Papers by Di Jiang
Augmenting Compliance-Guaranteed Customer Service Chatbots: Context-Aware Knowledge Expansion with Large Language Models (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Retrieval-based chatbots leverage human-verified Q&A knowledge to deliver accurate, verifiable responses. |
| Approach: | They propose a similar question generation task for LLM training and inference to enable comprehensive semantic exploration and enhanced alignment with source question-answer relationships. |
| Outcome: | The proposed methods achieve 92% user satisfaction rate in a deployed chatbot system, reflecting an 18% improvement over the baseline. |
IM^2: an Interpretable and Multi-category Integrated Metric Framework for Automatic Dialogue Evaluation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Evaluation metrics for dialogue systems are expensive and time-consuming . current evaluation metrics focus on a single quality or several qualities . |
| Approach: | They propose an interpretable, multi-faceted, and controllable framework to combine dialogue metrics which are good at measuring different qualities. |
| Outcome: | The proposed framework integrates a large number of evaluation metrics to improve the performance of the model. |
Parameter Importance is Not Static: Evolving Parameter Isolation for Supervised Fine-Tuning (2026.acl-long)
Copied to clipboard
Zekai Lin, Chao Xue, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Lei Jiang, Yu Lu, Bob Simons, Shuang Liang, Minlong Peng
| Challenge: | Recent approaches to fine-tuning of large language models suffer from task interference and catastrophic forgetting. |
| Approach: | They propose a fine-tuning framework that adapts isolation decisions based on online estimates of parameter importance. |
| Outcome: | The proposed framework reduces interference and forgetting while releasing outdated parameters to recover plasticity. |
Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models (2026.acl-long)
Copied to clipboard
Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim
| Challenge: | Incomplete learning is widespread and heterogeneous in large language models . authors identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between SFT supervision and pre-training knowledge, internal inconsistencies within SFT data, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns. |
| Approach: | They propose a diagnostic-first framework that maps incomplete learning to causes . they identify five recurrent sources of incomplete learning: missing prerequisite knowledge, conflicts between supervision and pre-training knowledge, internal inconsistencies, left-side forgetting during sequential fine-tuning, and insufficient optimization for rare or complex patterns. |
| Outcome: | The proposed framework maps incomplete learning to causes using observable training and inference signals. |
Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning (2022.aacl-main)
Copied to clipboard
| Challenge: | Recent language generative models are mostly trained on large-scale datasets, while in some real scenarios, the training datasets are often expensive and would be small-scale. |
| Approach: | They propose a novel duality fine-tuning method to capture more information from limited data and build connections between tasks. |
| Outcome: | The proposed method can capture more information from limited data, build connections between separate tasks, and is suitable for less-data constrained generation tasks. |
Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing intent clustering methods rely on embedding distance metrics and neglect of underlying semantic structures. |
| Approach: | They propose an LLM-in-the-loop framework that integrates language understanding capabilities into conventional clustering algorithms. |
| Outcome: | The proposed framework outperforms baselines in Chinese and improves quality, cost efficiency and downstream applications. |
BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing knowledge representation learning methods do not use graph contextualized knowledge. |
| Approach: | They propose to model subgraphs in a medical KG and integrate it with a pre-trained language model to do knowledge generalization. |
| Outcome: | The proposed model achieves state-of-the-art on several medical NLP tasks . it improves on MedERNIE, and the proposed model is effective . |
HyperText: Endowing FastText with Hyperbolic Geometry (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Empirically, we show that HyperText outperforms FastText on a range of text classification tasks with much reduced parameters. |
| Approach: | They propose a model that uses hyperbolic geometry to model tree-like hierarchies in natural language sentences by embedding words or ngrams in hyperbolical space. |
| Outcome: | Empirically, the proposed model outperforms FastText on a range of text classification tasks with much reduced parameters. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
Reason Only When Needed: Efficient Generative Reward Modeling via Model-Internal Uncertainty (2026.findings-acl)
Copied to clipboard
Chao Xue, Yao Wang, Mengqiao Liu, Di Liang, Xingsheng Han, Peiyang Liu, Xianjie Wu, Chenyao Lu, Lei Jiang, Yu Lu, Haibo Shi, Shuang Liang, Minlong Peng, Flora D. Salim
| Challenge: | Existing approaches to generating reward models rely on voting-based mechanisms to evaluate CoT outputs. |
| Approach: | They propose an efficient generative reward modeling framework grounded in model-internal uncertainty. |
| Outcome: | The proposed framework reduces inference cost while improving answer accuracy. |
Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to enhancing large language models fail to emphasize specific constraints and unlock the underlying knowledge. |
| Approach: | They propose a method that emphasizes specific constraints and unlocks knowledge within LLMs by iteratively emphasising on specific constraints. |
| Outcome: | The proposed method outperforms existing methods in enhancing generated content, especially in terms of specificity. |
Empathy Intent Drives Empathy Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Empathy is essential in human social interaction. |
| Approach: | They propose to annotate healthy empathy detection datasets IEMPATHIZE and TwittEmp with 8 empathy intent labels and perform joint training for the two tasks. |
| Outcome: | The proposed framework outperforms baselines on the two datasets. |
Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)
Copied to clipboard
Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen
| Challenge: | Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. |
| Approach: | They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
| Outcome: | The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs. |
RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods focus on sentencelevel event extraction (SEE), but they are inconsistent with actual situations. |
| Approach: | They propose a document-level event extraction framework which can model relation dependencies by a relation-augmented Attention Transformer. |
| Outcome: | The proposed framework can achieve state-of-the-art performance on two public datasets. |
QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks often lack domain coverage and provide limited insights into the working context of Chinese LLMs. |
| Approach: | They propose a multi-domain Chinese QA benchmark dedicated to localized assessment of Chinese LLMs. |
| Outcome: | The Qwen2.5 model outperforms the more advanced GPT-4o model in the Chinese market . the dataset includes over 17,000 questions across six vertical domains . |
LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning (2026.findings-acl)
Copied to clipboard
Zhengjun Huang, Zhoujin Tian, Qintian Guo, Fangyuan Zhang, Yingli Zhou, Di Jiang, Zeying Xie, Xiaofang Zhou
| Challenge: | Large Language Models are constrained by limited context windows and lack of persistent memory . recent efforts address these limitations via external memory architectures . |
| Approach: | They propose an end-to-end agentic memory framework for real-time updating and retrieval that integrates hierarchical and temporal indexing layers. |
| Outcome: | The proposed framework outperforms established benchmarks in temporal reasoning, multi-session consistency, and retrieval efficiency. |
Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) training with Mixture-of-Experts policies remains fragile and prone to reward collapse. |
| Approach: | They propose a router shift-based policy optimization method that computes a per-token router-shift ratio conditioned on the previously activated experts and applies stop-gradient and a lower-bound floor. |
| Outcome: | The proposed method achieves better performance and greater stability than previous methods. |
Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech (D19-3)
Copied to clipboard
| Challenge: | Language model adaptation (LMA) is a promising solution for conversational speech recognition systems. |
| Approach: | They propose to use language model adaptation techniques to adapt language models to conversational speech recognition. |
| Outcome: | The proposed toolkit compares state-of-the-art language model adaptation techniques in conversational speech recognition tasks. |
Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality (2024.findings-acl)
Copied to clipboard
Jiahuan Pei, Irene Viola, Haochen Huang, Junxiao Wang, Moonisa Ahsan, Fanghua Ye, Jiang Yiming, Yao Sai, Di Wang, Zhumin Chen, Pengjie Ren, Pablo Cesar
| Challenge: | a fine-grained, comprehensive understanding of multimodal environments remains under-explored. |
| Approach: | They propose an automated workflow for integrating AI agents into extended reality (XR) they propose a cerebral language agent that integrates LLM with memory, planning, and interaction with XR tools and a vision-language agent . |
| Outcome: | The proposed workflow integrates AI agents seamlessly into extended reality (XR) applications for fine-grained training. |
INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling (2025.findings-acl)
Copied to clipboard
Di Wu, Liting Jiang, Bohui Mao, Hongyan Xie, Haoxiang Su, Zhongjiang He, Ruiyu Fang, Shuangyong Song, Hao Huang, Xuelong Li
| Challenge: | Existing studies struggle to achieve performance comparable to that on high-resource languages due to inherent linguistic diversity of multilingual SLU tasks. |
| Approach: | They propose a multilingual information transfer network to solve these challenges . they propose to reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages. |
| Outcome: | The proposed model outperforms baseline models on the MASSIVE and MASSIV-UG datasets in overall accuracy across all languages. |
Dialogue Language Model with Large-Scale Persona Data Engineering (2025.naacl-industry)
Copied to clipboard
| Challenge: | Existing persona-consistent dialogue models lack robustness due to limited scale and diversity of datasets. |
| Approach: | They propose an open-domain persona dialogue system that employs extensive generative pre-training on a persona dialog dataset to enhance persona consistency. |
| Outcome: | The proposed model generates vast persona dialogue datasets and addresses invalid persona bias. |
ASR-EC Benchmark: Evaluating Large Language Models on Chinese ASR Error Correction (2025.emnlp-industry)
Copied to clipboard
| Challenge: | Automatic Speech Recognition (ASR) systems have a substantial number of erroneous recognition due to environmental noise, ambiguity, etc. |
| Approach: | They use a benchmark dataset to analyze ASR errors in the Chinese language . they then apply large language models to correct ASR error correction . |
| Outcome: | The proposed method is based on a dataset of ASR errors in the Chinese language . it shows prompting is not effective for ASR error correction . |
Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou
| Challenge: | Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging . |
| Approach: | They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning. |
| Outcome: | The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets. |