Papers by Sujian Li

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (2024.findings-emnlp)

Challenge:	Existing factual consistency metrics are often uncontrollably generating text that is factually inconsistent with inputs.
Approach:	They propose a weakly supervised framework that is directly trained on actual generated samples from language models with weakly annotated labels.
Outcome:	The proposed framework improves on the TRUE benchmark by 3.3% over existing methods with 435M parameters.

Copied to clipboard

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li

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

Challenge:	Existing studies focus on specialized agents designed for particular tasks.
Approach:	They propose to scale annotated interaction trajectories and fine-tune LLMs on AgentBank to get a series of agent models, Samoyed.
Outcome:	The proposed model can scale to get generalized agent capabilities.

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

Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning (D18-1)

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

Chen Shi, Qi Chen, Lei Sha, Sujian Li, Xu Sun, Houfeng Wang, Lintao Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing dialog datasets rely on human labeling, which is expensive, limited in size, and in low coverage.
Approach:	They propose a framework to automatically cluster dialogue intents and slots . they collect context features, leverage an autoencoder for feature assembly, and adapt a dynamic hierarchical clustering method for intent and slot labeling.
Outcome:	The proposed framework can promote human labeling cost to a great extent and achieve good intent clustering accuracy (84.1%) it also provides reasonable and instructive slot labeling results.

Do NLP Models Know Numbers? Probing Numeracy in Embeddings (D19-1)

Copied to clipboard

Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh, Matt Gardner

Exploring In-Context Learning for Knowledge Grounded Dialog Generation (2023.findings-emnlp)

Challenge:	Existing models cannot capture numeracy, but they can be useful for complex reasoning tasks.
Approach:	They investigate numerical reasoning capabilities of a question-answering model . they probe token embedding methods on synthetic list maximum, number decoding, and addition tasks.
Outcome:	The proposed model excels on questions that require numerical reasoning, i.e., it already captures numeracy.

Copied to clipboard

Qinyu Chen, Wenhao Wu, Sujian Li

Dialogue Systems & Conversational Agents

Challenge:	Existing knowledge grounded dialog generation models are prone to hallucination and produce factually inaccurate outputs.
Approach:	They propose a retrieval-based framework which leverages in-context learning and retrieval techniques to enhance LLMs on knowledge grounded dialog generation.
Outcome:	The proposed framework outperforms existing training-based models on a large-scale knowledge graph with 1M+ facts and is expected to perform knowledge-intensive tasks.

Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting (2021.acl-long)

Copied to clipboard

Yi Cheng, Siyao Li, Bang Liu, Ruihui Zhao, Sujian Li, Chenghua Lin, Yefeng Zheng

Text Generation

Challenge:	Existing QG systems perform substantially worse in answering multi-hop questions than single-hop ones.
Approach:	They propose a framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
Outcome:	The proposed framework increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.

FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain (2025.emnlp-main)

Copied to clipboard

Suifeng Zhao, Zhuoran Jin, Sujian Li, Jun Gao

Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation (2022.emnlp-main)

Challenge:	Existing RAG research focuses on textual data, overlooking rich visual content in financial documents.
Approach:	They propose a visual RAG benchmark tailored for finance that integrates multimodal data and provides visual citation to ensure traceability.
Outcome:	The proposed visual RAG benchmark integrates multimodal data and provides visual citation to ensure traceability.

Copied to clipboard

Peiyi Wang, Yifan Song, Tianyu Liu, Binghuai Lin, Yunbo Cao, Sujian Li, Zhifang Sui

Evaluating Text Coherence at Sentence and Paragraph Levels (2020.lrec-1)

Challenge:	Existing studies attribute catastrophic forgetting to the corruption of the learned representations as new relations come . Continual relation extraction models suffer from catastrophic forgetting when learning new relations .
Approach:	They propose to use adversarial class augmentation mechanism to learn more precise representations . they propose to train the model on a sequence of tasks where two new relations are discovered .
Outcome:	The proposed model improves on two popular benchmarks.

Copied to clipboard

Sennan Liu, Shuang Zeng, Sujian Li

Reasoning

Challenge:	Existing text ordering models have been used to test coherence in NLP for a long time.
Approach:	They propose to perform paragraph ordering task and sentence ordering by using four corpora from different domains.
Outcome:	The proposed model performs better under certain extreme conditions than the most prevalent metric used before.

Consecutive Question Generation via Dynamic Multitask Learning (2022.findings-emnlp)

Copied to clipboard

Yunji Li, Sujian Li, Xing Shi

Question Generation

Challenge:	, . ; ) ()((); ()) .())((2): ""().
Approach:	They propose a sequential sequential question-answer generation task with auxiliary tasks generating other elements to generate logically related question-anchor pairs to understand a passage.
Outcome:	The proposed framework improves question generation significantly and benefit multiple related tasks.

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

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.

LongAttn: Selecting Long-context Training Data via Token-level Attention (2025.findings-acl)

Copied to clipboard

Longyun Wu, Dawei Zhu, Guangxiang Zhao, Zhuocheng Yu, Junfeng Ran, Xiangyu Wong, Lin Sun, Sujian Li

InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective (2023.findings-emnlp)

Challenge:	Existing methods to select long-context data often rely on sentence-level analysis, which can be greatly optimized in both performance and efficiency.
Approach:	They propose a token-level framework which quantifies long-range dependencies for LLMs by calculating token-based dependency strength and distribution uniformity of token scores.
Outcome:	The proposed framework quantifies long-range dependencies, enabling more accurate and efficient data selection.

Copied to clipboard

Yifan Song, Peiyi Wang, Weimin Xiong, Dawei Zhu, Tianyu Liu, Zhifang Sui, Sujian Li

DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding (2026.acl-long)

Challenge:	Recent studies have identified the severe performance decrease on analogous classes as a key factor for catastrophic forgetting.
Approach:	They propose a replay-based continual text classification method that uses fast-slow and current-past contrastive learning to perform mutual information maximization and better recover previously learned representations.
Outcome:	The proposed method achieves state-of-the-art on three text classification tasks.

Copied to clipboard

Dawei Zhu, Rui Meng, Jiefeng Chen, Sujian Li, Tomas Pfister, Jinsung Yoon

FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness (2022.findings-emnlp)

Challenge:	Existing approaches to localizing evidence from long visual documents fail on a fundamental challenge: evidence localization.
Approach:	They propose a tool-augmented multi-agent framework that “zooms in” on evidence like a lens.
Outcome:	The proposed framework achieves state-of-the-art performance on MMLongBench-Doc and FinRAGBench-V, surpassing even human experts.

Copied to clipboard

Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Ziqiang Cao, Sujian Li, Hua Wu

Joint Learning for Targeted Sentiment Analysis (D18-1)

Challenge:	Existing models of abstractive summarization are able to generate fluent and coherent summaries, but they still suffer from the unfaithful generation problem.
Approach:	They propose to improve the faithfulness of existing models by enhancing their factual robustness by using a novel training strategy, namely FRSUM, which teaches the model to defend against both explicit adversarial samples and implicit factual adversarials.
Outcome:	The proposed training strategy improves faithfulness of various models, such as T5, BART, and T5 .

Copied to clipboard

Dehong Ma, Sujian Li, Houfeng Wang

Sentiment Analysis

Challenge:	Recent studies have attempted to perform two tasks separately, e.g., target extraction and sentiment classification.
Approach:	They propose a hierarchical stack bidirectional gated recurrent units (HSBi-GRU) model which allows the target label to influence their sentiment label.
Outcome:	The proposed model outperforms baseline models on two datasets and shows that it can learn abstract features.

Exploring Sequence-to-Sequence Learning in Aspect Term Extraction (P19-1)

Copied to clipboard

Dehong Ma, Sujian Li, Fangzhao Wu, Xing Xie, Houfeng Wang

Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation (2022.emnlp-main)

Challenge:	Aspect term extraction (ATE) aims at identifying all aspect terms in a sentence . sequence labeling based methods cannot make full use of overall meaning of sentence if they have dependencies between labels.
Approach:	They propose to formalize ATE as a sequence-to-sequence (Seq2Seque) learning task . they propose gated unit networks and position-aware attention mechanism to make it suit to ATE .
Outcome:	The proposed learning task is effective when labels correspond to words one by one . the proposed learning system is gated unit networks and position-aware attention mechanism .

Copied to clipboard

Wenhao Wu, Wei Li, Jiachen Liu, Xinyan Xiao, Sujian Li, Yajuan Lyu

Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification (2020.coling-main)

Challenge:	Existing models for text generation are weak enough to handle perturbations in inputs, leading to degeneration in faithfulness and informativeness.
Approach:	They propose a framework for improving faithfulness and informativeness of Seq2Seq models by perturbing word representations and word swapping.
Outcome:	The proposed framework improves faithfulness and informativeness of Seq2Seq models under automatic and human evaluation settings.

Copied to clipboard

Lianzhe Huang, Xin Sun, Sujian Li, Linhao Zhang, Houfeng Wang

Sentiment Analysis

Challenge:	Existing approaches to aspect-level sentiment classification focus on modeling the relationship between aspect words and their contexts with attention, and ignore the use of elaborate knowledge implicit in the context.
Approach:	They exploit syntactic awareness to the model by the graph attention network on the dependency tree structure and external pre-training knowledge by BERT language model, which helps to model the interaction between the context and aspect words better.
Outcome:	The proposed model can model the interaction between the context and aspect words better by using syntactic awareness and external pre-training knowledge.

Cross-Lingual Leveled Reading Based on Language-Invariant Features (2021.findings-emnlp)

Copied to clipboard

Simin Rao, Hua Zheng, Sujian Li

Multilinguality

Challenge:	Leveled reading (LR) aims to automatically classify texts by the cognitive levels of readers.
Approach:	They propose to use adversarial training and cross-lingual pre-training methods to transfer LR knowledge from annotated data in resource-rich English to Chinese.
Outcome:	The proposed method captures language-invariant features between English and Chinese.

Promoting Pre-trained LM with Linguistic Features on Automatic Readability Assessment (2022.aacl-short)

Copied to clipboard

Shudi Hou, Simin Rao, Yu Xia, Sujian Li

InstructEval: Instruction-Tuned Text Evaluator from Human Preference (2024.findings-acl)

Challenge:	Automatic readability assessment (ARA) aims at classifying the readability level of a text automatically.
Approach:	They propose to integrate linguistic features with pre-trained language models to improve the accuracy of ARA.
Outcome:	The proposed algorithm improves on the long passage characteristic of ARA using commonly used linguistic features and abundant datasets.

Copied to clipboard

Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Sujian Li

Realistic Training Data Generation and Rule Enhanced Decoding in LLM for NameGuess (2025.emnlp-main)

Challenge:	InstructEval is a general text evaluator based on open-source Large Language Models (LLMs).
Approach:	They propose to build a general multi-aspect text evaluator based on open-source Large Language Models (LLMs) they use extensive open Human Preference Modeling datasets and a small set of multi-spect annotated data to overcome the shortage of annotation resources for multi-task evaluations.
Outcome:	The proposed model performs comparable or superior to commercial LLMs like ChatGPT or GPT-4 in terms of both overall and multi-aspect evaluation tasks.

Copied to clipboard

Yikuan Xia, Jiazun Chen, Sujian Li, Jun Gao

Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization (P18-1)

Challenge:	Abbreviated column names often harm downstream tasks, causing performance drops of 10.54, 40.50, and 3.83 percentage points.
Approach:	They propose a method that integrates a subsequence abbreviation generator trained on human-annotated data and collects non-subsequent abbrevations to improve the training set.
Outcome:	The proposed approach improves on the English NameGuess task and surpasses state-of-the-art LLMs.

Copied to clipboard

Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei

Text Generation

Challenge:	Existing summarization systems rely on the source text to generate summaries, which tends to work unstably.
Approach:	They propose to use existing summaries as soft templates to guide the seq2seq model . they use a popular IR platform to Retrieve proper summary as candidate templates .
Outcome:	The proposed model outperforms state-of-the-art models in terms of informativeness and readability.

Low Resource Style Transfer via Domain Adaptive Meta Learning (2022.naacl-main)

Copied to clipboard

Xiangyang Li, Xiang Long, Yu Xia, Sujian Li

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues (2022.acl-long)

Challenge:	Existing unsupervised text style transfer methods suffer from performance degradation when fine-tuning the model in new domains.
Approach:	They propose a domain adaptive meta-learning approach with an adversarial style training approach for better content preservation and style transfer.
Outcome:	The proposed approach generalizes well on unseen low-resource domains against ten strong baselines.

Copied to clipboard

Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei, Weidong Zhan, Baobao Chang, Sujian Li, Tianyu Liu, Zhifang Sui

Tree-structured Decoding for Solving Math Word Problems (D19-1)

Challenge:	Existing work in vision language cross-modal reasoning uses binary or multi-choice classification based on source image and textual query.
Approach:	They propose a task where a textual premise is the background presumption on each source image.
Outcome:	The proposed task is based on a dataset of 15,360 movie screenshots and human-curated premise templates from 6 pre-defined categories.

Copied to clipboard

Qianying Liu, Wenyv Guan, Sujian Li, Daisuke Kawahara

Numerical Reasoning

Challenge:	Existing approaches to solve math word problems do not consider an abstract syntax tree.
Approach:	They propose a tree-structured decoding method that generates an abstract syntax tree of an equation in a top-down manner and can stop during decoding without a redundant stop token.
Outcome:	The proposed method achieves state-of-the-art performance on the largest dataset on this task.

EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection (2025.coling-main)

Copied to clipboard

Zheng Li, Sujian Li, Dawei Zhu, Qilong Ma, Weimin Xiong

Sentiment Analysis

Challenge:	Existing methods for personality detection ignore the connection between psychological knowledge “emotion regulation” and personality traits.
Approach:	They propose to use emotion regulation and emotion features to retrieve few-shot samples and provide process CoTs for inferring labels from text.
Outcome:	The proposed method outperforms SOTA by 15.05/4.29 on the two benchmark datasets.

ConFiguRe: Exploring Discourse-level Chinese Figures of Speech (2022.coling-1)

Copied to clipboard

Dawei Zhu, Qiusi Zhan, Zhejian Zhou, Yifan Song, Jiebin Zhang, Sujian Li

Speech & Audio in NLP

Challenge:	Figures of speech often deviate from their literal meanings to express deeper semantic implications.
Approach:	They propose a concept of figurative unit, which is the carrier of a figure, and build a Chinese corpus for Contextualized Figure Recognition.
Outcome:	The proposed model is based on 12 types of figures commonly used in Chinese . it shows that the proposed tasks are challenging for existing models .

Debiasing Generative Named Entity Recognition by Calibrating Sequence Likelihood (2023.acl-short)

Copied to clipboard

Yu Xia, Yongwei Zhao, Wenhao Wu, Sujian Li

Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (2024.emnlp-main)

Challenge:	Existing approaches to recognize flat, overlapped and discontinuous entities uniformly have been used for Named Entity Recognition.
Approach:	They propose a reranking-based approach that redistributes the likelihood among candidate sequences depending on their performance via a contrastive loss.
Outcome:	The proposed method boosts baseline and yields competitive or better results compared with the state-of-the-art methods on 8 widely-used datasets for Named Entity Recognition.

Copied to clipboard

Weimin Xiong, Yifan Song, Xiutian Zhao, Wenhao Wu, Xun Wang, Ke Wang, Cheng Li, Wei Peng, Sujian Li

KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model (2023.findings-emnlp)

Challenge:	Recent approaches to enhance agent performance focus on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals.
Approach:	They propose a step-level framework that provides detailed step-by-step guidance to enhance agent training by using Monte Carlo methods.
Outcome:	The proposed framework outperforms strong baselines on three tasks and shows that it is effective in augmenting efficiency and its applicability to diverse models.

Copied to clipboard

Lei Geng, Xu Yan, Ziqiang Cao, Juntao Li, Wenjie Li, Sujian Li, Xinjie Zhou, Yang Yang, Jun Zhang

Multilinguality

Challenge:	Existing models for multilingual biomedical training are monolingual, resulting in limited cross-lingual capability.
Approach:	They propose a model that transforms a multilingual biomedical corpus into a biomedically domain using a knowledge-anchored approach.
Outcome:	The proposed model outperforms monolingual and multilingual models in cross-lingual scenarios.

Toward Fast and Accurate Neural Discourse Segmentation (D18-1)

Copied to clipboard

Yizhong Wang, Sujian Li, Jingfeng Yang

Discourse & Pragmatics

Challenge:	Existing discourse segmenters rely on complicated hand-crafted features and are not practical in actual use.
Approach:	They propose an end-to-end neural segmenter based on BiLSTM-CRF framework that can segment texts fast and accurately using a large corpus.
Outcome:	The proposed model is significantly faster than previous methods while achieving state-of-the-art performance on the RST-DT corpus.

MPO: Boosting LLM Agents with Meta Plan Optimization (2025.findings-emnlp)

Copied to clipboard

Weimin Xiong, Yifan Song, Qingxiu Dong, Bingchan Zhao, Feifan Song, null XWang, Sujian Li

Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation (N18-1)

Challenge:	Existing methods for interactive planning tasks suffer from planning hallucinations and require retraining for each new agent.
Approach:	They propose a framework that leverages explicit guidance through meta plans to assist agent planning and enables continuous optimization based on feedback from the agent’s task execution.
Outcome:	The proposed framework outperforms existing baselines on two representative tasks and significantly improves task completion efficiency and generalization capabilities.

Copied to clipboard

Shuming Ma, Xu Sun, Wei Li, Sujian Li, Wenjie Li, Xuancheng Ren

Text Generation

Challenge:	Existing models tend to memorize words instead of learning meaning of words . existing models tend not to model semantic information, resulting in incorrect sentences .
Approach:	They propose a novel model that generates words by querying distributed word representations . they evaluate model on two paraphrase-oriented tasks, namely text simplification and short abstractive summarization .
Outcome:	The proposed model outperforms the baseline model on two paraphrase-oriented tasks . it achieves state-of-the-art performance on these benchmark datasets .

Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection (2021.findings-acl)

Copied to clipboard

Linhao Zhang, Dehong Ma, Sujian Li, Houfeng Wang

Challenge:	Existing matching models for response selection perform the independent matching (IM) approach. Existing models for matching only perform one match regardless of the number of options.
Approach:	They propose a joint matching approach which performs matching only once regardless of the number of options.
Outcome:	The proposed approach outperforms existing models and reduces training time by over half.

Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification (P18-1)

Copied to clipboard

Yizhong Wang, Kai Liu, Jing Liu, Wei He, Yajuan Lyu, Hua Wu, Sujian Li, Haifeng Wang

Reasoning

Challenge:	Recent years have seen rapid growth in the MRC community . MRC is believed to be a crucial step in building a general intelligent agent .
Approach:	They propose an end-to-end neural model that enables multiple passages to verify each other based on their content representations.
Outcome:	The proposed model outperforms the baseline on the English MS-MARCO dataset and the Chinese DuReader dataset, and achieves state-of-the-art performance on both datasets.

KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization (2026.findings-eacl)

Copied to clipboard

Mingbo Song, Heming Xia, Jun Zhang, Chak Tou Leong, Qiancheng Xu, Wenjie Li, Sujian Li

Challenge:	Large language models (LLMs) have proven highly capable in handling downstream tasks, but the token-by-token generation in autoregressive decoding results in quadratic computational complexity.
Approach:	They propose a method that proposes skipping certain layers to construct a draft model, which eliminates the need for additional parameters or training.
Outcome:	The proposed method achieves 1.31.6 speedup in LLM inference while being sensitive to domain shifts.

SciDTB: Discourse Dependency TreeBank for Scientific Abstracts (P18-2)

Copied to clipboard

An Yang, Sujian Li

Syntactic Text Processing

Challenge:	Discourse relations are annotated on scientific articles.
Approach:	They propose a domain-specific discourse treebank annotated on scientific articles . they use dependency trees to represent discourse structure, which is flexible and simplified .
Outcome:	The proposed treebank is a benchmark for evaluating discourse dependency parsers.

Rationale-Enhanced Language Models are Better Continual Relation Learners (2023.emnlp-main)

Copied to clipboard

Weimin Xiong, Yifan Song, Peiyi Wang, Sujian Li

The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism (2025.naacl-long)

Challenge:	Recent studies have found that catastrophic forgetting arises from the model’s lack of robustness against future analogous relations.
Approach:	They propose a multi-task rationale tuning strategy to help the model learn current relations robustly and conduct contrastive rationale replay to further distinguish analogous relations.
Outcome:	The proposed method outperforms the state-of-the-art models on two benchmarks.

Copied to clipboard

Yifan Song, Guoyin Wang, Sujian Li, Bill Yuchen Lin

Challenge:	Current evaluations of large language models (LLMs) focus on a single output per example, which limits our understanding of LLM performance variability in real-world applications.
Approach:	They explore the performance differences between greedy decoding and sampling and identify benchmarks’ consistency regarding non-determinism and examine unique model behaviors.
Outcome:	The proposed model outperforms sampling methods and greedy decoding outperformed other models.

Exploring Fine-Grained Human Motion Video Captioning (2025.coling-main)

Copied to clipboard

Bingchan Zhao, Xinyi Liu, Zhuocheng Yu, Tongchen Yang, Yifan Song, Mingyu Jin, Sujian Li, Yizhou Wang

Text Level Graph Neural Network for Text Classification (D19-1)

Challenge:	Existing video captioning models fail to capture nuanced semantics of videos . existing models generate coarse descriptions of human motions, resulting in poor quality .
Approach:	They construct a fine-grained human motion video captioning dataset named BoFiT and a model that generates fine-grain descriptions of human motions via prompting.
Outcome:	The proposed model outperforms existing models on comprehensive metrics.

Copied to clipboard

Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang

BASS: Boosting Abstractive Summarization with Unified Semantic Graph (2021.acl-long)

Challenge:	Recent researches have explored graph neural network (GNN) techniques on text classification, but they are faced with the problems of fixed corpus level graph structure which don’t support online testing and high memory consumption.
Approach:	They propose a graph neural network model that builds graphs for each input text with global parameters sharing instead of a single graph for the whole corpus.
Outcome:	The proposed model outperforms existing models on several text classification datasets even with consuming less memory.

Copied to clipboard

Wenhao Wu, Wei Li, Xinyan Xiao, Jiachen Liu, Ziqiang Cao, Sujian Li, Hua Wu, Haifeng Wang

PsyPath: Psychologically-guided Self-Exploration for Personality Detection (2026.findings-acl)

Challenge:	Abstractive summarization for long-document or multi-document remains challenging for Seq2Seq as it does not analyze long-distance relations in text.
Approach:	They propose a framework for Boosting Abstractive Summarization based on a unified Semantic graph which aggregates co-referent phrases distributing across a long range of context and conveys rich relations between phrases.
Outcome:	The proposed framework improves document representation and summary generation process by leveraging the graph structure.

Copied to clipboard

Zheng Li, Hongxin Ding, Chenyu Zhang, Weimin Xiong, Dawei Zhu, Sujian Li

Composing Elementary Discourse Units in Abstractive Summarization (2020.acl-main)

Challenge:	Personality detection aims to label traits via identifying linguistic cues from written text.
Approach:	They propose a framework that allows large language models to generate and answer psychologically meaningful questions and a hybrid scoring mechanism to evaluate the generated nodes in the reasoning paths.
Outcome:	The proposed framework outperforms baselines on two benchmark datasets and significantly improves performance and interpretability in downstream tasks.

Copied to clipboard

Zhenwen Li, Wenhao Wu, Sujian Li

Summarization

Challenge:	Abstractive summarization uses a single document sentence to generate a summary, but this can cause performance degradation.
Approach:	They propose to use elementary discourse unit (EDU) as the summarization unit to extract and group informative EDUs and then an EDU fusion model to fuse the EDU in each group into one sentence.
Outcome:	The proposed model can be used to combine informative EDUs into one sentence and reward selection actions.

Denoising based Sequence-to-Sequence Pre-training for Text Generation (D19-1)

Copied to clipboard

Liang Wang, Wei Zhao, Ruoyu Jia, Sujian Li, Jingming Liu

LongEmbed: Extending Embedding Models for Long Context Retrieval (2024.emnlp-main)

Challenge:	PoDA pre-trains encoders and decoders by denoising noise-corrupted text . Unlike encoder-only or decode-only methods, it can be used for text generation tasks without using any task-specific techniques.
Approach:	They propose a sequence-to-sequence (seq2sequ) pre-training method PoDA which denoises autoencoders by denoising noise-corrupted text.
Outcome:	The proposed method improves model performance over strong baselines without using any task-specific techniques and significantly speed up convergence.

Copied to clipboard

Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li

Representation Learning

Challenge:	Existing embedding models support only 512 input tokens, hindering their application in scenarios requiring long inputs.
Approach:	They evaluate the performance of existing embedding models by using a new benchmark and a training-free context window extension strategy.
Outcome:	The proposed model extends the input window of existing models by several folds.

A Transition-based Method for Complex Question Understanding (2022.coling-1)

Copied to clipboard

Yu Xia, Wenbin Jiang, Yajuan Lyu, Sujian Li

Explainability & Interpretability in NLP

Challenge:	Existing work on complex question understanding does not model intermediate states and does not provide step-wise information.
Approach:	They propose a transition-based method where a decider predicts a sequence of actions to build the graph node-by-node.
Outcome:	The proposed method parses complex questions to QDMR using atomic operators . it has transparent and human-readable intermediate results, showing improved interpretability .

Contrastive Bootstrapping for Label Refinement (2023.acl-short)

Copied to clipboard

Shudi Hou, Yu Xia, Muhao Chen, Sujian Li

CoUDA: Coherence Evaluation via Unified Data Augmentation (2024.naacl-long)

Challenge:	Existing methods for fine-grained classification categorize texts into coarse-gritty classes, but they are suboptimal in real-world scenarios.
Approach:	They propose a lightweight contrastive clustering-based bootstrapping method to iteratively refine the labels of passages.
Outcome:	The proposed method outperforms the state-of-the-art methods by a large margin on NYT and 20News datasets.

Copied to clipboard

Dawei Zhu, Wenhao Wu, Yifan Song, Fangwei Zhu, Ziqiang Cao, Sujian Li

ISR: Self-Refining Referring Expressions for Entity Grounding (2025.acl-long)

Challenge:	Existing data augmentations for coherence evaluation rely on heuristic rules and lack designing criteria.
Approach:	They propose a data augmentation framework that breaks down coherence into global and local aspects and designs augmentation strategies for both aspects.
Outcome:	The proposed framework surpasses recent models in scoring and ranking tasks with 233M parameters.

Copied to clipboard

Zhuocheng Yu, Bingchan Zhao, Yifan Song, Sujian Li, Zhonghui He

FaGANet: An Evidence-Based Fact-Checking Model with Integrated Encoder Leveraging Contextual Information (2024.lrec-main)

Challenge:	Entity grounding is a crucial task in the construction of multimodal knowledge graphs.
Approach:	They propose a novel scheme to enhance the multimodal large language model's capability to generate high quality REs for the given entities as explicit contextual clues.
Outcome:	The proposed method surpasses other methods in entity grounding, highlighting its effectiveness, robustness and potential for broader applications.

Copied to clipboard

Weiyao Luo, Junfeng Ran, Zailong Tian, Sujian Li, Zhifang Sui

Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (P19-1)

Challenge:	Existing evidence-based fact-checking efforts are time-consuming and challenging . however, relying on surface patterns of claims makes it difficult to identify subtle connections between claims and evidence.
Approach:	They propose a model that leverages sentence-level attention and graph attention network to enhance accuracy and fusing claims and evidence information for accurate identification of even well-disguised data.
Outcome:	The proposed model improves accuracy and state-of-the-art in the evidence-based fact-checking task.

Copied to clipboard

An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li

Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision (2025.findings-emnlp)

Challenge:	Recent results show pre-trained language models (LMs) can improve machine reading comprehension (MRC) Experimental results indicate that KT-NET offers significant and consistent improvements over BERT .
Approach:	They propose a method that leverages external knowledge bases to improve machine reading comprehension (MRC) KT-NET employs an attention mechanism to select desired knowledge from KBs and fuses selected knowledge with BERT to enable context- and knowledge-aware predictions.
Outcome:	The proposed model outperforms baseline models on ReCoRD and SQuAD1.1 benchmarks and ranks 1st on the ReCoDR and SQUAD1.1 leaderboards.

Copied to clipboard

Dawei Zhu, Xiyu Wei, Guangxiang Zhao, Wenhao Wu, Haosheng Zou, Junfeng Ran, null XWang, Lin Sun, Xiangzheng Zhang, Sujian Li

Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension (C18-1)

Challenge:	Recent advances in Large Language Models (LLMs) have highlighted the challenge of handling long-context tasks.
Approach:	They propose a chain-of-thought framework that teaches models to generate high-quality reasoning paths for enhanced long-context performance.
Outcome:	The proposed framework generalizes across most long-context scenarios and amplifys with increasing context length.

Copied to clipboard

Liang Wang, Sujian Li, Wei Zhao, Kewei Shen, Meng Sun, Ruoyu Jia, Jingming Liu