Papers by Qun Liu

Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification (2025.acl-long)

Challenge:	Experimental results show that pretrained language models generate inconsistent factual knowledge in many conversational tasks.
Approach:	They propose a method which explicitly introduces extended feedforward networks (FFNs) in Transformers to enhance factual knowledge expressions given the specific patterns of knowledge-grounded dialogue inputs.
Outcome:	The proposed methods improve the factual expression capability of feedforward networks (FFNs) in knowledge-grounded dialogue systems by knowledge enhancement and alignment respectively.

Copied to clipboard

Chengwu Liu, Ye Yuan, Yichun Yin, Yan Xu, Xin Xu, Zaoyu Chen, Yasheng Wang, Lifeng Shang, Qun Liu, Ming Zhang

Decomposable Neural Paraphrase Generation (P19-1)

Challenge:	Chain-of-Thought prompting is a de facto method to elicit reasoning capabilities from large language models (LLMs).
Approach:	They propose a step-aware formal verification framework Safe to address hallucinations in CoT prompting . they propose 'formal step' as a benchmark for step correctness theorem proving with 30,809 formal statements.
Outcome:	The proposed framework shows significant performance improvement while offering interpretable and verifiable evidence.

Copied to clipboard

Zichao Li, Xin Jiang, Lifeng Shang, Qun Liu

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training (2021.emnlp-main)

Challenge:	Existing models learn to generate paraphrases by mapping a sequence to another, with each word processed and generated in a uniform way.
Approach:	They propose a Transformer-based model that can learn and generate paraphrases at different levels of granularity in a disentangled way.
Outcome:	The proposed model achieves competitive in-domain performance compared to state-of-the-art models and significantly better performance when adapting to a new domain.

Copied to clipboard

Minghao Wu, Yitong Li, Meng Zhang, Liangyou Li, Gholamreza Haffari, Qun Liu

Hierarchical Memory Organization for Wikipedia Generation (2025.acl-long)

Challenge:	MultiUAT dynamically adjusts training data usage based on model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Approach:	They propose an approach that dynamically adjusts the training data usage based on the model’s uncertainty on a small set of trusted clean data for multi-corpus machine translation.
Outcome:	The proposed approach outperforms baselines on 16 languages and 2 domains on English-German translation.

Copied to clipboard

Eugene J. Yu, Dawei Zhu, Yifan Song, Xiangyu Wong, Jiebin Zhang, Wenxuan Shi, Xiaoguang Li, Qun Liu, Sujian Li

Challenge:	Existing methods for generating Wikipedia articles do not utilize memory directly for outline generation.
Approach:	They propose a method to generate Wikipedia articles autonomously by leveraging a hierarchical memory architecture.
Outcome:	The proposed framework outperforms baseline methods in producing informative and reliable articles.

LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework (2022.findings-naacl)

Copied to clipboard

Mengjie Zhao, Fei Mi, Yasheng Wang, Minglei Li, Xin Jiang, Qun Liu, Hinrich Schuetze

How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis (2022.findings-acl)

Challenge:	Recent work shows that large-scale pretrained language models (PLMs) are effective few-shot learners.
Approach:	They propose a method that treats few-shotlearners as crowdsourcing workers . they propose to use these workers to train models that solve a task well .
Outcome:	The proposed approach treats few-shotlearners as crowdsourcing workers . the resulting annotations can be utilized to train models that solve the task well .

Copied to clipboard

Shaobo Li, Xiaoguang Li, Lifeng Shang, Zhenhua Dong, Chengjie Sun, Bingquan Liu, Zhenzhou Ji, Xin Jiang, Qun Liu

Learning to Jointly Translate and Predict Dropped Pronouns with a Shared Reconstruction Mechanism (D18-1)

Challenge:	Recent studies show that pre-trained language models can fill in the missing factual words in cloze-style prompts such as ”Dante was born in [MASK]” .
Approach:	They propose to quantitatively measure and evaluate the word-level patterns that PLMs depend on to generate the missing factual words.
Outcome:	The proposed model fills in the missing factual words in cloze-style prompts by relying on effective clues or shortcut patterns.

Copied to clipboard

Longyue Wang, Zhaopeng Tu, Andy Way, Qun Liu

G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks (2022.emnlp-main)

Challenge:	Pronouns are often omitted in pro-drop languages, such as Chinese . this leads to various translation problems in terms of completeness, syntax and semantics .
Approach:	They propose a reconstruction-based approach to alleviate dropped pronoun (DP) translation problems for neural machine translation models by employing a shared reconstructor and a joint learning approach.
Outcome:	The proposed approach improves translation performance and accuracy of DP predictions.

Copied to clipboard

Zhongwei Wan, Yichun Yin, Wei Zhang, Jiaxin Shi, Lifeng Shang, Guangyong Chen, Xin Jiang, Qun Liu

mCLIP: Multilingual CLIP via Cross-lingual Transfer (2023.acl-long)

Challenge:	Existing domain-adaptive pre-training (DAPT) models tend to forget the general knowledge acquired by general PLMs, leading to catastrophic forgetting and sub-optimal performance.
Approach:	They propose a framework which augments the domain-specific PLM by a memory built from the frozen general PLM without losing the general knowledge.
Outcome:	The proposed framework augments the domain-specific PLM by a memory built from the frozen general PLM without losing the general knowledge.

Copied to clipboard

Guanhua Chen, Lu Hou, Yun Chen, Wenliang Dai, Lifeng Shang, Xin Jiang, Qun Liu, Jia Pan, Wenping Wang

Refining Source Representations with Relation Networks for Neural Machine Translation (C18-1)

Challenge:	Existing multilingual vision-language pretrained models are biased towards English due to the lack of sufficient non-English image-text pairs.
Approach:	They propose to train a retrieval-efficient dual-stream multilingual VLP model by aligning CLIP model and a multilingual text encoder through a novel Triangle Cross-modal Knowledge Distillation method.
Outcome:	Empirical results show that mCLIP achieves new state-of-the-art performance for both zero-shot and finetuned multilingual image-text retrieval tasks.

Copied to clipboard

Wen Zhang, Jiawei Hu, Yang Feng, Qun Liu

Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editing (2025.acl-long)

Challenge:	Existing neural machine translation frameworks that forget distant information and disregard relationship between source and target words are not effective.
Approach:	They propose to use relation networks to learn better representations of the source . they propose to associate source words with each other to help retain their relationships .
Outcome:	Experiments show that the proposed approach outperforms the encoder-decoder framework on several datasets.

Copied to clipboard

Kaishuai Xu, Tiezheng Yu, Wenjun Hou, Yi Cheng, Chak Tou Leong, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li

MINER: Multi-Interest Matching Network for News Recommendation (2022.findings-acl)

Challenge:	Existing studies to improve mathematical ability typically involve applying preference learning to step-wise solution pairs, but they overlook critical subtle errors.
Approach:	They propose a preference learning framework that injects predefined subtle errors into pivotal tokens to construct hard pairs for error mitigation.
Outcome:	Extensive experiments show that the proposed framework improves on Qwen2-7B-Instruct and MATH with 4.5K training samples.

Copied to clipboard

Jian Li, Jieming Zhu, Qiwei Bi, Guohao Cai, Lifeng Shang, Zhenhua Dong, Xin Jiang, Qun Liu

Representation Learning

Challenge:	Existing methods learn a single user embedding from user’s historical behaviors to represent the reading interest.
Approach:	They propose a poly attention scheme to learn multiple interest vectors for each user, which encodes the different aspects of user interest.
Outcome:	The proposed approach significantly outperforms existing state-of-the-art methods on the MIND news recommendation benchmark.

LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling (2022.emnlp-main)

Copied to clipboard

Dongsheng Chen, Chaofan Tao, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu

COPEN: Probing Conceptual Knowledge in Pre-trained Language Models (2022.emnlp-main)

Challenge:	Recent large-scale video-language pre-trained models have shown appealing performance on downstream tasks.
Approach:	They propose a video-text model that adapts a pre-trained image-language model into a text-based model without heavy pre-training.
Outcome:	The proposed model outperforms existing models on video-text retrieval and video question answering tasks without heavy pre-training.

Copied to clipboard

Hao Peng, Xiaozhi Wang, Shengding Hu, Hailong Jin, Lei Hou, Juanzi Li, Zhiyuan Liu, Qun Liu

A Mutual Information Maximization Approach for the Spurious Solution Problem in Weakly Supervised Question Answering (2021.acl-long)

Challenge:	Existing knowledge probing studies focus on evaluating factual knowledge of pre-trained language models (PLMs) but ignore conceptual knowledge.
Approach:	They evaluate conceptual knowledge of pre-trained language models by annotating 24k data instances covering 393 concepts.
Outcome:	The proposed tasks evaluate pre-trained language models' conceptual knowledge of entities, learn conceptual properties, and conceptualize entities in contexts.

Copied to clipboard

Zhihong Shao, Lifeng Shang, Qun Liu, Minlie Huang

WIKIGENBENCH:Exploring Full-length Wikipedia Generation under Real-World Scenario (2025.coling-main)

Challenge:	Weakly supervised question answering usually has only final answers as supervision signals while correct solutions are not provided.
Approach:	They propose to explicitly exploit the semantic correlations between question-answer pairs and predicted answers by maximizing mutual information between question and answer pairs.
Outcome:	The proposed method significantly outperforms previous learning methods in terms of task performance and is more effective in training models to produce correct solutions.

Copied to clipboard

Jiebin Zhang, Eugene J. Yu, Qinyu Chen, Chenhao Xiong, Dawei Zhu, Han Qian, Mingbo Song, Weimin Xiong, Xiaoguang Li, Qun Liu, Sujian Li

ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer (2022.acl-long)

Challenge:	Existing efforts to generate Wikipedia articles for new events fall short of real-world application.
Approach:	They propose a benchmark to generate Wikipedia articles for new events under real-world scenarios . they use systematic metrics and LLM-based metrics to assess verifiability, organization, and other aspects aligned with real-life scenarios.
Outcome:	The proposed benchmarks show that hierarchical-based methods generate more comprehensive content while fine-tuned methods achieve better verifiability.

Copied to clipboard

Ningning Wang, Guobing Gan, Peng Zhang, Shuai Zhang, Junqiu Wei, Qun Liu, Xin Jiang

MTRec: Multi-Task Learning over BERT for News Recommendation (2022.findings-acl)

Challenge:	Existing sparse attention methods use fixed patterns to select words without considering similarities between words.
Approach:	They propose a neural clustering method which integrates into the Self-Attention Mechanism in Transformer and integrates it into the target task.
Outcome:	The proposed method outperforms two typical sparse attention methods on translation, text classification, and text matching tasks while having a comparable or even better time and memory efficiency.

Copied to clipboard

Qiwei Bi, Jian Li, Lifeng Shang, Xin Jiang, Qun Liu, Hanfang Yang

HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management (2021.findings-acl)

Challenge:	Existing news recommendation methods learn news representations solely based on news titles. Existing methods only utilize title information and neglect other valuable news information such as categories and entities.
Approach:	They propose a multi-task method to incorporate multi-field information into BERT, which improves its news encoding capability.
Outcome:	Extensive experiments on the MIND news recommendation benchmark show the proposed method is effective.

Copied to clipboard

Silin Gao, Ryuichi Takanobu, Wei Peng, Qun Liu, Minlie Huang

Structured Pruning for Efficient Generative Pre-trained Language Models (2023.findings-acl)

Challenge:	Task-oriented dialog systems typically manage structured knowledge to guide goal-oriented conversations.
Approach:	They propose a TOD system with hybrid knowledge management, HyKnow, which extends the belief state to manage both structured and unstructured knowledge.
Outcome:	The proposed model outperforms existing TOD systems in the evaluation of a multiWOZ dataset on unstructured knowledge with strong end-to-end performance.

Copied to clipboard

Chaofan Tao, Lu Hou, Haoli Bai, Jiansheng Wei, Xin Jiang, Qun Liu, Ping Luo, Ngai Wong

REIC: RAG-Enhanced Intent Classification at Scale (2025.emnlp-industry)

Challenge:	Large-scale generative Pre-trained Language Models (PLMs) are limited in their deployment in real-world applications.
Approach:	They propose to prune the feed-forward networks of generative pre-trained language models to smaller widths without designing extra operators.
Outcome:	The proposed method achieves 1.51x/6.96x inference speedup on GPU/CPU with 67% size reduction.

Copied to clipboard

Ziji Zhang, Michael Yang, Zhiyu Chen, Yingying Zhuang, Shu-Ting Pi, Qun Liu, Rajashekar Maragoud, Vy Nguyen, Anurag Beniwal

Information Retrieval

Challenge:	Accurate intent classification is critical for efficient routing in customer service . however, as companies expand their product lines, intent classification faces scalability challenges .
Approach:	They propose a retrieval-augmented generation Enhanced Intent Classification approach which leverages retrieval augmented generation to integrate relevant knowledge into a model.
Outcome:	The proposed approach outperforms fine-tuning, zero-shot, and few-shot methods on real-world datasets.

Compression of Generative Pre-trained Language Models via Quantization (2022.acl-long)

Copied to clipboard

Chaofan Tao, Lu Hou, Wei Zhang, Lifeng Shang, Xin Jiang, Qun Liu, Ping Luo, Ngai Wong

Two Parents, One Child: Dual Transfer for Low-Resource Neural Machine Translation (2021.findings-acl)

Challenge:	Existing methods to compress generative pre-trained language models fail on generative tasks due to homogeneous word embeddings and limited memory.
Approach:	They propose a token-level contrastive distillation method to learn distinguishable word embeddings and a module-wise dynamic scaling method to make quantizers adaptive to different modules.
Outcome:	The proposed method outperforms the state-of-the-art compression methods on generative PLMs by a clear margin.

Copied to clipboard

Meng Zhang, Liangyou Li, Qun Liu

Word-level Textual Adversarial Attacking as Combinatorial Optimization (2020.acl-main)

Challenge:	Neural machine translation suffers when parallel data is scarce for training . a new framework to transfer multiple sources of auxiliary data is proposed .
Approach:	They propose a framework to transfer multiple sources of auxiliary data from high-resource parallel data to low-resourced translation models using pretrained language models.
Outcome:	The proposed approach yields consistent improvements over strong competitors for multiple translation directions.

Copied to clipboard

Yuan Zang, Fanchao Qi, Chenghao Yang, Zhiyuan Liu, Meng Zhang, Qun Liu, Maosong Sun

Robustness in NLP

Challenge:	Existing word-level attack models are far from perfect because of unsuitable search space reduction methods and inefficient optimization algorithms.
Approach:	They propose a novel adversarial adversarialist model that incorporates word substitution and particle swarm optimization to solve two problems separately.
Outcome:	The proposed model achieves much higher success rates and crafts more high-quality adversarial examples as compared to baseline methods.

Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers (2020.emnlp-main)

Copied to clipboard

Yimeng Wu, Peyman Passban, Mehdi Rezagholizadeh, Qun Liu

GhostBERT: Generate More Features with Cheap Operations for BERT (2021.acl-long)

Challenge:	Existing knowledge distillation techniques are not suitable for deep learning tasks due to memory constraints.
Approach:	They propose to combine knowledge from a large teacher network into a student network (S) they propose to use a combinatorial mechanism to inject layer-level supervision from T to S .
Outcome:	The proposed model outperforms existing models in PortugueseEnglish, TurkishEnglish and EnglishGerman directions and students trained using it have 50% fewer parameters and can deliver comparable results to 12-layer teachers.

Copied to clipboard

Zhiqi Huang, Lu Hou, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu

Sub-Character Tokenization for Chinese Pretrained Language Models (2023.tacl-1)

Challenge:	Existing studies show that some parameters in pre-trained language models can be pruned away without severe accuracy degradation.
Approach:	They propose a method which generates more features with very cheap operations from the remaining features and can be applied to unpruned BERT models to enhance their performance.
Outcome:	Empirical results on the GLUE benchmark on three backbone models (i.e., BERT, RoBERTa and ELECTRA) verify the efficacy of the proposed method.

Copied to clipboard

Chenglei Si, Zhengyan Zhang, Yingfa Chen, Fanchao Qi, Xiaozhi Wang, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun

AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models (2023.acl-short)

Challenge:	Existing tokenization methods for Chinese PLMs treat each character as an indivisible token, but ignore the unique feature of the writing system where additional linguistic information exists below the character level.
Approach:	They propose to encode Chinese characters into short sequences and construct Chinese vocabulary based on the encoded text.
Outcome:	The proposed tokenizers can tokenize inputs into much shorter sequences, improving computational efficiency.

Copied to clipboard

Siheng Li, Cheng Yang, Yichun Yin, Xinyu Zhu, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering (2023.acl-long)

Challenge:	Existing research on information-seeking conversations is stymied by the lack of training data.
Approach:	They propose to use autoconv for synthetic conversation generation to capture the characteristics of the information-seeking process and fine tune an LLM with a few human conversations to generate synthetic conversations with high quality.
Outcome:	The proposed model improves on two commonly-used datasets and alleviates the dependence on human annotation.

Copied to clipboard

Pei Ke, Fei Huang, Fei Mi, Yasheng Wang, Qun Liu, Xiaoyan Zhu, Minlie Huang

One Cannot Stand for Everyone! Leveraging Multiple User Simulators to train Task-oriented Dialogue Systems (2023.acl-long)

Challenge:	Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability.
Approach:	They propose a metric that evaluates natural language generation tasks as an instruction-style question answering task and utilizes instruction-tuned pre-trained language models without training on evaluation datasets.
Outcome:	The proposed metric achieves state-of-the-art performance in untrained metrics for evaluating text summarization and dialogue generation, which exhibits strong dimension-level / task-level generalization ability and interpretability.

Copied to clipboard

Yajiao Liu, Xin Jiang, Yichun Yin, Yasheng Wang, Fei Mi, Qun Liu, Xiang Wan, Benyou Wang

Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning (2025.emnlp-main)

Challenge:	Recent studies have found that Task-oriented Dialogue systems can be more suitable for human users.
Approach:	They propose a framework to optimize ToD systems by leveraging Multiple User SimulaTors.
Outcome:	The proposed framework improves performance on multiWOZ with human evaluations and automatic evaluations.

Copied to clipboard

Yunhao Gou, Hansi Yang, Zhili Liu, Kai Chen, Yihan Zeng, Lanqing Hong, Zhenguo Li, Qun Liu, Bo Han, James Kwok, Yu Zhang

Controlled Text Generation Using Dictionary Prior in Variational Autoencoders (2022.findings-acl)

Challenge:	Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), but its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content and poor OCR quality.
Approach:	They propose a corruption-robust training paradigm that surpasses existing strategies for mitigating the effects of corrupted data.
Outcome:	The proposed training paradigm surpasses existing strategies for mitigating the effects of corrupted data.

Copied to clipboard

Xianghong Fang, Jian Li, Lifeng Shang, Xin Jiang, Qun Liu, Dit-Yan Yeung

BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models (2020.findings-emnlp)

Challenge:	Variational autoencoders (VAEs) have been widely applied in text generation tasks, but they suffer from insufficient representation capacity and poor controllability.
Approach:	They propose a data-driven prior that has expressivity and controllability.
Outcome:	The proposed prior enjoys expressivity and controllability and can be used in language modeling and controlled text generation.

Copied to clipboard

Bin He, Di Zhou, Jinghui Xiao, Xin Jiang, Qun Liu, Nicholas Jing Yuan, Tong Xu

FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models (2022.findings-naacl)

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 .

Copied to clipboard

Yinpeng Guo, Liangyou Li, Xin Jiang, Qun Liu

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression (2025.findings-emnlp)

Challenge:	Existing work on cross-lingual transfer has not studied how to leverage knowledge of rich-resource languages without labels.
Approach:	They propose a 2-step knowledge distillation framework to achieve knowledge transfer from off-the-shelf models in rich-resource languages.
Outcome:	The proposed method reduces annotation cost and protects private labels.

Copied to clipboard

Jiebin Zhang, Dawei Zhu, Yifan Song, Wenhao Wu, Chuqiao Kuang, Xiaoguang Li, Lifeng Shang, Qun Liu, Sujian Li

Challenge:	storing more tokens in the KV cache at lower precision can enhance the long-context performance of large language models.
Approach:	They propose a token-precision trade-off strategy to optimize KV cache compression . they also propose storing more tokens in the KV at lower precision .
Outcome:	The proposed method achieves an optimal point within the Information Bottleneck compared to standalone KV pruning or KV quantization.

DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling (2021.emnlp-main)

Copied to clipboard

Baojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao, Yuyang Zhang, Lifeng Shang, Linlin Li, Xiao Chen, Xin Jiang, Qun Liu

Don’t Shoot The Breeze: Topic Continuity Model Using Nonlinear Naive Bayes With Attention (2024.emnlp-industry)

Challenge:	Existing approaches to integrate lexical knowledge into deep learning models are limited by large-scale dynamic lexicons.
Approach:	They propose a plug-in lexicon incorporation approach for BERT based sequence labeling tasks . they adopt word-agnostic tag embeddings to avoid re-training the representation .
Outcome:	The proposed framework achieves new SOTA even with large scale lexicons, the authors show . they adopt word-agnostic tag embeddings to avoid re-training the representation .

Copied to clipboard

Shu-Ting Pi, Pradeep Bagavan, Yejia Li, Disha Disha, Qun Liu

Explainability & Interpretability in NLP

Challenge:	Large-scale language models (LLMs) are becoming increasingly popular in business scenarios, but maintaining topic continuity is a challenge.
Approach:	They propose a topic continuity model that assesses whether a response aligns with the initial conversation topic using a Naive Bayes approach.
Outcome:	The proposed model outperforms existing models in handling lengthy and complex conversations.

Read before Generate! Faithful Long Form Question Answering with Machine Reading (2022.findings-acl)

Copied to clipboard

Dan Su, Xiaoguang Li, Jindi Zhang, Lifeng Shang, Xin Jiang, Qun Liu, Pascale Fung

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Challenge:	Long-form question answering (LFQA) generates a paragraph-length answer for a given question.
Approach:	They propose a framework that jointly models answer generation and machine reading.
Outcome:	The proposed model generates a more factually accurate answer from millions of documents retrieved from a large dataset.

Copied to clipboard

Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026.acl-long)

Challenge:	Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach:	They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome:	The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.

Copied to clipboard

Ziyi Wang, Yuxuan Lu, Yimeng Zhang, Pei Chen, Ziwei Dong, Jing Huang, Jiri Gesi, Xianfeng Tang, Chen Luo, Qun Liu, Yisi Sang, Hanqing Lu, Manling Li, Jin Lai, Dakuo Wang

Knowledge Diffusion for Neural Dialogue Generation (P18-1)

Challenge:	Tool-calling agents are increasingly deployed in real-world customer-facing workflows . but most studies on tool-callers focus on idealized settings with general, fixed, and well-specified tasks.
Approach:	They propose a tool-calling agent-based data pipeline that converts trajectories into user-facing tasks with controlled intent adaptations.
Outcome:	The proposed pipeline can be used to study tool use under three scenarios.

Copied to clipboard

Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, Dawei Yin

HyperText: Endowing FastText with Hyperbolic Geometry (2020.findings-emnlp)

Challenge:	End-to-end neural dialogue generation does not employ knowledge to guide the generation.
Approach:	They propose a neural knowledge diffusion model to introduce knowledge into dialogue generation.
Outcome:	The proposed model outperforms baseline models on a real-world dataset.

Copied to clipboard

Yudong Zhu, Di Zhou, Jinghui Xiao, Xin Jiang, Xiao Chen, Qun Liu

Information Extraction & Text Mining

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.

Accurate Word Alignment Induction from Neural Machine Translation (2020.emnlp-main)

Copied to clipboard

Yun Chen, Yang Liu, Guanhua Chen, Xin Jiang, Qun Liu

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Challenge:	Prior work suggests that Transformer captures poor word alignments through its attention mechanism.
Approach:	They propose two new word alignment induction methods that use attention weights to capture accurate word alignments.
Outcome:	The proposed methods outperform baselines on three publicly available datasets and are significantly better than GIZA++.

Copied to clipboard

Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu

Revisiting Robust Neural Machine Translation: A Transformer Case Study (2021.findings-emnlp)

Challenge:	Existing solutions for visual document understanding lack granularity of document textlines.
Approach:	They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome:	The proposed system performs better on various VDU tasks in English and Chinese.

Copied to clipboard

Peyman Passban, Puneeth Saladi, Qun Liu

The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation (2020.findings-emnlp)

Challenge:	Recent advances in NMT have shown promising results but are vulnerable to noise.
Approach:	They propose a data-driven technique called Target Augmented Fine-tuning to incorporate noise during training.
Outcome:	The proposed techniques perform with no degradation where up to 10% of entire test words are infected by noise.

Copied to clipboard

Jie He, Tao Wang, Deyi Xiong, Qun Liu

BinaryBERT: Pushing the Limit of BERT Quantization (2021.acl-long)

Challenge:	a test suite to evaluate commonsense reasoning capability of neural machine translation is presented . language models pretrained on large-scale corpora achieve a commonsensing accuracy of lower than 72% on target translations of this test suite.
Approach:	They propose a test suite to evaluate the commonsense reasoning capability of neural machine translation.
Outcome:	The proposed test suite performs poorly on commonsense reasoning of the three ambiguity types in terms of reasoning accuracy and reasoning consistency.

Copied to clipboard

Haoli Bai, Wei Zhang, Lu Hou, Lifeng Shang, Jin Jin, Xin Jiang, Qun Liu, Michael Lyu, Irwin King

Tailoring Neural Architectures for Translating from Morphologically Rich Languages (C18-1)

Challenge:	Recent pre-trained language models have achieved remarkable performance improvement in various tasks, but the improvement generally comes at the cost of increasing model size and computation.
Approach:	They propose a binary quantization technique which initializes binaryBERT by splitting from a ternary network.
Outcome:	The proposed model achieves state-of-the-art performance on the GLUE and SQUAD benchmarks while being 24x smaller.

Copied to clipboard

Peyman Passban, Andy Way, Qun Liu

SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme (2023.findings-acl)

Challenge:	A morphologically complex word is a hierarchical constituent with meaning-preserving subunits, so word-based models which rely on surface forms might not be powerful enough to translate such structures.
Approach:	They propose a neural architecture which is designed to deal with morphological complexities on the source side and redesign the decoder accordingly to benefit from such information.
Outcome:	The proposed model outperforms existing subword- and character-based architectures and showed significant improvements on translating from German, Russian, and Turkish into English.

Copied to clipboard

Yusen Sun, Liangyou Li, Qun Liu, Dit-Yan Yeung

“Knowing When You Don’t Know”: A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation (2024.findings-emnlp)

Challenge:	Existing methods of generating singable lyrics are based on a given melody, but there are two main challenges: generating the lyrics without knowing the melody and composing compatible melodies.
Approach:	They propose a Chinese lyric generation and editing system which rewrites lyrics of an existing song such that they are compatible with the rhythm of the existing melody.
Outcome:	The proposed system is based on a randomized multi-level masking strategy and can generate new lyrics or edit fragments without prior knowledge of melody composition.

Copied to clipboard

Nandan Thakur, Luiz Bonifacio, Crystina Zhang, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Boxing Chen, Mehdi Rezagholizadeh, Jimmy Lin

Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order (2020.acl-main)

Challenge:	Prior work on RAG grounds Large Language Models to reduce factual hallucinations lacks a comprehensive evaluation of different language families.
Approach:	They propose a human-annotated dataset for evaluating LLM robustness in RAG . they find that most models struggle to balance the two capacities .
Outcome:	The proposed dataset includes both a non-relevant and a relevant subset.

Copied to clipboard

Yi Liao, Xin Jiang, Qun Liu

Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoning (2025.emnlp-main)

Challenge:	Large-scale pretrained language models such as masked language model (MLM) have brought significant improvements to many NLU and NLG tasks.
Approach:	They propose a probabilistic masking scheme for the masked language model and a model with a uniform prior distribution on the masking ratio.
Outcome:	The proposed model outperforms BERT on a bunch of downstream NLG tasks.

Copied to clipboard

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Yufei Wang, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages (2023.tacl-1)

Challenge:	Existing methods that use Chain-of-Thought suffer from path homogenization and inefficient use of intermediate results.
Approach:	They propose a framework that introduces checkpoints between reasoning steps to reduce path homogenization and create fault-tolerant mechanisms.
Outcome:	The proposed framework reduces path homogenization and creates fault-tolerant mechanism by utilizing high-quality intermediate results.

Copied to clipboard

Xinyu Zhang, Nandan Thakur, Odunayo Ogundepo, Ehsan Kamalloo, David Alfonso-Hermelo, Xiaoguang Li, Qun Liu, Mehdi Rezagholizadeh, Jimmy Lin

From Script to Stage: Automating Experimental Design for Social Simulations with LLMs (2026.findings-acl)

Challenge:	MIRACL is a multilingual dataset for ad hoc retrieval across 18 languages that collectively encompass over three billion native speakers around the world.
Approach:	They have gathered over 726k high-quality relevance judgments for 78k queries over Wikipedia in these languages, where all annotations have been performed by native speakers hired by their team.
Outcome:	MIRACL covers languages that are typologically close as well as distant from 10 language families and 13 sub-families, associated with varying amounts of publicly available resources.

Copied to clipboard

Yuwei Guo, Zihan Zhao, Xiaowei Liu, Xiangning Yu, Qun Ma, Deyu Zhou, Xiao Xue

Challenge:	Xu et al., 2024): multi-agent simulations based on large language models are a new paradigm for social science research . traditional experimental design relies on interdisciplinary expertise and technical barriers . Xiaoping and Xin eli argue that LLM-driven agents are unreliable for rigorous experimental design due to hallucinations and limited verifiability.
Approach:	They propose a framework for multi-agent experiment design based on script generation . Script Composition, Script Finalization, and Actor Generation are the core phases of the framework .
Outcome:	The proposed framework lowers the barrier for social science experimental design and provides scientifically grounded decision support for policy-making.

Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk (2024.emnlp-main)

Copied to clipboard

Zhiyuan Zeng, Qipeng Guo, Xiaoran Liu, Zhangyue Yin, Wentao Shu, Mianqiu Huang, Bo Wang, Yunhua Zhou, Linlin Li, Qun Liu, Xipeng Qiu

Green & Sustainable NLP

Challenge:	Existing methods to optimize LLM for long sequences for long documents are slow and consume memory.
Approach:	They propose a method that starts with a small memory size and gradually increases it . they propose Decremental Chunk based on Incremental Memory (IMDC) which reduces chunk size while increasing memory size .
Outcome:	The proposed method is faster (1.45x) and reduces GPU memory consumption by 23.3% compared to fixed-size memory.

AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation (2023.findings-emnlp)

Copied to clipboard

Xingshan Zeng, Liangyou Li, Qun Liu

RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer (2021.findings-acl)

Challenge:	End-to-end speech translation (ST) models need large amount of training data to perform well.
Approach:	They propose a shrinking mechanism to mitigate the length mismatch between speech and text features by predicting word boundaries.
Outcome:	The proposed method achieves better performance on the MUST-C dataset, with higher inference speed and lower memory usage.

Copied to clipboard

Xingshan Zeng, Liangyou Li, Qun Liu

Universal Conditional Masked Language Pre-training for Neural Machine Translation (2022.acl-long)

Challenge:	End-to-end simultaneous speech translation (SST) is useful in many scenarios but has not been fully investigated.
Approach:	They propose an end-to-end simultaneous speech translation model called RealTranS . they use interleaved convolution and unidirectional Transformer layers to downsample input speech .
Outcome:	The proposed model outperforms existing models on public and widely-used datasets in multiple latency settings.

Copied to clipboard

Pengfei Li, Liangyou Li, Meng Zhang, Minghao Wu, Qun Liu

Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation (2022.coling-1)

Challenge:	Pre-trained sequence-to-sequence models have significantly improved Neural Machine Translation (NMT) this paper demonstrates that pre-training a sequence- to-squence model with a bidirectional decoder can produce notable performance gains for both Autoregressive and Non-autoregressive NMT tasks.
Approach:	They propose a conditional masked language model pre-trained on bilingual and monolingual corpora in many languages.
Outcome:	The proposed model can achieve significant performance improvements on all scenarios from low- to extremely high-resource languages.

Copied to clipboard

Yihe Wang, Yitong Li, Yasheng Wang, Fei Mi, Pingyi Zhou, Xin Wang, Jin Liu, Xin Jiang, Qun Liu

Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing (2022.emnlp-main)

Challenge:	Existing methods for generating open-domain dialogue systems underutilize training data.
Approach:	They propose a retrieval-generation training framework that takes advantage of heterogeneous training data by considering them as "evidence" they use BERTScore retrieval framework which gives better qualities of the training data, they show .
Outcome:	The proposed method performs well on zero-shot experiments and is more robust to real-world data.

Copied to clipboard

Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Phillippe Langlais

LLM-Based Dialogue Labeling for Multiturn Adaptive RAG (2025.emnlp-industry)

Challenge:	Existing pre-trained language models are not well-explored and are not reproducible in the literature.
Approach:	They propose to improve existing Arabic language pre-trained language models using a more methodical approach.
Outcome:	The proposed models outperform existing models on ALUE, a leaderboard-powered benchmark for Arabic NLU and NLG tasks.

Copied to clipboard

Zhiyu Chen, Biancen Xie, Sidarth Srinivasan, Manikandarajan Ramanathan, Rajashekar Maragoud, Qun Liu

HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks (2023.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) models integrate large language models with external knowledge retrieval . however, building multi-turn RAG-based chatbots for real-world customer service requires additional complexities.
Approach:	They propose methods to automatically generate labels for adaptive retrieval components using real customer-agent dialogue data.
Outcome:	The proposed method generates labels for components using real customer-agent dialogue data.

Copied to clipboard

Zhengkun Zhang, Wenya Guo, Xiaojun Meng, Yasheng Wang, Yadao Wang, Xin Jiang, Qun Liu, Zhenglu Yang

Learning to Edit: Aligning LLMs with Knowledge Editing (2024.acl-long)

Challenge:	Pretraining and fine-tuning are the dominant paradigms in natural language processing.
Approach:	They propose a parameter-efficient multitask learning framework that takes trainable hyper-embeddings and visual modality as input and outputs weights for different modules in a pretrained language model.
Outcome:	The proposed framework adds fewer trainable parameters in multi-task learning while achieving superior performances and transfer ability compared to state-of-the-art methods.

Copied to clipboard

Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang

Challenge:	Existing knowledge editing techniques rely on memorizing updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions.
Approach:	They propose a Learning to Edit framework that equips LLMs with the ability to apply updated knowledge to input questions through a two-phase process .
Outcome:	The proposed framework outperforms existing methods in knowledge editing tasks and compares it with four benchmarks and two LLM architectures.

Generate & Rank: A Multi-task Framework for Math Word Problems (2021.findings-emnlp)

Copied to clipboard

Jianhao Shen, Yichun Yin, Lin Li, Lifeng Shang, Xin Jiang, Ming Zhang, Qun Liu

FPT: Improving Prompt Tuning Efficiency via Progressive Training (2022.findings-emnlp)

Challenge:	Existing studies formalize MWP as a generation task but mathematical expressions are prone to minor mistakes.
Approach:	They propose a ranking task for math word problem (MWP) that learns from its own mistakes and distinguishes between correct and incorrect expressions.
Outcome:	The proposed model outperforms baselines on the classical Math23k dataset and is 7% higher than the state-of-the-art.

Copied to clipboard

Yufei Huang, Yujia Qin, Huadong Wang, Yichun Yin, Maosong Sun, Zhiyuan Liu, Qun Liu

Gradually Excavating External Knowledge for Implicit Complex Question Answering (2023.findings-emnlp)

Challenge:	Recent prompt tuning (PT) has gained increasing attention as a parameter-efficient way of tuning pre-trained language models (PLMs).
Approach:	They propose a prompt tuning algorithm that uses a small-scale partial PLM and progressively expands its depth and width until the full-model size.
Outcome:	The proposed method could save over 30% of training computations while achieving comparable performance.

Copied to clipboard

Chang Liu, Xiaoguang Li, Lifeng Shang, Xin Jiang, Qun Liu, Edmund Lam, Ngai Wong

Prompt-Based Length Controlled Generation with Multiple Control Types (2024.findings-acl)

Challenge:	Large language models (LLMs) have gained attention for their human-comparable capabilities but they may not solve open-domain implicit questions due to out-of-date domain knowledge, one-shot generation and restricted comprehensiveness.
Approach:	They propose a gradual knowledge excavation framework for open-domain complex question answering using extrinsic knowledge and historical knowledge.
Outcome:	The proposed framework achieves 78.17% accuracy with less than 6% parameters of its competitors, setting new SOTA in the 10B LLM class.

Copied to clipboard

Renlong Jie, Xiaojun Meng, Lifeng Shang, Xin Jiang, Qun Liu

Low-Resource NLP

Challenge:	Existing length control methods focus on a simple control type of “equal to” a target length.
Approach:	They propose a prompt-based method to achieve length controlled generation under different control types with high accuracy by using reinforcement learning and sample filtering with the reward signal given by rule-based reward models.
Outcome:	The proposed method significantly improves the accuracy of prompt-based length control on popular summarization datasets like CNNDM and NYT under multiple control types.

Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT (2020.acl-main)

Copied to clipboard

Zhiyong Wu, Yun Chen, Ben Kao, Qun Liu

Improving Domain Adaptation Translation with Domain Invariant and Specific Information (N19-1)

Challenge:	Recent pre-trained language models achieve state-of-the-art performance for downstream NLP tasks.
Approach:	They propose a parameter-free probing technique for analyzing pre-trained language models . their method does not require direct supervision from probing tasks .
Outcome:	The proposed method improves on linguistically-uninformed baselines on pre-trained language models.

Copied to clipboard

Shuhao Gu, Yang Feng, Qun Liu

Pre-training Language Models with Deterministic Factual Knowledge (2022.emnlp-main)

Challenge:	Neural machine translation models are based on the encoder-decoder architecture, which makes them overfitting to frequent observations.
Approach:	They propose a method to explicitly model out-of-domain information in an encoder-decoder framework . they propose combining out- of-domain training data with out-out-of domain data .
Outcome:	The proposed method outperforms baselines on multiple data sets.

Copied to clipboard

Shaobo Li, Xiaoguang Li, Lifeng Shang, Chengjie Sun, Bingquan Liu, Zhenzhou Ji, Xin Jiang, Qun Liu

Triangular Transfer: Freezing the Pivot for Triangular Machine Translation (2022.acl-short)

Challenge:	Existing studies show that Pre-trained Language Models fail to capture factual knowledge robustly.
Approach:	They propose to let PLMs learn the deterministic relationship between context and masked content to improve their ability to capture factual knowledge.
Outcome:	The proposed methods improve accuracy and consistency of factual knowledge capturing and boost performance of other knowledge-intensive tasks.

Copied to clipboard

Meng Zhang, Liangyou Li, Qun Liu

TernaryBERT: Distillation-aware Ultra-low Bit BERT (2020.emnlp-main)

Challenge:	Existing approaches to triangular machine translation have not fully exploited all types of auxiliary data.
Approach:	They propose a transfer-learning-based approach that utilizes all types of auxiliary data.
Outcome:	The proposed approach outperforms existing approaches with a series of experiments.

Copied to clipboard

Wei Zhang, Lu Hou, Yichun Yin, Lifeng Shang, Xiao Chen, Xin Jiang, Qun Liu

MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions (2023.acl-long)

Challenge:	Transformer-based pre-training models like BERT are computationally expensive and limited to resource-constrained devices.
Approach:	They propose a method which ternarizes the weights in a fine-tuned BERT model.
Outcome:	The proposed method outperforms the other methods on the GLUE and SQUAD benchmarks while being 14.9x smaller.

Copied to clipboard

Hao Sun, Zhexin Zhang, Fei Mi, Yasheng Wang, Wei Liu, Jianwei Cui, Bin Wang, Qun Liu, Minlie Huang

ProxyQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models (2024.acl-long)

Challenge:	A moral dialogue system aligned with users’ values could enhance conversation engagement and user connections.
Approach:	They propose a framework to train and evaluate moral dialogue systems based on communication mechanisms of morality and a method to construct moral discussions between simulated users and the dialogue system.
Outcome:	The proposed framework can train and evaluate moral dialogue systems based on simulated users and their values .

Copied to clipboard

Haochen Tan, Zhijiang Guo, Zhan Shi, Lu Xu, Zhili Liu, Yunlong Feng, Xiaoguang Li, Yasheng Wang, Lifeng Shang, Qun Liu, Linqi Song

Self-Supervised Quality Estimation for Machine Translation (2021.emnlp-main)

Challenge:	Existing evaluation methods for large language models are labor-intensive and lack efficiency.
Approach:	They propose a framework dedicated to assessing long-text generation that includes in-depth human-curated meta-questions spanning various domains . they use a set of proxy-quests with pre-annotated answers to assess the content's quality by incorporating the generated texts as contextual background.
Outcome:	The proposed framework assesses the quality of long-text content by matching it with references through human evaluation or automated metrics.

Copied to clipboard

Yuanhang Zheng, Zhixing Tan, Meng Zhang, Mieradilijiang Maimaiti, Huanbo Luan, Maosong Sun, Qun Liu, Yang Liu

ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis (2025.naacl-long)

Challenge:	Training QE models require massive parallel data with hand-crafted quality annotations, which are time-consuming and labor-intensive to obtain.
Approach:	They propose a self-supervised method to evaluate machine-translated sentences without references by recovering masked target words.
Outcome:	The proposed method outperforms previous unsupervised methods on several QE tasks in different language pairs and domains.

Copied to clipboard

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

Document Graph for Neural Machine Translation (2021.emnlp-main)

Challenge:	Large Language Models (LLMs) can be enhanced by using supervised fine-tuning . however, access to fine-timing data can be limited.
Approach:	They propose a Graph-based Sampling strategy and a Planned-generation strategy to enhance the coherence between dialogues by using 8,000 synthetic dialogues.
Outcome:	The proposed model achieves tool-calling performance comparable to or surpassing GPT-4 while maintaining strong general capabilities.

Copied to clipboard

Mingzhou Xu, Liangyou Li, Derek F. Wong, Qun Liu, Lidia S. Chao

FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (2024.acl-long)

Challenge:	Existing document-level NMT methods fail to leverage contexts beyond a few set of previous sentences.
Approach:	They propose to represent a document as a graph that connects relevant contexts regardless of distances.
Outcome:	Experiments on IWSLT English–French, Chinese-English, WMT English–German and Opensubtitle English–Russian show that using document graphs can significantly improve translation quality.

Copied to clipboard

Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang

bert2BERT: Towards Reusable Pretrained Language Models (2022.acl-long)

Challenge:	Existing benchmarks focus on evaluating pure response quality, rather than assessing whether the response follows constraints stated in the instruction.
Approach:	They propose a Multi-level Fine-grained Constraints Following Benchmark for Large Language Models that adds a single constraint to the initial instruction at each increased level.
Outcome:	The proposed model can follow instructions with more constraints, and is deemed to have better instruction-following ability.

Copied to clipboard

Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu, Qun Liu

Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation (2022.findings-acl)

Challenge:	Pre-training large language models can be expensive and wasteful.
Approach:	They propose a method which can transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and a two-stage learning method to further accelerate the pre-training.
Outcome:	The proposed method can transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and significantly improve the pre-training efficiency of the large model.

Copied to clipboard

Wenliang Dai, Lu Hou, Lifeng Shang, Xin Jiang, Qun Liu, Pascale Fung

Chain-of-Probe: Examining the Necessity and Accuracy of CoT Step-by-Step (2025.findings-naacl)

Challenge:	Recent large-scale vision-language pre-training models are powerful in multimodal classification and retrieval tasks.
Approach:	They propose to augment a vision-language pre-training model with a textual pre-trained language model . the model achieves 44.5% zero-shot accuracy on multimodal generation tasks .
Outcome:	The proposed model achieves 44.5% zero-shot accuracy on open-ended visual question answering and image captioning tasks.

Copied to clipboard

Zezhong Wang, Xingshan Zeng, Weiwen Liu, Yufei Wang, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

Improving Character-Based Decoding Using Target-Side Morphological Information for Neural Machine Translation (N18-1)

Challenge:	Current research found the issue of Early Answering in large language models where the models already have an answer before generating the Chain-of-Thought (CoT).
Approach:	They propose a method to probe changes in confidence during the model’s reasoning and prioritize answers with correct reasoning among multiple candidates.
Outcome:	The proposed method reveals that in a significant number of question-answer cases, CoT appears to be unnecessary and this necessity correlates with the simplicity of the task, defined by the reasoning steps required.

Copied to clipboard

Peyman Passban, Qun Liu, Andy Way

CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search (2024.emnlp-main)

Challenge:	Morphologically complex words (MCWs) are multi-layer structures consisting of different subunits, each of which carries semantic information and has a specific syntactic role.
Approach:	They propose an extension to the state-of-the-art model which works at the character level and boosts the decoder with target-side morphological information.
Outcome:	The proposed model improves on the state-of-the-art model and can be extended to include morphologically complex words (MCWs) in three languages.

Copied to clipboard

Fengran Mo, Abbas Ghaddar, Kelong Mao, Mehdi Rezagholizadeh, Boxing Chen, Qun Liu, Jian-Yun Nie

Paraphrasing

Challenge:	Recent advances in task-solving capabilities of Large Language Models (LLMs) have motivated researchers to integrate these models into existing conversational search systems.
Approach:	They propose a method that leverages the capabilities of large language models to resolve ambiguities in conversation history before query rewriting.
Outcome:	The proposed method leads to state-of-the-art results across most settings compared with closed-source LLMs.

Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework (2025.findings-acl)

Copied to clipboard

Kaishuai Xu, Tiezheng Yu, Yi Cheng, Wenjun Hou, Liangyou Li, Xin Jiang, Lifeng Shang, Qun Liu, Wenjie Li

Robustness in NLP

Challenge:	Existing methods for fine-tuning open-source LLMs are limited to text-based analysis under predefined general criteria.
Approach:	They propose a framework that fine-tunes LLMs to replicate the evaluation explanations and judgments of proprietary models.
Outcome:	The proposed evaluation framework outperforms existing fine-tuned evaluation methods in effectiveness and robustness.

Speeding Up Neural Machine Translation Decoding by Cube Pruning (D18-1)

Copied to clipboard

Wen Zhang, Liang Huang, Yang Feng, Lei Shen, Qun Liu

Towards Identifying Social Bias in Dialog Systems: Framework, Dataset, and Benchmark (2022.findings-emnlp)

Challenge:	Neural machine translation suffers from slow translation speed due to the large search space . a trade-off has to be made between translation quality and speed, argues a new study .
Approach:	They apply cube pruning technique to speed up dynamic programming into neural machine translation to speed it up.
Outcome:	The proposed method can translate faster on GPUs and CPUs with better translation quality than naive beam search.

Copied to clipboard

Jingyan Zhou, Jiawen Deng, Fei Mi, Yitong Li, Yasheng Wang, Minlie Huang, Xin Jiang, Qun Liu, Helen Meng

Compilable Neural Code Generation with Compiler Feedback (2022.findings-acl)

Challenge:	a number of safety concerns hinder the deployment of open-domain dialog systems, such as offensive languages and toxic behaviors, such social bias is difficult to detect.
Approach:	They propose a Dial-Bias Framework for analyzing social bias in conversations . they introduce a Chinese social bias dialog dataset and conduct in-depth ablation studies .
Outcome:	The proposed framework is the first annotated Chinese social bias dialog dataset . the proposed framework also provides a fine-grained dialog bias measurement benchmark .

Copied to clipboard

Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, Jin Liu, Hao Wu, Xin Jiang, Qun Liu

Programming Languages in NLP

Challenge:	Existing deep-learning approaches model code generation as text generation, but few of them account for compilability of the generated programs.
Approach:	They propose a three-stage pipeline utilizing compiler feedback for compilable code generation to improve compilability.
Outcome:	The proposed pipeline improves compilability of generated programs by combining compiler feedback, language model fine-tuning, and compilable discrimination.

TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models (2021.acl-long)

Copied to clipboard

Jie He, Bo Peng, Yi Liao, Qun Liu, Deyi Xiong

Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Challenge:	Using pretrained language models, we propose an error-annotated dataset for text generation . we use carefully selected prompt words to guide GPT-2 to generate candidate sentences .
Approach:	They propose an error-annotated dataset with multiple benchmark tasks for text generation from pretrained language models.
Outcome:	The proposed dataset covers 24 types of errors according to common sense and linguistics.

Copied to clipboard

Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip Yu, Zhijiang Guo

Robustness in NLP

Challenge:	Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach:	They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome:	The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.

A General Framework for Adaptation of Neural Machine Translation to Simultaneous Translation (2020.aacl-main)

Copied to clipboard

Yun Chen, Liangyou Li, Xin Jiang, Xiao Chen, Qun Liu

TinyBERT: Distilling BERT for Natural Language Understanding (2020.findings-emnlp)

Challenge:	Despite the success of neural machine translation, simultaneous neural machine translators are challenging due to syntactic structure difference and simultaneity requirements.
Approach:	They propose a framework for adapting neural machine translation to translate simultaneously . they propose 'prefix translation' that utilizes a consecutive NMT model to translate source prefixes .
Outcome:	The proposed framework balancing quality and latency on three translation corpora and two language pairs shows that it performs well.

Copied to clipboard

Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, Qun Liu

LFED: A Literary Fiction Evaluation Dataset for Large Language Models (2024.lrec-main)

Challenge:	Pre-trained language models are computationally expensive and difficult to efficiently execute on resource-restricted devices.
Approach:	They propose a Transformer distillation method that performs Transformer distillations at pre-training and task-specific learning stages.
Outcome:	The proposed method accelerates inference and reduces model size while maintaining accuracy.

Copied to clipboard

Linhao Yu, Qun Liu, Deyi Xiong

Bridging the Gap between Training and Inference for Neural Machine Translation (P19-1)

Challenge:	LFED is a literary fiction evaluation dataset for large language models that evaluate the capability of LLMs on the long fiction comprehension and reasoning.
Approach:	They propose a Literary Fiction Evaluation Dataset to evaluate LLMs' comprehension and reasoning on long fictions.
Outcome:	The proposed dataset evaluates the capability of large language models on the long fiction comprehension and reasoning.

Copied to clipboard

Wen Zhang, Yang Feng, Fandong Meng, Di You, Qun Liu

Improving Unsupervised Question Answering via Summarization-Informed Question Generation (2021.emnlp-main)

Challenge:	Neural Machine Translation generates target words sequentially while at inference it has to generate the entire sequence from scratch.
Approach:	They propose to use ground truth and inference to generate target words sequentially while at inference it has to generate the entire sequence from scratch.
Outcome:	Experiments on Chinese->English and WMT’14 English->German translation tasks show that the proposed model can achieve significant improvements on multiple datasets.

Copied to clipboard

Chenyang Lyu, Lifeng Shang, Yvette Graham, Jennifer Foster, Xin Jiang, Qun Liu

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios (2024.findings-acl)

Challenge:	Question Generation (QG) is the production of meaningful questions given a set of input passages and corresponding answers.
Approach:	They propose a method which uses questions generated heuristically from news summaries as a source of training data for a QG system.
Outcome:	The proposed method outperforms previous unsupervised models on three in-domain datasets and three out-of-domain ones.

Copied to clipboard

Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu

Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context (2021.emnlp-main)

Challenge:	Existing benchmarks focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization.
Approach:	They propose a benchmark to evaluate LLMs’ ability in tool utilization within real-world scenarios.
Outcome:	The proposed benchmark improves LLMs’ ability in tool utilization within real-world scenarios and eliminates the restriction of pre-defined toolset.

Copied to clipboard

Huibin Ge, Chenxi Sun, Deyi Xiong, Qun Liu

Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-Alignment (2025.acl-long)

Challenge:	Existing datasets for word prediction with long-range context have not been tested.
Approach:	They propose automatic and manual selection strategies tailored to Chinese to ensure that target words can only be predicted with long-term context.
Outcome:	The proposed model is 45 points behind human in terms of top-1 word prediction accuracy.

Copied to clipboard

Zhili Liu, Yunhao Gou, Kai Chen, Lanqing Hong, Jiahui Gao, Fei Mi, Yu Zhang, Zhenguo Li, Xin Jiang, Qun Liu, James Kwok

NewsDialogues: Towards Proactive News Grounded Conversation (2023.findings-acl)

Challenge:	Recent studies show that reasoning abilities contribute significantly to model safety, while integrating Mixture-of-Experts (MoE) architectures can further enhance alignment.
Approach:	They propose a framework that synergistically combines reasoning chains and expert mixtures to improve self-alignment.
Outcome:	The proposed framework improves model safety, jailbreak resistance, and over-refusal capabilities, achieving performance comparable to OpenAI’s state-of-the-art o1 model.

Copied to clipboard

Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning (2021.findings-acl)

Challenge:	Hot news is one of the most popular topics in daily conversations.
Approach:	They propose a task where a dialogue system can lead the conversation based on key topics of the news.
Outcome:	The proposed method can lead conversations based on key topics of the news . it can also be used in information-seeking and chit-chat scenarios .

Copied to clipboard

Chenglei Si, Zhengyan Zhang, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun

EWEK-QA : Enhanced Web and Efficient Knowledge Graph Retrieval for Citation-based Question Answering Systems (2024.acl-long)

Challenge:	Pretrained language models perform poorly under adversarial attacks due to the large search space.
Approach:	They propose a method to cover a much larger proportion of the attack search space by adding textual adversarial examples during training.
Outcome:	The proposed method covers a much larger proportion of the attack search space.

Copied to clipboard

Mohammad Dehghan, Mohammad Alomrani, Sunyam Bagga, David Alfonso-Hermelo, Khalil Bibi, Abbas Ghaddar, Yingxue Zhang, Xiaoguang Li, Jianye Hao, Qun Liu, Jimmy Lin, Boxing Chen, Prasanna Parthasarathi, Mahdi Biparva, Mehdi Rezagholizadeh

ERNIE: Enhanced Language Representation with Informative Entities (P19-1)

Challenge:	citation-based QA systems are suffering from two shortcomings . they usually rely only on web as a source of extracted knowledge and external knowledge sources can hamper the efficiency of the system.
Approach:	They propose to use a web-based knowledge graph retrieval solution to enrich extracted knowledge fed to a citation-based QA system.
Outcome:	The proposed model outperforms open-source state-of-the-art models in 7 quantitative and human evaluation tasks.

Copied to clipboard

Zhengyan Zhang, Xu Han, Zhiyuan Liu, Xin Jiang, Maosong Sun, Qun Liu

Neural Machine Translation with Heterogeneous Topic Knowledge Embeddings (2021.emnlp-main)

Challenge:	Existing pre-trained language models rarely consider incorporating knowledge graphs (KGs) Existing models capture rich semantic patterns from plain text and can be fine-tuned to improve performance of NLP tasks.
Approach:	They propose to incorporate knowledge graphs into pre-trained language models to enhance language representation with external knowledge.
Outcome:	The proposed model can take full advantage of lexical, syntactic, and knowledge information simultaneously.

Copied to clipboard

Weixuan Wang, Wei Peng, Meng Zhang, Qun Liu

Modeling Semantic Compositionality with Sememe Knowledge (P19-1)

Challenge:	Existing NMT models can handle meaning ambiguities based on local contexts, but it remains a challenge to translate words in implicit collocations.
Approach:	They propose heterogeneous ways of embedding topic information into NMT models . they propose to incorporate topic knowledge embeddable into the NMT model .
Outcome:	The proposed methods outperform baselines on English -> German and English => French translation tasks.

Copied to clipboard

Fanchao Qi, Junjie Huang, Chenghao Yang, Zhiyuan Liu, Xiao Chen, Qun Liu, Maosong Sun

MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models (2024.emnlp-main)

Challenge:	Semantic compositionality (SC) is defined as the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents.
Approach:	They propose to incorporate sememes into SC models and employ them in learning multiword expressions.
Outcome:	The proposed models achieve significant performance boost compared to baseline methods without sememe knowledge.

Copied to clipboard

Wai-Chung Kwan, Xingshan Zeng, Yuxin Jiang, Yufei Wang, Liangyou Li, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong

AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models (2021.acl-long)

Challenge:	Existing evaluation frameworks focus on single-turn evaluations, overlooking the models’ capabilities in multi-turn interactions.
Approach:	They propose a benchmark to evaluate the multi-turn conversational abilities of large language models (LLMs) by analyzing human-LLM conversations and constructing multi-turned queries for each category using GPT-4.
Outcome:	The proposed model outperforms open-source models in multi-turn tasks while retaining and recalling historical information.

Copied to clipboard

Yichun Yin, Cheng Chen, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)

Challenge:	Pre-trained language models (PLMs) have achieved great success in natural language processing.
Approach:	They propose a method that automatically searches architecture hyper-parameters in BERT . they use one-shot learning and the search space to provide an adaptive development way .
Outcome:	The proposed method outperforms both the baseline and distillation-based methods on GLUE and SQUAD benchmarks.

Copied to clipboard

Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen

Achieving Reliable Human Assessment of Open-Domain Dialogue Systems (2022.acl-long)

Challenge:	Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance.
Approach:	They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents.
Outcome:	The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain.

Copied to clipboard

Tianbo Ji, Yvette Graham, Gareth Jones, Chenyang Lyu, Qun Liu