Papers by Xiaojun Quan
A Deep Neural Information Fusion Architecture for Textual Network Embeddings (D19-1)
Copied to clipboard
| Challenge: | Textual network embeddings aim to learn a low-dimensional representation for every node in the network while seeking to retain the original network information. |
| Approach: | They propose a deep neural architecture to fuse the two kinds of informations into one representation. |
| Outcome: | The proposed model outperforms the comparing methods on all three datasets. |
Knowledge Verification to Nip Hallucination in the Bud (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models generate responses that sound plausible but contradict factual knowledge, a phenomenon known as hallucination. |
| Approach: | They propose a novel approach to align large language models to evaluate knowledge boundaries based on external knowledge to reduce hallucinations . |
| Outcome: | The proposed approach reduces hallucinations across six benchmarks using foundation LLMs of varying backbones and scales. |
AD-KD: Attribution-Driven Knowledge Distillation for Language Model Compression (2023.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge distillation methods focus on the transfer of model-specific knowledge but overlook data-specific information. |
| Approach: | They propose an attribution-driven knowledge distillation approach which explores the token-level rationale behind the teacher model and transfers attribution knowledge to the student model. |
| Outcome: | The proposed method outperforms state-of-the-art methods on the GLUE benchmark and shows that it is more efficient than existing methods. |
Cool-Fusion: Fuse Large Language Models without Training (2025.acl-long)
Copied to clipboard
| Challenge: | Cool-Fusion is a simple yet effective approach to combine two or more heterogeneous large language models . |
| Approach: | They propose a method that fuses the knowledge of two or more heterogeneous large language models to leverage complementary strengths. |
| Outcome: | The proposed method increases accuracy from three strong source LLMs on GSM8K by 17.4%. |
SocialBench: Sociality Evaluation of Role-Playing Conversational Agents (2024.findings-acl)
Copied to clipboard
Hongzhan Chen, Hehong Chen, Ming Yan, Wenshen Xu, Gao Xing, Weizhou Shen, Xiaojun Quan, Chenliang Li, Ji Zhang, Fei Huang
| Challenge: | Existing studies on role-playing agents have focused on enhancing their conversational capability, role-specific knowledge and style, but there has been a gap in assessing their social intelligence. |
| Approach: | They propose a benchmark to evaluate the sociality of role-playing agents using LLMs. |
| Outcome: | The proposed benchmark is constructed from various sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. |
Psycholinguistic Tripartite Graph Network for Personality Detection (2021.acl-long)
Copied to clipboard
| Challenge: | Existing work on personality detection from online posts adopts multifarious deep neural networks to represent the posts and builds predictive models in a data-driven manner without the exploitation of psycholinguistic knowledge. |
| Approach: | They propose a psycholinguistic knowledge-based tripartite graph network, TrigNet, which consists of a tripartitic graph network and a BERT-based graph initializer. |
| Outcome: | The proposed graph network outperforms the existing state-of-the-art model by 3.47 and 2.10 points in average F1 on two datasets. |
Mutual-Taught for Co-adapting Policy and Reward Models (2025.acl-long)
Copied to clipboard
Tianyuan Shi, Canbin Huang, Fanqi Wan, Longguang Zhong, Ziyi Yang, Weizhou Shen, Xiaojun Quan, Ming Yan
| Challenge: | Experimental results show that this iterative approach leads to consistent improvements in both the policy model and reward model. |
| Approach: | They propose a method that iteratively improves both the policy model and reward model without requiring additional human annotation. |
| Outcome: | The proposed method improves both the policy model and reward model without human annotation. |
Low-Resource Generation of Multi-hop Reasoning Questions (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to generate valid and fluent questions from text are limited and insufficient for training. |
| Approach: | They propose to generate multi-hop reasoning questions from the raw text in a low resource circumstance by deducing over multiple relations on several sentences in the text. |
| Outcome: | The proposed model can be applied to the task of machine reading comprehension and achieve significant performance improvements. |
Edit-Wise Preference Optimization for Grammatical Error Correction (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been successful in grammatical error correction (GEC) but their strengths have yet to be fully demonstrated in GEC . |
| Approach: | They propose a method to optimize grammatical errors by assigning higher reward weights to edit tokens during preference optimization. |
| Outcome: | The proposed method outperforms baselines on English and Chinese datasets and achieves state-of-the-art performance. |
ThinkSwitcher: When to Think Hard, When to Think Fast (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large reasoning models excel at solving complex tasks by leveraging long chain-of-thought (CoT) reasoning. |
| Approach: | They propose a framework that enables a single LRM to dynamically switch between short and long CoT modes based on task complexity. |
| Outcome: | The proposed framework reduces computational cost by 20-30% while maintaining high accuracy on complex tasks. |
Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent years have seen a rapid growth of interest in building task-oriented dialogue systems. |
| Approach: | They propose a retrieve-and-memorize framework to deal with unbalanced distribution of system actions in dialogue datasets. |
| Outcome: | The proposed framework achieves competitive performance among state-of-the-art models on a large-scale task-oriented dialogue dataset. |
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have revolutionized natural language processing with impressive capabilities, but they lack domain specificity, real-time information and face challenges in solving specialized problems. |
| Approach: | They propose a multi-LLM approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer. |
| Outcome: | The proposed model outperforms existing models by demonstrating its effectiveness and advantages in tool learning. |
Clustering-Aware Negative Sampling for Unsupervised Sentence Representation (2023.findings-acl)
Copied to clipboard
| Challenge: | Using clustering-aware learning, in-batch negatives are often ignored in sentence representation learning. |
| Approach: | They propose a method that integrates cluster information into contrastive learning for unsupervised sentence representation learning. |
| Outcome: | The proposed method compares favorably with baselines on semantic textual similarity tasks. |
Constituency Lattice Encoding for Aspect Term Extraction (2020.coling-main)
Copied to clipboard
| Challenge: | a challenge for aspect term extraction is to extract phrase-level aspect terms . a constituency lattice structure is constructed using the span annotations of constituents of a sentence . |
| Approach: | They propose to incorporate the span annotations of constituents of a sentence to leverage syntactic information in neural network models. |
| Outcome: | The proposed model outperforms existing models on two benchmark datasets. |
MUSTIE: Multimodal Structural Transformer for Web Information Extraction (2023.acl-long)
Copied to clipboard
Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Zenglin Xu, Shaoliang Nie, Sinong Wang, Madian Khabsa, Hamed Firooz, Dongfang Liu
| Challenge: | Recent sequential modeling approaches focus on extracting information from textual sources while ignoring rich information from other modalities such as image and web layout. |
| Approach: | They propose a novel MUltimodal Structural Transformer that integrates multiple modalities for web information extraction. |
| Outcome: | The proposed model outperforms existing methods on WebSRC and Common Crawl benchmarks. |
Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems (2023.emnlp-main)
Copied to clipboard
| Challenge: | Current approaches to task-oriented dialogue systems integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with extensive knowledge bases. |
| Approach: | They propose a retriever-generator architecture that harnesses a retrieval and a generator to generate system responses by using feedback from the generator as pseudo-labels. |
| Outcome: | The proposed architecture shows superior performance on three benchmark datasets. |
Learning to Answer Psychological Questionnaire for Personality Detection (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing text-based personality detection research relies on data-driven approaches to implicitly capture personality cues in online posts lacking the guidance of psychological knowledge. |
| Approach: | They propose a model to capture key information in texts and a questionnaire to help the user to make a personality assessment. |
| Outcome: | The proposed model captures key information in texts and a questionnaire and can be used to improve personality prediction. |
Self-Evolution Fine-Tuning for Policy Optimization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent years have showcased the remarkable capabilities and performance of large language models (LLMs) across a broad range of tasks. |
| Approach: | They propose supervised fine-tuning (SEFT) for LLM alignment to eliminate the need for annotated samples while retaining the stability and efficiency of SFT. |
| Outcome: | The proposed method eliminates the need for annotated samples while maintaining the stability and efficiency of SFT. |
Joint Generator-Ranker Learning for Natural Language Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text generation train the generator and ranker individually . existing methods neglect the mutual feedback that could enhance the quality of outputs . |
| Approach: | They propose a joint training algorithm that integrates the generator and ranker in a single framework. |
| Outcome: | The proposed algorithm surpasses existing methods on four public datasets across three common generation scenarios. |
Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Aspect term extraction is a task to extract aspect terms from review texts as opinion targets for sentiment analysis. |
| Approach: | They propose a conditional generation task for augmentation of aspect term extraction . they use a sequence-to-sequence method that generates a new sentence . results confirm that their method alleviates the data scarcity problem significantly . |
| Outcome: | The proposed method reduces the data scarcity problem significantly and boosts current models. |
PsyCoT: Psychological Questionnaire as Powerful Chain-of-Thought for Personality Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have demonstrated remarkable zero-shot performance across various NLP tasks. |
| Approach: | They propose a method which mimics the way individuals complete psychological questionnaires in a multi-turn dialogue manner and prompts an LLM to rate individual items at each turn. |
| Outcome: | The proposed method improves the performance and robustness of the standard GPT-3.5 personality detection task on two benchmark datasets. |
Autoregressive Entity Generation for End-to-End Task-Oriented Dialog (2022.coling-1)
Copied to clipboard
| Challenge: | Task-oriented dialog systems require external knowledge base to generate a response . current systems require scanning the KB at each turn, which is inefficient when the kb scales up . |
| Approach: | They propose to generate entity autoregressively before leveraging it to guide response generation. |
| Outcome: | Experiments on MultiWOZ 2.1 single and CAMREST show that the proposed system generates more high-quality and entity-consistent responses in an end-to-end manner. |
Bi-Granularity Contrastive Learning for Post-Training in Few-Shot Scene (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to fine-tune pre-trained models to downstream tasks are limited by labeled examples. |
| Approach: | They propose to apply post-training on unlabeled task data before fine-tuning by contrastive learning that considers either token-level or sequence-level similarity. |
| Outcome: | Empirical results show that contrastive masked language modeling surpasses other methods in few-shot settings without the need for data augmentation. |
ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on proactive dialogue models focus on domain-specific or task-oriented scenarios, which leads to fragmented evaluations and limits the comprehensive exploration of models’ proactive dialogue abilities. |
| Approach: | They propose a framework for evaluating proactive dialogue capabilities of large language models that decomposes proactive dialogue into target planning and dialogue guidance, establishing evaluation metrics across various domains. |
| Outcome: | The proposed framework decomposes proactive dialogue into target planning and dialogue guidance, establishing evaluation metrics across various domains, and enables automatic generation of diverse and challenging evaluation data. |
MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction (2023.findings-acl)
Copied to clipboard
Li Yang, Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Yu Chen, Madian Khabsa, Sinong Wang, Zenglin Xu, Dongfang Liu
| Challenge: | Existing methods for product attribute value extraction focus on extracting values for a set of known attributes with sufficient training data. |
| Approach: | They propose a prompt tuning approach to extract attributes from product information using mixed prompts. |
| Outcome: | The proposed approach improves on two product benchmarks and shows parameter-efficient training and avoids model overfitting. |
Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Exploration (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing data for instruction-tuning are inadequate for a wide range of tasks, limiting the scope for nuanced comprehension and interactions within these domains. |
| Approach: | They propose to use Large Language Models to explore a multitude of variations or possibilities to improve instruction-tuning data by active exploration. |
| Outcome: | The proposed approach improves domain-specific instruction coverage and shows significant improvements over baselines. |
FuseChat: Knowledge Fusion of Chat Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are costly and require significant computational resources and time. |
| Approach: | They propose a fuse-and-merge framework for the knowledge fusion of chat LLMs . they conduct pairwise knowledge fusing on source chat LRMs to create multiple target LLM . |
| Outcome: | The proposed framework is superior to baselines of various sizes. |
XPrompt: Exploring the Extreme of Prompt Tuning (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prompt tuning learns soft prompts to condition pre-trained Language Models for performing downstream tasks in a parameter-efficient manner. |
| Approach: | They propose a Prompt tuning model with an eXtremely small scale that learns soft prompts to condition the frozen Pre-trained Language Models for performing downstream tasks in a parameter-efficient manner. |
| Outcome: | The proposed model outperforms the vanilla Prompt-Tuning and can significantly improve across tasks and model scales. |
Embedding Dynamic Attributed Networks by Modeling the Evolution Processes (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods to embed nodes into low-dimensional vectors focus on static networks, but in practice, many networks are evolving over time and hence are dynamic, e.g., social networks. |
| Approach: | They propose to extract high-order neighborhood information at each given timestamp and then use an embedding prediction framework to capture the temporal correlations. |
| Outcome: | Extensive experiments on four real-world datasets show that the proposed method outperforms baseline methods for dynamic link prediction and node classification tasks. |
ReAlign: Structured Revision for Small Language Model Alignment (2025.findings-emnlp)
Copied to clipboard
| Challenge: | weak policies struggle to generate informative on-policy samples and suffer from unstable gradients when trained on off-police signals from stronger models. |
| Approach: | They propose a training framework that combines stability of on-policy learning with reviser-assisted supervision. |
| Outcome: | The proposed training framework outperforms strong preference optimization baselines on AlpacaEval-2 and Arena-Hard. |
Disentangled Phonetic Representation for Chinese Spelling Correction (2023.acl-long)
Copied to clipboard
| Challenge: | Chinese Spelling Correction (CSC) aims to detect and correct erroneous characters in Chinese sentences. |
| Approach: | They propose to integrate phonetic and character representations to allow interaction between textual and phonetic information. |
| Outcome: | The proposed method is superior to other methods on three benchmarks. |
Alirector: Alignment-Enhanced Chinese Grammatical Error Corrector (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to address overcorrection in Chinese grammatical error correction (CGEC) are difficult to adapt to decoder-only large language models (LLMs). |
| Approach: | They propose an alignment-enhanced corrector for the overcorrection problem that applies to both Seq2Seq models and decoder-only large language models (LLMs). |
| Outcome: | The proposed corrector alleviates the overcorrection problem in Chinese grammatical error correction (CGEC) using generative models and decoder-only large language models. |
APrompt: Attention Prompt Tuning for Efficient Adaptation of Pre-trained Language Models (2023.emnlp-main)
Copied to clipboard
Qifan Wang, Yuning Mao, Jingang Wang, Hanchao Yu, Shaoliang Nie, Sinong Wang, Fuli Feng, Lifu Huang, Xiaojun Quan, Zenglin Xu, Dongfang Liu
| Challenge: | Existing prompt tuning methods only introduce prompts at the input layer, limiting performance and leaving large room for improvement. |
| Approach: | They propose a method that involves tuning a small set of soft prompts for pre-trained language models. |
| Outcome: | The proposed method outperforms state-of-the-art methods with pre-trained models on the SuperGLUE benchmark. |
Syntax-Enhanced Pre-trained Model (2021.acl-long)
Copied to clipboard
Zenan Xu, Daya Guo, Duyu Tang, Qinliang Su, Linjun Shou, Ming Gong, Wanjun Zhong, Xiaojun Quan, Daxin Jiang, Nan Duan
| Challenge: | Existing methods that use syntax of text in pre-training and fine-tuning suffer from discrepancy between the two stages. |
| Approach: | They propose a model that utilizes the syntactic structure of text in pre-training and fine-tuning stages. |
| Outcome: | The proposed model achieves state-of-the-art on six public benchmark datasets. |
Multi-choice Relational Reasoning for Machine Reading Comprehension (2020.coling-main)
Copied to clipboard
| Challenge: | cloze-style reading comprehension is a task that requires much semantic understanding and reasoning using various clues from texts. |
| Approach: | They propose a multi-choice relational reasoning model that emulates human reading comprehension by combining fusion representations of document, query and candidates. |
| Outcome: | The proposed model outperforms baseline models significantly on four datasets. |
Directed Acyclic Graph Network for Conversational Emotion Recognition (2021.acl-long)
Copied to clipboard
| Challenge: | Empirical evidence shows that a good representation of conversation context significantly contributes to the model performance. |
| Approach: | They propose to encode query utterances with a directed acyclic graph to better model the intrinsic structure within a conversation. |
| Outcome: | The proposed model outperforms existing models on four ERC benchmarks with state-of-the-art models employed as baselines. |
BlockPruner: Fine-grained Pruning for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have significant computational and memory costs associated with training and inference. |
| Approach: | They propose a training-free structured pruning approach that targets redundancies in MHA and MLP blocks. |
| Outcome: | The proposed pruning approach achieves more granular and effective pruning compared to state-of-the-art pruning methods. |
Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System (2023.emnlp-main)
Copied to clipboard
| Challenge: | generative models struggle to distinguish subtle differences among retrieved knowledge records, resulting in suboptimal quality of generated responses. |
| Approach: | They propose to use maximum marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision. |
| Outcome: | The proposed approach improves on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models. |
Learning to Generate Question by Asking Question: A Primal-Dual Approach with Uncommon Word Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing automatic question generation methods focus on encoding passage and answer to generate question. |
| Approach: | They propose an automatic question generation approach which integrates question generation with its dual problem, question answering, into a unified primal-dual framework. |
| Outcome: | The proposed approach outperforms existing methods on SQuAD and HotpotQA benchmarks. |
Multi-Grained Knowledge Retrieval for End-to-End Task-Oriented Dialog (2023.acl-long)
Copied to clipboard
| Challenge: | Existing systems blend knowledge retrieval with response generation and optimize them with direct supervision from reference responses. |
| Approach: | They propose a multi-grained knowledge retrieval system that decouples knowledge retrievals from response generation and introduces an entity selector and an attribute selector to acquire multigrained information from the knowledge base. |
| Outcome: | The proposed system performs better on small and large knowledge bases. |
BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization (P19-1)
Copied to clipboard
| Challenge: | Abstractive summarization models are limited in size and noisy training data. |
| Approach: | They propose a bi-directional selective encoding with template model which leverages template from training data to softly select key information from each source article to guide its summarization process. |
| Outcome: | The proposed model improves the summarization performance significantly on a standard summarizing dataset. |
Multi-Domain Dialogue Acts and Response Co-Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing pipeline approaches for task-oriented dialogue systems tend to predict multiple dialogue acts first and use them to assist response generation. |
| Approach: | They propose a neural co-generation model that generates dialogue acts and responses concurrently and preserves semantic structures of multi-domain dialogue acts. |
| Outcome: | The proposed model improves over state-of-the-art models in automatic and human evaluations on a large-scale dataset. |
Relational Graph Attention Network for Aspect-based Sentiment Analysis (2020.acl-main)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis aims to determine the sentiment polarity towards a specific aspect in online reviews. |
| Approach: | They propose a relational graph attention network to encode a tree structure for sentiment prediction. |
| Outcome: | The proposed approach improves the performance of the graph attention network (GAT) on the SemEval 2014 and Twitter datasets. |
MCC-KD: Multi-CoT Consistent Knowledge Distillation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable abilities in complex reasoning through chain of thought (CoT) prompting. |
| Approach: | They propose to generate multiple rationales for each question and enforce consistency among their predictions by minimizing the bidirectional KL-divergence between the answer distributions. |
| Outcome: | The proposed model achieves superior performance on in-distribution and commonsense reasoning benchmarks. |
Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge (2020.acl-main)
Copied to clipboard
| Challenge: | Chinese word segmentation and part-of-speech tagging are important fundamental tasks in natural language processing. |
| Approach: | They propose a neural model for Chinese word segmentation and part-of-speech tagging . they incorporate context features and syntactic knowledge for each input character . |
| Outcome: | The proposed model can learn and benefit from existing tools, but its quality may be poor. |