to clipboard

Yi Chen, Haiyun Jiang, Lemao Liu, Shuming Shi, Chuang Fan, Min Yang, Ruifeng Xu

InferenceDynamics: Adaptive LLM Routing through Structured Capability and Knowledge Profiling (2026.acl-long)

Challenge:	Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET) however, there is no comprehensive understanding of how to make better use of the existing information sources and how they affect the performance of ZFET.
Approach:	They propose a multi-source fusion model targeting auxiliary information from multiple sources to improve zero-shot fine-grained entity typing (ZFET)
Outcome:	The proposed model achieves 11.42% and 22.84% gains over state-of-the-art baselines on BBN and Wiki respectively with regard to macro F1 scores.

Copied to clipboard

Haochen Shi, Tianshi Zheng, Weiqi Wang, Baixuan Xu, Chunyang Li, Chunkit Chan, Tao Fan, Yangqiu Song

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Large Language Model (LLM) routing is a pivotal technique for navigating a diverse landscape of LLMs.
Approach:	They propose a flexible and scalable multi-dimensional routing framework that models the capability and knowledge of models.
Outcome:	The proposed framework can be used to generalize and identify top-performing models for group-level routing using modern benchmarks including MMLU-Pro, GPQA, BigGenBench, and LiveBench.

Copied to clipboard

Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun

TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data (2022.emnlp-main)

Challenge:	Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning .
Approach:	a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path .
Outcome:	Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness.

Copied to clipboard

Fan Zhou, Mengkang Hu, Haoyu Dong, Zhoujun Cheng, Fan Cheng, Shi Han, Dongmei Zhang

Fusion-in-T5: Unifying Variant Signals for Simple and Effective Document Ranking with Attention Fusion (2024.lrec-main)

Challenge:	Existing auto-regressive pre-trained language models are challenged by recent emerging numerical reasoning datasets due to the error-prone implicit calculation.
Approach:	They propose a pre-computation tool to pre-compute aggregation/arithmetic results for the table in advance, so they are handy and readily available for PLMs to answer numerical reasoning questions.
Outcome:	The proposed model improves on TAT-QA and T5 and BART-large on multiple benchmarks.

Copied to clipboard

Shi Yu, Chenghao Fan, Chenyan Xiong, David Jin, Zhiyuan Liu, Zhenghao Liu

Information Retrieval

Challenge:	Current document ranking pipelines involve multiple ranking layers to integrate different information step-by-step.
Approach:	They propose a novel re-ranker Fusion-in-T5 which integrates text matching information, ranking features, and global document information into one single unified model via templated-based input and global attention.
Outcome:	The proposed model significantly improves ranking performance over complex cascade pipelines.

Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference (2023.emnlp-main)

Copied to clipboard

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

FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)

Challenge:	Existing approaches to streaming speech translation use an offline model with a wait-k policy . however, there is a mismatch problem with an offline inference model trained with complete utterances .
Approach:	They propose an offline streaming speech translation model with wait-k policy to support different latency requirements.
Outcome:	The proposed model achieves better trade-offs between translation quality and latency than baselines.

Copied to clipboard

Yusong Hu, Runmin Ma, Yue Fan, Jinxin Shi, Zongsheng Cao, Yuhao Zhou, Jiakang Yuan, Shuaiyu Zhang, Shiyang Feng, Xiangchao Yan, Shufei Zhang, Wenlong Zhang, Lei Bai, Bo Zhang

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Challenge:	FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Approach:	They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Outcome:	The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download.

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

Robustness in NLP

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Few-Shot Semantic Dependency Parsing via Graph Contrastive Learning (2024.lrec-main)

Copied to clipboard

Bin Li, Yunlong Fan, Yikemaiti Sataer, Chuanqi Shi, Miao Gao, Zhiqiang Gao

RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answering (2025.findings-acl)

Challenge:	Existing graph neural networks (GNNs) have shown promising performance on semantic dependency parsing (SDP) training a high-performing model requires a large amount of labeled data and it is prone to over-fitting in the absence of sufficient labele .
Approach:	They propose a syntax-guided graph contrastive learning framework to train GNNs with unlabeled data and fine-tune pre-trained GNN models with few-shot labeled SDP data.
Outcome:	The proposed framework achieves promising results when few-shot training samples are available.

Copied to clipboard

Baixuan Li, Yunlong Fan, Tianyi Ma, Miao Gao, Chuanqi Shi, Zhiqiang Gao

Contextual Domain Classification with Temporal Representations (2021.naacl-industry)

Challenge:	Existing methods for generating and analyzing multiple document knowledge are not effective for multi-hop question answering.
Approach:	They propose a Monte Carlo tree-based approach to inference-time scaling using RASPberry.
Outcome:	Experimental results show that the proposed method achieves better inference-time scaling on smaller LLMs.

Copied to clipboard

Tzu-Hsiang Lin, Yipeng Shi, Chentao Ye, Yang Fan, Weitong Ruan, Emre Barut, Wael Hamza, Chengwei Su

Information Retrieval

Challenge:	Existing studies that incorporate context in SLU have focused on domains where context is limited to a few minutes.
Approach:	They propose temporal representations that combine wall-clock second difference and turn order offset information to utilize both recent and distant context in a novel large-scale setup.
Outcome:	The proposed model reduces 13.04% of classification errors compared to baseline . previous studies have focused on domains where context is limited to a few minutes .

PILE: Pairwise Iterative Logits Ensemble for Multi-Teacher Labeled Distillation (2022.emnlp-industry)

Copied to clipboard

Lianshang Cai, Linhao Zhang, Dehong Ma, Jun Fan, Daiting Shi, Yi Wu, Zhicong Cheng, Simiu Gu, Dawei Yin

UEGP: Unified Expert-Guided Pre-training for Knowledge Rekindle (2024.findings-naacl)

Challenge:	Pre-trained language models have been a key part of ranking systems . knowledge distillation is widely used to maintain high performance while keeping efficient computations.
Approach:	They propose an algorithm to combine knowledge from multi-teachers and label information to achieve competitive performance in offline and online experiments.
Outcome:	The proposed method has been deployed in a real-world commercial search system.

Copied to clipboard

Yutao Mou, Kexiang Wang, Jianhe Lin, Dehong Ma, Jun Fan, Daiting Shi, Zhicong Cheng, Gu Simiu, Dawei Yin, Weiran Xu

OmniCompliance-100K: A Multi-Domain, Rule-Grounded, Real-World Safety Compliance Dataset (2026.findings-acl)

Challenge:	Existing paradigms for pre-training and fine-tuning have limitations . knowledge rekindle aims to break through performance upper bounds of experts without introducing additional annotated data.
Approach:	They propose a new paradigm for pre-training and fine-tuning that aims to re-incorporate the fine- tuned expert model into the training cycle and break through performance upper bounds of experts.
Outcome:	The proposed model breaks through performance upper bounds of experts without additional annotated data.

Copied to clipboard

Wenbin Hu, Huihao Jing, Haochen Shi, Changxuan Fan, Haoran Li, Yangqiu Song

Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels (2025.emnlp-main)

Challenge:	Existing LLM safety datasets rely on ad-hoc taxonomies and lack rule-grounded, real-world cases.
Approach:	They construct a rule-grounded, real-world case dataset OmniCompliance-100K from a compliance perspective using a powerful web-searching agent.
Outcome:	The proposed dataset spans 74 regulations and policies across a wide range of domains including security and privacy regulations, content safety and user data privacy policies, financial security requirements, medical device risk management standards, educational integrity guidelines, and protections of fundamental human rights.

Copied to clipboard

Junjie Ye, Yuming Yang, Yang Nan, Shuo Li, Qi Zhang, Tao Gui, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan

FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining (2022.acl-long)

Challenge:	Large language models (LLMs) acquire substantial world knowledge during pretraining, which is further shaped by post-training techniques such as supervised fine-tuning (SFT).
Approach:	They evaluate closed-book question answering (CBQA) performance across five LLMs from the LLaMA-2 and LLama-3 families and examine the impact of supervised fine-tuning on model knowledge.
Outcome:	The proposed model performance is 14% worse than models fine-tuned on 1,920 samples and 12% worse on 240 samples.

Copied to clipboard

Zhoujun Cheng, Haoyu Dong, Ran Jia, Pengfei Wu, Shi Han, Fan Cheng, Dongmei Zhang

TeachMaster: Generative Teaching via Code (2026.acl-industry)

Challenge:	Tables store rich numerical data, but numerical reasoning over tables is still a challenge.
Approach:	They propose a spreadsheet formula is a valuable supervision for numerical reasoning in tables.
Outcome:	The proposed method outperforms state-of-the-art methods on three representative datasets of formula prediction, question answering, and cell type classification.

Copied to clipboard

Yuheng Wang, Runde Yang, Lin Wu, Jie Zhang, Jingru Fan, Tianle Zhou, Ruoyu Fu, Huatao Li, Ruijie Shi, Siheng Chen, Weinan E, Chen Qian

Weicong Qin, Yi Xu, Weijie Yu, Teng Shi, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu

Challenge:	Existing methods for creating video content are limited by high costs and slow update cycles.
Approach:	They propose a paradigm shifting educators from manual creators to high-level directors who focus on pedagogical intents while agents handle execution.
Outcome:	The proposed framework reduces production costs to 0.3% of traditional course videos and provides a robust solution for scalable education.

Copied to clipboard

Information Retrieval

Challenge:	Existing methods rely on semantic similarity to align historical consultations with current queries due to the absence of ‘value’ labels, but this lacks exploration of needs in user consultations.
Approach:	They propose a consultation value assessment framework that evaluates historical consultations from three novel perspectives: (1) Scenario Scope Value, (2) Posterior Action Value, and (3) Time Decay Value.
Outcome:	The proposed model outperforms baselines on public and commercial datasets on both retrieval and ranking tasks.

On the Sensitivity and Stability of Model Interpretations in NLP (2022.acl-long)

Copied to clipboard

Fan Yin, Zhouxing Shi, Cho-Jui Hsieh, Kai-Wei Chang