Papers by Jing Jiang

Synergizing Large Language Models and Pre-Trained Smaller Models for Conversational Intent Discovery (2024.findings-acl)

Challenge:	Existing models that use self-attention and position embedding have anomalous behavior that hinder long context window extrapolation.
Approach:	They propose a collinear constraint between Q and K to integrate RoPE and self-attention.
Outcome:	The proposed model integrates self-attention and position embedding into LLMs without fine-tuning.

Copied to clipboard

Jinggui Liang, Lizi Liao, Hao Fei, Jing Jiang

Automated Progressive Red Teaming (2025.coling-main)

Challenge:	Current attempts at CID rely on pretrained Small Language Models (SLMs) this lacks the ability to label new intents and is a challenge for small language models.
Approach:	They propose to combine Large Language Models (LLMs) with pre-trained SLMs for CID to enhance the semantic comprehension of LLMs.
Outcome:	The proposed approach improves the semantic comprehension of LLMs and the operational agility of SLMs by realigning existing descriptors within the SLM’s feature space to correct cluster distortion and promote robust learning of representations.

Copied to clipboard

Bojian Jiang, Yi Jing, Tong Wu, Tianhao Shen, Deyi Xiong, Qing Yang

Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases (2020.acl-main)

Challenge:	Automated red teaming (ART) is effective but time-consuming, costly and lacks scalability.
Approach:	They propose an automated red teaming framework that generates adversarial prompts to expose LLM vulnerabilities.
Outcome:	The proposed framework explores and exploits LLM vulnerabilities through multi-round interactions.

Copied to clipboard

Yunshi Lan, Jing Jiang

Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization (2026.findings-acl)

Challenge:	Existing work on complex knowledge base question answering addresses two types of complexity at the same time.
Approach:	They propose a modified staged query graph generation method that handles both types of complexity at the same time.
Outcome:	The proposed method achieves state-of-the-art on three benchmark KBQA datasets.

Copied to clipboard

Xia Jiang, Jing Chen, Cong Zhang, Jie Gao, Chengpeng Hu, Chenhao Zhang, Yaoxin Wu, Yingqian Zhang

Dynamic Parallel Tree Search for Efficient LLM Reasoning (2025.acl-long)

Challenge:	NLCO evaluates large language models for combinatorial optimization (CO) . existing evaluations emphasize relatively simple reasoning competencies .
Approach:	They propose a combinatorial optimization benchmark that evaluates large language models on CO reasoning.
Outcome:	The proposed model can handle combinatorial optimization without writing code or calling external solvers.

Copied to clipboard

Yifu Ding, Wentao Jiang, Shunyu Liu, Yongcheng Jing, Jinyang Guo, Yingjie Wang, Jing Zhang, Zengmao Wang, Ziwei Liu, Bo Du, Xianglong Liu, Dacheng Tao

#HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention (2021.emnlp-main)

Challenge:	Recent methods focus on search accuracy while overlooking computational efficiency.
Approach:	They propose a parallelism framework that dynamically optimizes reasoning path in inference.
Outcome:	The proposed framework improves efficiency by 2-4 on average while maintaining or even surpassing existing reasoning algorithms in accuracy.

Copied to clipboard

Yuji Zhang, Yubo Zhang, Chunpu Xu, Jing Li, Ziyan Jiang, Baolin Peng

Tagging

Challenge:	Existing methods based on latent topics cannot capture user interests and thus can't be used to predict how likely a user will post with a hashtag.
Approach:	They propose a personalized topic attention model that captures salient contents to personalize hashtag contexts by predicting how likely a user will post with a hashtag.
Outcome:	The proposed model significantly outperforms the state-of-the-art recommendation approach without exploiting latent topics.

BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering (2024.emnlp-main)

Copied to clipboard

Haoyu Wang, Ruirui Li, Haoming Jiang, Jinjin Tian, Zhengyang Wang, Chen Luo, Xianfeng Tang, Monica Cheng, Tuo Zhao, Jing Gao

Muffin or Chihuahua? Challenging Multimodal Large Language Models with Multipanel VQA (2024.acl-long)

Challenge:	Retrieval-augmented Large Language Models struggle with complex inputs and noisy knowledge retrieval hindering model effectiveness.
Approach:	They propose a query generation method that integrates query generation blending with knowledge filtering to enhance retrieval-augmented LLMs.
Outcome:	The proposed approach surpasses state-of-the-art benchmarks on open-domain question answering benchmarks.

Copied to clipboard

Yue Fan, Jing Gu, Kaiwen Zhou, Qianqi Yan, Shan Jiang, Ching-Chen Kuo, Yang Zhao, Xinze Guan, Xin Wang

Revisiting Distant Supervision for Relation Extraction (L18-1)

Challenge:	Multipanel images are a common form of visual representations, and humans can achieve approximately 99% accuracy on these questions.
Approach:	They propose a benchmark that tests multipanel visual reasoning models with 6,600 triplets of questions, answers, and multipanel images.
Outcome:	The proposed benchmark features 6,600 triplets of questions, answers, and multipanel images that challenge state-of-the-art Multimodal Large Language Models (MLLMs) human users can attain approximately 99% accuracy on these questions, compared with previous benchmarks.

Copied to clipboard

Tingsong Jiang, Jing Liu, Chin-Yew Lin, Zhifang Sui

Evolutionary Guided Decoding: Iterative Value Refinement for LLMs (2026.acl-long)

Challenge:	Existing approaches for relation extraction (RE) use supervised learning on relation-specific training data, which is expensive to acquire.
Approach:	They propose to use a new testing dataset to re-examine distant supervision approaches . they aim to draw new conclusions based on the new testing data .
Outcome:	The proposed method can generate training data without noise and bias issues . the proposed method is annotated by the researchers on Amzaon Mechanical Turk .

Copied to clipboard

Zhenhua Liu, Lijun Li, Ruizhe Chen, Yuxian Jiang, Tong Zhu, Zhaochen Su, Wenliang Chen, Jing Shao

An Empirical Study of Memorization in NLP (2022.acl-long)

Challenge:	Existing methods for directing language model outputs are limited in their accuracy due to a distributional gap . existing methods train static value functions on trajectories sampled exclusively from the base policy .
Approach:	They propose a framework to bridge a distributional gap in the accuracy of value functions . they propose RLHF to align language models with human values and task requirements .
Outcome:	The proposed framework reduces computational costs and improves value function accuracy by leveraging principled value function optimization.

Copied to clipboard

Xiaosen Zheng, Jing Jiang

Linguistic Theories

Challenge:	Existing studies see memorization as hindering generalization in deep learning models.
Approach:	They propose a long-tail theory to explain the memorization behavior of deep learning models . they use three different NLP tasks to test whether the theory holds .
Outcome:	The proposed long-tail theory is validated in three NLP tasks and shows it is faithful.

Leveraging Web-Crawled Data for High-Quality Fine-Tuning (2024.findings-emnlp)

Copied to clipboard

Jing Zhou, Chenglin Jiang, Wei Shen, Xiao Zhou, Xiaonan He

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset (2021.findings-emnlp)

Challenge:	Currently, large language models are fine-tuned using expensive human-annotated data or GPT-4 generated data.
Approach:	They propose to use web-crawled data to train a language model on a smaller set of data . their results show that the model can convert web data with irregular formats into high-quality ones .
Outcome:	The proposed model outperforms open-source models larger than 32B and outperformed open-sourced models such as GPT-3.5.

Copied to clipboard

Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim

Consistent Client Simulation for Motivational Interviewing-based Counseling (2025.acl-long)

Challenge:	Existing question answering datasets lack numerical reasoning and reasoning processes . current research on numerical reasoning focuses on simple calculations .
Approach:	They propose a conversational and bilingual question answering dataset with numerical reasoning with compound mathematical expressions.
Outcome:	The proposed model achieves 55.5 exact match scores while human performance is 89.7.

Copied to clipboard

Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Nicholas Gabriel Lim, Cameron Tan Shi Ern, Phey Ling Kit, Jenny Giam Xiuhui, John Pinto, Ee-Peng Lim

A BERT-based Dual Embedding Model for Chinese Idiom Prediction (2020.coling-main)

Challenge:	Existing approaches to simulate human clients in mental health counseling are limited and cost prohibitive.
Approach:	They propose a framework that supports consistent client simulation for mental health counseling by tracking the mental state of a simulated client, controlling its state transitions, and generating for each state behaviors consistent with the client’s motivation, beliefs, preferred plan to change, and and receptivity.
Outcome:	The proposed framework can simulate human clients for mental health counseling tasks and achieve higher consistency than previous methods.

Copied to clipboard

Minghuan Tan, Jing Jiang

Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering (2021.acl-long)

Challenge:	Chinese idioms are special fixed phrases whose meanings are often highly idiomatic and non-compositional.
Approach:	They propose to use a BERT-based dual embedding model to encode contextual words and learn dual embeds of the idioms.
Outcome:	The proposed model performs better than the existing state of the art on a Chinese idiom cloze dataset.

Copied to clipboard

Yunshi Lan, Jing Jiang

Natural Language Interfaces

Challenge:	a new method for conversational Knowledge Base Question Answering (KBQA) uses implied entities from the conversation history to answer questions.
Approach:	They propose to model the implied entities of conversational KBQA by applying a graph neural network to derive a probability distribution of focal entities for each question.
Outcome:	The proposed model captures transitions of focal entities and performs answer ranking on two datasets.

MIThinker: A Plug-and-Play Policy-Optimized Thinker For Motivational Interviewing Counseling (2026.findings-acl)

Copied to clipboard

Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Ee-Peng Lim

Prompting for Multimodal Hateful Meme Classification (2022.emnlp-main)

Challenge:	Existing reasoning large language models (LLMs) generate responses without explicitly aligning thoughts with counseling techniques, limiting their effectiveness.
Approach:	They propose a lightweight thinking model that generates therapeutic thoughts to guide MI counseling agents in strategy selection and response generation.
Outcome:	The proposed model achieves theory-of-mind assessment comparable to state-of the-art systems with an order of magnitude less computation.

Copied to clipboard

Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang

Exploring and Adapting Chinese GPT to Pinyin Input Method (2022.acl-long)

Challenge:	Hateful meme classification requires complex reasoning and contextual background knowledge.
Approach:	They propose a simple yet effective prompt-based model that prompts pre-trained language models for hateful meme classification.
Outcome:	The proposed model outperforms state-of-the-art models on hateful meme classification task.

Copied to clipboard

Minghuan Tan, Yong Dai, Duyu Tang, Zhangyin Feng, Guoping Huang, Jing Jiang, Jiwei Li, Shuming Shi

Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer (2025.acl-long)

Challenge:	a frozen GPT can generate state-of-the-art performance on perfect pinyin, but performance drops when input includes abbreviated pinyan, which links to even larger number of Chinese characters.
Approach:	They propose to use Chinese GPT to generate fluent sentences using abbreviated pinyin.
Outcome:	The proposed approach improves on abbreviated pinyin across all domains.

Copied to clipboard

Guodong Du, Zitao Fang, Jing Li, Junlin Li, Runhua Jiang, Shuyang Yu, Yifei Guo, Yangneng Chen, Sim Kuan Goh, Ho-Kin Tang, Daojing He, Honghai Liu, Min Zhang

Speaker Verification in Agent-generated Conversations (2024.acl-long)

Challenge:	Foundational models and their checkpoints have advanced deep learning, boosting performance across applications.
Approach:	They propose a method for pruning fine-tuned models by calculating differences between them and original model.
Outcome:	The proposed method can improve performance across vision, NLP, and multi-modal benchmarks.

Copied to clipboard

Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Ee-Peng Lim

Dialogue Systems & Conversational Agents

Challenge:	Recent advances in large language models have increased the capabilities of conversational AI to solve challenging dialogue problems.
Approach:	They propose a task to verify whether two sets of utterances originate from the same speaker.
Outcome:	The proposed task aims to verify whether two sets of utterances originate from the same speaker.

Efficient Cross-modal Prompt Learning with Semantic Enhancement for Domain-robust Fake News Detection (2025.coling-main)

Copied to clipboard

Fei Wu, Hao Jin, Changhui Hu, Yimu Ji, Xiao-Yuan Jing, Guo-Ping Jiang

Improving Multi-label Emotion Classification via Sentiment Classification with Dual Attention Transfer Network (D18-1)

Challenge:	Existing MFND methods conduct cross-modal information interaction at later stage, resulting in weak generalization ability.
Approach:	They propose an automatic multi-modal fake news detection method that exploits cross-modal information interaction at later stage.
Outcome:	The proposed method outperforms state-of-the-art methods on three MFND benchmarks.

Copied to clipboard

Jianfei Yu, Luís Marujo, Jing Jiang, Pradeep Karuturi, William Brendel

Information Retrieval

Challenge:	Existing approaches to emotion detection are lexicon-based, graphical model-based and linear classifier-based.
Approach:	They propose a transfer learning architecture to divide sentence representation into two different feature spaces which capture general sentiment words and other important emotion-specific words via a dual attention mechanism.
Outcome:	The proposed model can capture general sentiment words and other emotion-specific words via a dual attention mechanism on two benchmark datasets.

PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check (2021.acl-long)

Copied to clipboard

Li Huang, Junjie Li, Weiwei Jiang, Zhiyu Zhang, Minchuan Chen, Shaojun Wang, Jing Xiao

Syntactic Text Processing

Challenge:	False gram and phonological errors make Chinese spelling check difficult . a novel end-to-end trainable model outperforms existing methods .
Approach:	They propose a trainable Chinese spelling check model that integrates phonological and visual information into a pre-trained language model.
Outcome:	The proposed model outperforms existing state-of-the-art models on three benchmarks.

Unsupervised Deep Structured Semantic Models for Commonsense Reasoning (N19-1)

Copied to clipboard

Shuohang Wang, Sheng Zhang, Yelong Shen, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Jing Jiang

Modularized Zero-shot VQA with Pre-trained Models (2023.findings-acl)

Challenge:	Existing methods for commonsense reasoning rely on human-crafted features and knowledge bases, but unsupervised learning is not feasible due to the lack of labeled training data or comprehensive knowledge bases.
Approach:	They propose two unsupervised models based on the Deep Structured Semantic Models framework to tackle two commonsense reasoning tasks: Winograd Schema Challenge (WSC) and Pronoun Disambiguation (PDP).
Outcome:	The proposed models capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.

Copied to clipboard

Rui Cao, Jing Jiang

Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering (2024.emnlp-main)

Challenge:	Recent work on zero-shot visual question answering does not explicitly consider multi-step reasoning chains, making them less interpretable compared with a decomposition-based approach.
Approach:	They propose a modularized zero-shot network that explicitly decomposes questions into sub reasoning steps and is highly interpretable.
Outcome:	The proposed model decomposes questions into sub reasoning steps and is highly interpretable.

Copied to clipboard

Dongze Hao, Qunbo Wang, Longteng Guo, Jie Jiang, Jing Liu

Information Retrieval

Challenge:	a framework that leverages the visual-language model to select key knowledge retrieved by DPR and answer questions improves performance of the baseline on the open-domain Knowledge-based VQA benchmark, OK-VQA.
Approach:	They propose a framework that leverages visual-language models to retrieve related knowledge . they use dense passage retrieval to retrieve knowledge related to visual-linguistics .
Outcome:	The proposed framework significantly improves the baseline on the open-domain Knowledge-based VQA benchmark, OK-VQA.

Colloquial Singaporean English Style Transfer with Fine-Grained Explainable Control (2025.acl-long)

Copied to clipboard

Jinggui Liang, Dung Vo, Yap Hong Xian, Hai Leong Chieu, Kian Ming A. Chai, Jing Jiang, Lizi Liao

Explainability & Interpretability in NLP

Challenge:	Existing methods for style transfer between Singlish and Standard English lack explainability and fine-grained control.
Approach:	They propose a multi-agent framework where large language models act as expert agents for each linguistic aspect.
Outcome:	The proposed model enables precise, interpretable transformations, advancing explainability in NLP for Singlish.

COSY: COunterfactual SYntax for Cross-Lingual Understanding (2021.acl-long)

Copied to clipboard

Sicheng Yu, Hao Zhang, Yulei Niu, Qianru Sun, Jing Jiang

Syntactic Text Processing

Challenge:	Pre-trained multilingual language models suffer from a large performance gap between source and target languages . e.g., multilingual-BERT models are widely used in cross-lingual tasks .
Approach:	They propose a language-agnostic approach to integrate universal syntax into language models . they use SYntax-aware networks and a COunterfactual training method .
Outcome:	The proposed model achieves state-of-the-art performance on natural language inference and question answering without auxiliary training data.

Translate-Train Embracing Translationese Artifacts (2022.acl-short)

Copied to clipboard

Sicheng Yu, Qianru Sun, Hao Zhang, Jing Jiang

Multilinguality

Challenge:	Existing approaches to train multilingual tasks are based on translationese and translatetrain.
Approach:	They propose to use translationese to mitigate the gap between the source and target languages to train the translator.
Outcome:	The proposed method outperforms baselines on the multilingual QA dataset TyDiQA.

Cross-Thought for Sentence Encoder Pre-training (2020.emnlp-main)

Copied to clipboard

Shuohang Wang, Yuwei Fang, Siqi Sun, Zhe Gan, Yu Cheng, Jingjing Liu, Jing Jiang

VLStereoSet: A Study of Stereotypical Bias in Pre-trained Vision-Language Models (2022.aacl-main)

Challenge:	Existing models to pretrain sentence encoders with large unlabeled corpus are lacking in linguistic information retrieval.
Approach:	They propose a novel approach to pre-training sequence encoder using transformers . they propose to train a Transformer-based sequence encoded over a large set of short sequences based on a set of masked words .
Outcome:	The proposed approach outperforms state-of-the-art encoders on hotpotQA by improving intermediate information retrieval performance.

Copied to clipboard

Kankan Zhou, Eason Lai, Jing Jiang

Visual Data in NLP

Challenge:	Existing studies on pre-trained vision-language models have focused on measuring biases and stereotypes in a single modality.
Approach:	They extend a recently released stereotypical bias dataset into a vision-language probing dataset called VLStereoSet to measure stereotypical biased vision-linguistic models.
Outcome:	The proposed probing task measures stereotypical bias in vision-language models and its intra-modal and inter-modal biases.

Revisiting the Markov Property for Machine Translation (2024.findings-eacl)

Copied to clipboard

Cunxiao Du, Hao Zhou, Zhaopeng Tu, Jing Jiang

Machine Translation

Challenge:	Statistical machine translation (SMT) has employed Markov models, but autoregressive models are less effective.
Approach:	They propose to use a Markov Autoregressive Transformer to model neural machine translation using four WMT benchmarks.
Outcome:	The proposed model performs better than autoregressive models on four WMT benchmarks.

Coupled Hierarchical Transformer for Stance-Aware Rumor Verification in Social Media Conversations (2020.emnlp-main)

Copied to clipboard

Jianfei Yu, Jing Jiang, Ling Min Serena Khoo, Hai Leong Chieu, Rui Xia

S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency (2025.naacl-long)

Challenge:	Existing approaches to rumor verification and stance classification fail to exploit intertask dependencies .
Approach:	They propose a Hierarchical Transformer model which uses BERT to obtain thread representations . they propose 'coupled' transformer modules to capture intertask interactions and a post-level attention layer to use predicted stance labels for RV.
Outcome:	The proposed model outperforms existing methods on two benchmark datasets.

Copied to clipboard

Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, XiTai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu

ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense (2023.findings-emnlp)

Challenge:	Large language models exhibit limitations when handling complex mathematical reasoning and logical inference tasks.
Approach:	They propose a sparsification strategy to reduce token costs within Multi-agent Debate (MAD) this strategy minimizes ineffective exchanges of information and unproductive discussions among agents .
Outcome:	The proposed approach reduces token costs by up to 94.5% while maintaining performance degradation below 2.0%.

Copied to clipboard

Kankan Zhou, Eason Lai, Wei Bin Au Yeong, Kyriakos Mouratidis, Jing Jiang

Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision (2022.findings-naacl)

Challenge:	a vision-language model with commonsense knowledge can reason beyond common sense . however, pre-trained vision-linguistic models are incapable of interpreting counter-intuitive content .
Approach:	They introduce a probing dataset to evaluate vision-language models' reasoning abilities . they use images that defy commonsense knowledge to test their reasoning abilities.
Outcome:	The proposed dataset evaluates whether pre-trained vision-language models can reason beyond common sense . it contains images that defy commonsense knowledge with regards to color, shape, material, size and position .

Copied to clipboard

Yang Li, Guodong Long, Tao Shen, Jing Jiang

Knowledge Generation for Zero-shot Knowledge-based VQA (2024.findings-eacl)

Challenge:	Distant supervision uses triple facts to label corpus for relation extraction, leading to wrong labeling and long-tail problems.
Approach:	They propose a model to enrich distantly-supervised sentences with entity types by injecting context-free and -related backgrounds into sentences to alleviate sentence-level wrong labeling.
Outcome:	The proposed model achieves state-of-the-art on benchmarks and in overall and long-tail performance.

Copied to clipboard

Rui Cao, Jing Jiang

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention (2020.coling-main)

Challenge:	Recent knowledge-based visual question answering methods do not explicitly show the knowledge needed to answer the questions and therefore lack interpretability.
Approach:	They propose a method which generates knowledge from an LLM and incorporates it into a zero-shot manner.
Outcome:	The proposed method performs better than previous zero-shot K-VQA methods on two benchmarks and is generally relevant and helpful.

Copied to clipboard

Yang Li, Tao Shen, Guodong Long, Jing Jiang, Tianyi Zhou, Chengqi Zhang

Unsupervised Keyphrase Extraction by Learning Neural Keyphrase Set Function (2023.findings-acl)

Challenge:	Existing approaches to handle wrong labeling and long-tail relations are labor-intensive and scarce training data.
Approach:	They propose a neural network to handle wrong labeling and long-tail relations by collaborating relation-augmented attention.
Outcome:	The proposed neural network improves the state-of-the-art on the NYT dataset .

Copied to clipboard

Mingyang Song, Haiyun Jiang, Lemao Liu, Shuming Shi, Liping Jing

FOCUS: Evaluating Pre-trained Vision-Language Models on Underspecification Reasoning (2025.acl-long)

Challenge:	Unsupervised keyphrase extraction is a task of extracting a keyphrase set that provides readers with highlevel information about the key ideas or important topics described in the document.
Approach:	They propose an unsupervised keyphrase extraction task that is a document-set matching problem instead of modeling the relevance between an individual phrase and the document.
Outcome:	The proposed model outperforms the state-of-the-art unsupervised keyphrase extraction baselines by a large margin.

Copied to clipboard

Kankan Zhou, Eason Lai, Kyriakos Mouratidis, Jing Jiang

Towards Generating Controllable and Solvable Geometry Problem by Leveraging Symbolic Deduction Engine (2025.acl-industry)

Challenge:	a new dataset evaluates whether vision-language models have underspecification reasoning abilities . underspecifications are often left incomplete or vague, and are often ignored for mutual understanding .
Approach:	They propose a probing dataset to evaluate whether VLMs have underspecification reasoning . they find that pre-trained vision-language models lack this ability .
Outcome:	The proposed probing dataset shows that pre-trained vision-language models lack underspecification reasoning abilities.

Copied to clipboard

Zhuoxuan Jiang, Tianyang Zhang, Peiyan Peng, Jing Chen, Yinong Xun, Haotian Zhang, Lichi Li, Yong Li, Shaohua Zhang

Text Generation

Challenge:	Compared to math word problems, geometry problems emphasize multi-modal formats and the translation between informal and formal languages.
Approach:	They propose a symbolic deduction engine-based geometry problem generation framework that leverages a symbolic deduction engine to generate geometry problems.
Outcome:	The proposed method avoids inherent biases in translating natural language into formal language and guarantees to control the generated problems in terms of knowledge points and difficulties by an elaborate checking function.

Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together (N19-1)

Copied to clipboard

Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation (2022.coling-1)

Challenge:	Neural networks equipped with self-attention have parallelizable computation and the ability to capture both long-range and local dependencies.
Approach:	They propose a novel attention mechanism called "Multi-mask Tensorized Self-Attention" it captures pairwise and global dependencies by a compatibility function composed of dot-product and additive attentions .
Outcome:	The proposed model outperforms CNN-/RNN-/attention-based models on nine NLP benchmarks with compelling memory- and time-efficiency.

Copied to clipboard

Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang

Machine Translation

Challenge:	Recent studies have incorporated approaches to improving the standard cross-entropy loss to ameliorate the effect of multimodality.
Approach:	They propose a new training oaxe loss which removes the penalty of word order errors in the standard cross-entropy loss.
Outcome:	Extensive experiments on NAT benchmarks show that the proposed approach improves translation quality and improves model performance.

Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model (2021.emnlp-main)

Copied to clipboard

Hongjiang Jing, Zuchao Li, Hai Zhao, Shu Jiang

METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis (2020.coling-main)

Challenge:	Existing models focus on aspect term extraction, opinion term extraction and sentiment polarity classification but ignore the difference.
Approach:	They propose a joint aspect-based sentiment analysis task that focuses on the difference between the two tasks to improve the model's robustness.
Outcome:	Empirical results show that the proposed model outperforms the previous state-of-the-art on four benchmark datasets.

Copied to clipboard

Bin Jiang, Jing Hou, Wanyue Zhou, Chao Yang, Shihan Wang, Liang Pang

Sentiment Analysis

Challenge:	Existing methods for learning complex sentences with multiple aspects are ill-equipped to learn complex sentences .
Approach:	They propose a mutual enhanced transformation network for the ABSA task . it improves representation learning of the aspect with contextual semantic features .
Outcome:	The proposed model improves representation learning of the aspect with contextual semantic features, giving the aspect more abundant information.

Subgraph-Guided Executable Logical Form Generation for Knowledge Base Question Answering (2026.findings-acl)

Copied to clipboard

Yuhang Tian, Dandan Song, Zhijing Wu, Changzhi Zhou, Jun Yang, Huipeng Ma, Chenhao Li, Luan Zhang, Yading Li, Xudong Li, Shenxi Liu, Jing Jiang

Natural Language Interfaces

Challenge:	Existing retrieval-augmented approaches focus on ignoring the structural information of the Knowledge Base (KB) and the question.
Approach:	They propose a structure-aware subgraph retrieval stage that ranks candidate subgraphs by aligning them with the question’s structure, along with semantic relevance.
Outcome:	Experiments on GrailQA, WebQSP, and GraphQuestions show that the proposed framework achieves state-of-the-art performance.

Seeing Culture: A Benchmark for Visual Reasoning and Grounding (2025.emnlp-main)

Copied to clipboard

Burak Satar, Zhixin Ma, Patrick Amadeus Irawan, Wilfried Ariel Mulyawan, Jing Jiang, Ee-Peng Lim, Chong-Wah Ngo

A Co-Matching Model for Multi-choice Reading Comprehension (P18-2)

Challenge:	Multimodal vision-language models (VLMs) have made significant progress in cultural understanding tasks . but these datasets often fall short of providing cultural reasoning while underrepresenting many cultures.
Approach:	They propose a Seeing Culture Benchmark that requires VLMs to reason on culturally rich images in two stages.
Outcome:	The proposed approach requires VLMs to reason on culturally rich images in two stages . the Seeing Culture Benchmark identifies cultural reasoning shortcomings in multimodal models .

Copied to clipboard

Shuohang Wang, Mo Yu, Jing Jiang, Shiyu Chang

Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer (2020.acl-main)

Challenge:	Existing approaches to machine comprehension are based on pairwise sequence matching, but this approach is not suitable for multi-choice reading comprehension since questions and answers are often equally important.
Approach:	They propose a co-matching approach that models whether a passage can match both a question and a candidate answer using a dataset from Chinese exams.
Outcome:	The proposed approach achieves state-of-the-art on the RACE dataset from Chinese middle and high school English examinations.

Copied to clipboard

Jianfei Yu, Jing Jiang, Li Yang, Rui Xia

An Empirical Analysis of the Writing Styles of Persona-Assigned LLMs (2024.emnlp-main)

Challenge:	Existing methods for named entity recognition ignore visual context bias . NER is a key component of many information extraction tasks .
Approach:	They propose to use a multimodal interaction module to generate word-aware visual representations and leverage purely text-based entity span detection as an auxiliary module to guide the final predictions.
Outcome:	The proposed approach achieves state-of-the-art on two benchmark datasets.

Copied to clipboard

Manuj Malik, Jing Jiang, Kian Ming Chai

Actively Learn from LLMs with Uncertainty Propagation for Generalized Category Discovery (2024.naacl-long)

Challenge:	Recent efforts to "personalize" large language models by assigning them specific personas are limited by current knowledge of how well they perform.
Approach:	They use a style embedding model to analyze writing styles of persona-assigned LLMs . they find significant style differences between personas using Kullback-Leibler divergence .
Outcome:	The proposed model shows significant differences in writing styles among personas across socio-demographic groups.

Copied to clipboard

Jinggui Liang, Lizi Liao, Hao Fei, Bobo Li, Jing Jiang

Challenge:	Generalized category discovery (GCD) is a crucial task in open-world computing, where new categories frequently emerge, necessitating models that can adapt and learn continually.
Approach:	They propose to integrate the feedback from LLMs into an active learning paradigm to simplify the labeling task and minimize the spread of inaccurate feedback.
Outcome:	The proposed approach significantly improves baseline models at a nominal average cost.

Embedding WordNet Knowledge for Textual Entailment (C18-1)

Copied to clipboard

Yunshi Lan, Jing Jiang

Representation Learning

Challenge:	Existing deep learning models for textual entailment do not require any feature engineering or linguistic analysis.
Approach:	They propose to embed WordNet-derived lexical entailment relations into specially-learned word vectors and incorporate them into a decomposable attention model for textual enlightment.
Outcome:	The proposed model significantly improves on the SICK and SNLI datasets.

Enhancing Multimodal Named Entity Recognition through Adaptive Mixup Image Augmentation (2025.coling-main)

Copied to clipboard

Bo Xu, Haiqi Jiang, Jie Wei, Hongyu Jing, Ming Du, Hui Song, Hongya Wang, Yanghua Xiao

LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs (2025.acl-long)

Challenge:	Current named entity recognition methods struggle with text-image mismatch problem due to a lack of visual context.
Approach:	They propose an adaptive mixup image augmentation method that generates augmented images based on matching score between text and image .
Outcome:	The proposed method can be integrated into existing models and demonstrate consistent performance improvements.

Copied to clipboard

Chansung Park, Juyong Jiang, Fan Wang, Sayak Paul, Jing Tang

CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification (2024.eacl-long)

Challenge:	LLMOps pipelines are used to migrate knowledge and abilities from service-oriented LLMs to smaller, locally manageable models.
Approach:	They propose an LLMOps pipeline for the seamless migration of knowledge and abilities from service-oriented LLMs to smaller, locally manageable models.
Outcome:	Experiments with leading-edge LLMs show that the proposed pipeline can scale to meet various tasks and domains.

Copied to clipboard

Yang Li, Canran Xu, Guodong Long, Tao Shen, Chongyang Tao, Jing Jiang

CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration (2025.acl-long)

Challenge:	Existing methods to improve pre-trained language models for many-class classification suffer from verbalizer ambiguity . a significant disparity exists between the pre-training and fine-tuning stages of the model .
Approach:	They propose a method to tune pre-trained language models to a broad spectrum of tasks . they use an instance-dependent soft prefix to complement language verbalizers in many-class classification .
Outcome:	The proposed method outperforms baselines on many-class datasets.

Copied to clipboard

Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Phey Ling Kit, Nicholas Gabriel Lim, Cameron Tan Shi Ern, Ee-Peng Lim

Challenge:	Motivational Interviewing (MI) is a client-centered counseling technique designed to address ambivalence and facilitate behavior change in clients.
Approach:	They propose to use a STAR framework to evoke change talk by using large language models to assess MI skill competency, client’s state inference accuracy, topic exploration proficiency, and overall counseling success.
Outcome:	The proposed agent outperforms several state-of-the-art methods and shows more realistic counselor-like behavior.

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026.acl-long)

Copied to clipboard

Hengyuan Zhang, Shiping Yang, Xiao Liang, Chenming Shang, Yuxuan Jiang, Chaofan Tao, Jing Xiong, Hayden Kwok-Hay So, Ruobing Xie, Angel X. Chang, Ngai Wong

Knowledge Fusion By Evolving Weights of Language Models (2024.findings-acl)

Challenge:	Existing studies show that stronger models are not always optimal teachers, suggesting a mismatch between the teacher’s output and the student’s learning ability.
Approach:	They propose a method that routes each prompt to its optimal teacher via a query-level router that jointly considers the student models’ learnability and teacher models’ response quality.
Outcome:	The proposed method outperforms baselines on six benchmarks including instruct tuning and math reasoning settings.

Copied to clipboard

Guodong Du, Jing Li, Hanting Liu, Runhua Jiang, Shuyang Yu, Yifei Guo, Sim Kuan Goh, Ho-Kin Tang

RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion (2020.coling-main)

Challenge:	Experimental results on mainstream language models show that Evolver outperforms previous state-of-the-art models by large margins due to the high training costs of large language models.
Approach:	They propose a method to integrate multiple models from diverse training scenarios into a unified model.
Outcome:	The proposed method outperforms state-of-the-art models on mainstream language models by large margins.

Copied to clipboard

Hao Huang, Guodong Long, Tao Shen, Jing Jiang, Chengqi Zhang

Improving Grammatical Error Correction by Correction Acceptability Discrimination (2024.lrec-main)

Challenge:	Existing approaches for knowledge graph embedding have limitations in complex vector space . embeddability of one-to-many relations is not explicitly alleviated .
Approach:	They propose a relation-adaptive translating embedding function that can be extended to complex vector space.
Outcome:	The proposed translation function improves expressive power and alleviates embedding ambiguity problem.

Copied to clipboard

Bin Cao, Kai Jiang, Fayu Pan, Chenlei Bao, Jing Fan

Syntactic Text Processing

Challenge:	Existing Grammatical Error Correction (GEC) methods overlook the assessment of sentence-level syntax and semantics in the corrected sentence.
Approach:	They propose a correction acceptance discrimination task to assess sentence-level syntax and semantics in corrected sentences and a pipeline method to remove invalid corrections.
Outcome:	The proposed method improves F0.5 score by 1.01% over 13 GEC systems in the BEA-2019 test set.

Fine-grained Entity Typing without Knowledge Base (2021.emnlp-main)

Copied to clipboard

Jing Qian, Yibin Liu, Lemao Liu, Yangming Li, Haiyun Jiang, Haisong Zhang, Shuming Shi

Knowledge Representation

Challenge:	Existing work on fine-grained entity typing (FET) relies on knowledge bases as distant supervision, but lack of or incompleteness of KB can hinder training.
Approach:	They propose a two-step framework that trains FET models without accessing any knowledge base.
Outcome:	The proposed framework achieves competitive performance with respect to the models trained on the original KB-supervised datasets.

An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework Based on Semantic Blocks (2022.coling-1)

Copied to clipboard

Xinnian Liang, Jing Li, Shuangzhi Wu, Jiali Zeng, Yufan Jiang, Mu Li, Zhoujun Li

DAPE V2: Process Attention Score as Feature Map for Length Extrapolation (2025.acl-long)

Challenge:	Existing unsupervised summarization methods fail to consider efficiency and effectiveness when the input document is extremely long.
Approach:	They propose an efficient Coarse-to-Fine Facet-Aware Ranking framework for unsupervised long document summarization based on the semantic block.
Outcome:	The proposed framework can achieve new state-of-the-art unsupervised summarization results on Gov-Report, billSum, arXiv, and PubMed.

Copied to clipboard

Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li