Papers by Hui Jiang
Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control (2026.findings-acl)
Copied to clipboard
Changhao Jiang, Jiahao Chen, Zhenghao Xiang, Zhixiong Yang, Hanchen Wang, Jiabao Zhuang, Xinmeng Che, Jiajun Sun, Hui Li, Yifei Cao, Shihan Dou, Ming Zhang, Junjie Ye, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, but academic research remains non-reproducible due to the lack of publicly available training data. |
| Approach: | They propose a system for long-form song generation with fine-grained style conditioning that includes a licensed synthetic dataset and a song generation model, Muse. |
| Outcome: | The proposed system achieves competitive performance on phoneme error rate, text–music style similarity, and audio aesthetic quality while enabling controllable segment-level generation across different musical structures. |
Explicit Utilization of General Knowledge in Machine Reading Comprehension (P19-1)
Copied to clipboard
| Challenge: | Existing MRC models are unable to integrate general knowledge with human knowledge. |
| Approach: | They propose a data enrichment method which uses WordNet to extract inter-word semantic connections as general knowledge from each given passage-question pair. |
| Outcome: | The proposed model outperforms state-of-the-art models and is robust to noise. |
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | a new CLTL model is proposed to facilitate cross-linguistic transfer learning between distant languages . a key to CLTL is to learn a shared representation space for the given source-target language pair. |
| Approach: | They propose a new CLTL model that integrates machine translation with MT . they use an unannotated data technique to make use of the model's pre-training and fine-tuning . |
| Outcome: | The proposed model achieves better CLTL performance than the baseline model without more annotated data. |
Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)
Copied to clipboard
Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, Xiaodan Zhu
| Challenge: | Existing methods for AVE are limited on rare attributes due to poor generalization ability. |
| Approach: | They propose to leverage pretraining and transfer learning to address weaknesses in existing methods. |
| Outcome: | The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources. |
A Table-to-Text Framework with Heterogeneous Multidominance Attention and Self-Evaluated Multi-Pass Deliberation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Table-to-text works have been widely applied in different domains, such as weather forecast and financial report generation. |
| Approach: | They propose a table-to-text approach on top of Self-evaluated multi-pass Generation and Heterogenous Multidominance Attention to explore the hierarchical structure. |
| Outcome: | The proposed method outperforms several SOTA methods quantitatively and qualitatively on three public datasets. |
Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | In encoder-decoder neural models, multiple encoders are used to represent contextual information in addition to the individual sentence. |
| Approach: | They propose to use multiple context encoders to encode the individual sentences in document-level neural machine translation (NMT) They propose a noisy dropout setup and a single-encoder approach to encode context sentences. |
| Outcome: | The proposed approach encodes the context and the current sentence without contexts. |
LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Long-context processing ability has emerged as a significant challenge for large language models. |
| Approach: | They propose a pipeline for synthesizing faithful long-context reasoning instruction datasets . they integrate ground truth and citation-based reasoning prompts integrating them . |
| Outcome: | The proposed pipeline eliminates distractions and improves reasoning chains. |
Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning (2025.findings-emnlp)
Copied to clipboard
Yangning Li, Tingwei Lu, Yinghui Li, Yankai Chen, Wei-Chieh Huang, Wenhao Jiang, Hui Wang, Hai-Tao Zheng, Philip S. Yu
| Challenge: | Efficient instruction tuning aims to enhance the ultimate performance of large language models (LLMs) current methods suffer from the curriculum rigidity, resulting in a fixed and potentially sub-optimal learning trajectory. |
| Approach: | a framework for efficient instruction tuning is proposed to address the issue of curriculum rigidity . current methods rely on static heuristic difficulty metrics and fail to adapt to evolving capabilities . |
| Outcome: | Efficient instruction tuning aims to enhance the ultimate performance of large language models . current methods suffer from the curriculum rigidity, resulting in a fixed learning trajectory . |
FreebaseQA: A New Factoid QA Data Set Matching Trivia-Style Question-Answer Pairs with Freebase (N19-1)
Copied to clipboard
| Challenge: | Using FreebaseQA, we can generate over 54K matches from about 28K unique questions with minimal cost. |
| Approach: | They propose a data set for open-domain factoid question answering tasks over structured knowledge bases, like Freebase, using a combination of trivia-type question-answer pairs and subject-predicate-object triples. |
| Outcome: | The proposed data set generates 54K matches from 28K unique questions with minimal cost. |
Toward Safe and Human-Aligned Game Conversational Recommendation via Multi-Agent Decomposition (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing systems for conversational recommender systems (CRS) have strong results in movies, but games present distinct challenges . MATCHA framework provides specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking, and stronger safety. |
| Approach: | They propose a framework for conversational recommender systems that assigns specialized agents for intent parsing, tool-augmented retrieval, multi-LLM ranking and risk control. |
| Outcome: | MATCHA outperforms baselines on real user request dataset, improves Hit@5 by 20%, reduces popularity bias by 24%, and achieves 97.9% adversarial defense. |
Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large reasoning models exhibit human-like behaviors such as exploration, verification, reflection, and correction. |
| Approach: | They propose a supervised fine-tuning framework for long chain-of-thoughts reasoning . they leverage a difficulty-aware reward model to estimate the learning value of questions . |
| Outcome: | The proposed framework performs fine-tuning on large reasoning models on 10% of the data selected. |
Recall, Expand, and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity Typing (2023.acl-long)
Copied to clipboard
| Challenge: | State-of-the-art (SOTA) methods use the cross-encoder architecture to concatenate a mention (and its context) with each type and feed it into a pretrained language model (PLM) to score their relevance. |
| Approach: | They propose to perform entity typing in a recall-expand-filter manner and use a novel model to encode and score all these K candidates in one forward pass. |
| Outcome: | The proposed method is thousands of times faster than the CE-based architecture and is very efficient in fine-grained (130 types) and coarse-grain (9 types) entity typing. |
Efficient Knowledge Infusion via KG-LLM Alignment (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for knowledge infusion face knowledge mismatch and poor information compliance of LLMs with knowledge graphs. |
| Approach: | They propose a three-stage alignment strategy to enhance the LLM's capability to utilize information from knowledge graphs. |
| Outcome: | The proposed method outperforms baselines on biomedical question-answering datasets and outperformed existing methods. |
HSCodeComp: A Realistic and Expert-level Agent Benchmark for Hierarchical Rule Application (2026.acl-long)
Copied to clipboard
| Challenge: | Existing agent benchmarks neglect hierarchical rule application in real-world domains . a critical gap persists in numerous real-life professional domains where decision-making is governed by expert-written rules. |
| Approach: | They propose a benchmark requiring agents to assign a unique 10-digit Harmonized System (HS) Code to products by aligning their fuzzy attributes with strict tariff classification rules. |
| Outcome: | The proposed benchmarks lack hierarchical rule application capability in real-world domains . the proposed benchmark is based on e-commerce and is open-source . |
Exploring Dynamic Selection of Branch Expansion Orders for Code Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing code generation models model abstract syntax tree (AST) but not suitable for all multi-branch nodes. |
| Approach: | They propose to equip a Seq2Tree model with a branch selector to determine optimal expansion orders for multi-branch nodes. |
| Outcome: | The proposed model can determine optimal expansion orders of branches for multi-branch nodes. |
Shallow-to-Deep Training for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Experimental results show that deep training is 1:4 faster than training from scratch. |
| Approach: | They propose a shallow-to-deep training method that learns deep models by stacking shallow models. |
| Outcome: | The proposed method is 1:4 faster than training from scratch and achieves BLEU scores of 30:33 and 43:29 on two translation tasks. |
Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models (D18-1)
Copied to clipboard
| Challenge: | In this paper, we propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) in neural languages modelling, called dual-FOFE. |
| Approach: | They propose a new approach to employ the fixed-size ordinally-forgetting encoding (FOFE) in neural languages modelling, called dual-FOFE. |
| Outcome: | The proposed method significantly reduces the complexity and improves perplexity by 10% over the original FOFE model. |
Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation (2025.coling-main)
Copied to clipboard
| Challenge: | Current named entity recognition methods struggle with text-image mismatch problem due to a lack of visual context. |
| Approach: | They propose an adaptive mixup image augmentation method that generates augmented images based on matching score between text and image . |
| Outcome: | The proposed method can be integrated into existing models and demonstrate consistent performance improvements. |
From Scores to Preferences: Redefining Evaluation Paradigm for Speech Quality Reward Modeling (2026.findings-acl)
Copied to clipboard
Yifei Cao, Changhao Jiang, Jiabao Zhuang, Jiajun Sun, Ming Zhang, Zhiheng Xi, Hui Li, Shihan Dou, Yuran Wang, Yunke Zhang, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that the MOS-aware GRM significantly improves fine-grained speech quality discrimination. |
| Approach: | They propose a MOS-aware reward model that incorporates MOS gap into reward function during reinforcement learning. |
| Outcome: | The proposed model significantly improves fine-grained speech quality discrimination. |
Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency (2025.acl-long)
Copied to clipboard
Jiafeng Liang, Shixin Jiang, Xuan Dong, Ning Wang, Zheng Chu, Hui Su, Jinlan Fu, Ming Liu, See-Kiong Ng, Bing Qin
| Challenge: | Large Multimodal Models (LMMs) have demonstrated impressive performance on general video comprehension benchmarks, but their robustness needs to be thoroughly investigated for broader applications. |
| Approach: | They propose a temporal robustness benchmark which introduces temporal inconsistency perturbations separately at the visual and textual modalities to assess the robustness of models. |
| Outcome: | The proposed method improves the model’s robustness and reliability in temporal analysis. |
ContrastKV: Robust KV Cache Eviction via Contrastive Signal Fusion for Multi-Query Generalization (2026.acl-long)
Copied to clipboard
| Challenge: | Existing query-agnostic approaches rely on a single proxy query, leading to fragile eviction decisions under high evict ratios. |
| Approach: | They propose a query-agnostic KV cache eviction algorithm that exploits complementary semantic and non-semantic signals. |
| Outcome: | Experiments show that the proposed algorithm outperforms state-of-the-art methods while retaining up to 92% accuracy with only 20% of the KV cache budget. |
Towards Robust k-Nearest-Neighbor Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | k-Nearest-Neighbor Machine Translation (kNN-MT) is a popular research paradigm in machine translation. |
| Approach: | They propose a confidence-enhanced kNN-MT model with robust training to reduce noise . they introduce NMT confidence to refine the modeling of important components of kN-MT . |
| Outcome: | The proposed model improves on four benchmark datasets and is robust to training. |
The Lower The Simpler: Simplifying Hierarchical Recurrent Models (N19-1)
Copied to clipboard
| Challenge: | Using a simplified version of GRU, we replace the GRUs at the middle layers of hierarchical recurrent models with Fixed-size Ordinally-Forgetting Encoding (FOFE). |
| Approach: | They propose to make the lower layers simpler than the upper ones to simplify two typical hierarchical recurrent models, namely Hierarchical Recurrent Encoder-Decoder (HRED) and R-NET, whose basic building block is GRU. |
| Outcome: | The proposed models contain less trainable parameters, consume less training time, and achieve slightly better performance than baseline models. |