Papers by Wei Xiang

In-context Contrastive Learning for Event Causality Identification (2024.emnlp-main)

Challenge:	Natural language inference (NLI) tasks are difficult to perform on large datasets . a small number of simple sentences can improve model performance, authors say .
Approach:	They propose to use syntactically simple sentences to test the inference ability of NLI models.
Outcome:	The proposed set of simple sentences shows that the models fine-tuned on MNLI and SNLI perform poorly on Simple Pair.

Copied to clipboard

Liang Chao, Wei Xiang, Bang Wang

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models (2026.findings-acl)

Challenge:	Recent prompt learning-based approaches have shown promising improvements on the ECI task . however, they are subject to the delicate design of multiple prompts and positive correlations between the main task and derivate tasks.
Approach:	They propose an event causality identification model that uses contrastive learning to enhance both positive and negative demonstrations.
Outcome:	The proposed model improves on the event-related causality identification task . it uses contrastive learning to enhance both positive and negative demonstrations .

Copied to clipboard

Xinyi Zeng, Xue Yang, Jingyuan Zhang, Huanqian Yan, Xiang Chen, Kaiwen Wei, Hankun Kang, Yu Tian

Responsible & Trustworthy NLP

Challenge:	Existing defense methods rely on fine-tuning or inefficient post-hoc interventions, limiting their ability to address novel attacks.
Approach:	They propose a decoding-level defense mechanism that employs a lightweight discriminator to iteratively steer the decoding process toward safety.
Outcome:	The proposed method improves safety performance by up to 33.40% without fine-tuning on multiple MLLMs.

Demystifying Small Language Models for Edge Deployment (2025.acl-long)

Copied to clipboard

Zhenyan Lu, Xiang Li, Dongqi Cai, Rongjie Yi, Fangming Liu, Wei Liu, Jian Luan, Xiwen Zhang, Nicholas D. Lane, Mengwei Xu

Unsupervised Morphological Tree Tokenizer (2025.findings-acl)

Challenge:	Small language models (SLMs) are a promising solution for resource-constrained devices such as smartphones and the Web of Things.
Approach:	They propose to use SLMs to build and optimize a set of small language models that are publicly accessible.
Outcome:	The proposed models outperform 7B models in general tasks, while their in-context learning capabilities remain limited and their efficiency has significant optimization potential.

Copied to clipboard

Qingyang Zhu, Xiang Hu, Pengyu Ji, Wei Wu, Kewei Tu

Syntactic Text Processing

Challenge:	Conventional statistical tokenizers often disrupt constituent boundaries within words, thereby corrupting semantic information.
Approach:	They propose a method that uses morphological structure guidance to induce character-level structures of words by training a deep model.
Outcome:	Empirical results show that the proposed method retains complete morphemes and outperforms existing methods on morphological segmentation and language modeling tasks.

Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset (2022.emnlp-main)

Copied to clipboard

Haolin Deng, Yanan Zhang, Yangfan Zhang, Wangyang Ying, Changlong Yu, Jun Gao, Wei Wang, Xiaoling Bai, Nan Yang, Jin Ma, Xiang Chen, Tianhua Zhou

Information Extraction & Text Mining

Challenge:	Existing EE datasets define fixed event types and design specific schemas for each of them, failing to cover diverse events emerging from the online text.
Approach:	They propose to use a sentence-level dataset to benchmark Open Event Extraction without restricting event types.
Outcome:	The proposed dataset contains more than 42,000 news titles in 34 topics collected from Chinese web pages.

CSTree-SRI: Introspection-Driven Cognitive Semantic Tree for Multi-Turn Question Answering over Extra-Long Contexts (2025.acl-long)

Copied to clipboard

Zhaowen Wang, Xiang Wei, Kangshao Du, Yiting Zhang, Libo Qin, Yingjie Xia, Li Kuang

Question Answering

Challenge:	Large Language Models (LLMs) have achieved remarkable success in natural language processing (NLP), particularly in single-turn question answering (QA) on short-text.
Approach:	They propose a framework that captures logical correlations across chunks of ELC and maintains coherence of multi-turn Questions.
Outcome:	The proposed framework is able to capture logical correlations across chunks of ELC and maintain coherence of multi-turn Questions.

FinKario: Event-Enhanced Automated Construction of Financial Knowledge Graph (2026.acl-long)

Copied to clipboard

Xiang Li, Penglei Sun, Wanyun Zhou, Zikai Wei, Yongqi Zhang, Xiaowen Chu

LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling (2026.acl-long)

Challenge:	Equity research reports are crucial resources for investors, but lack professional analysis and the rapid evolution of market events outpaces their update cycles.
Approach:	They propose an event-Enhanced automated construction of financial knowledge graph (FinKario) that automatically integrates real-time company fundamentals and market events through prompt-driven extraction guided by professional institutional templates.
Outcome:	The proposed model outperforms financial LLMs by 18.81% and institutional strategies by 17.85% on average in backtesting.

Copied to clipboard

Dawei Xiang, Kexin Chu, Wenyan Xu, Wenhui Zhang, Wei Zhang

Learning Dialogue Representations from Consecutive Utterances (2022.naacl-main)

Challenge:	Experiments show that LAS cuts token usage by 43% and reduces end-to-end latency by more than 36%, while causing at most a 1.4 percentage-point drop in accuracy compared with a strong fixed workflow.
Approach:	They propose a system that dynamically chooses the right workflow for each query.
Outcome:	Experiments show that LAS cuts token usage by 43% and reduces end-to-end latency by more than 36% while causing at most a 1.4 percentage-point drop in accuracy compared with a strong fixed workflow.

Copied to clipboard

Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall, Xiaofei Ma, Andrew Arnold, Bing Xiang

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)

Challenge:	Dialogue Sentence Embedding (DSE) is a self-supervised contrastive learning method that learns effective dialogue representations suitable for a wide range of dialogue-oriented tasks.
Approach:	They propose a self-supervised contrastive learning method that learns dialogue representations suitable for a wide range of dialogue tasks.
Outcome:	The proposed method outperforms baselines on five dialogue tasks on a few-shot and zero-shot datasets.

Copied to clipboard

Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang

Multilinguality

Challenge:	Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool.
Approach:	They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images .
Outcome:	The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images.

Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models (2026.acl-long)

Copied to clipboard

Xiang Hu, Zhanchao Zhou, Ruiqi Liang, Zehuan Li, Wei Wu, Jianguo Li

MAPO: Advancing Multilingual Reasoning through Multilingual-Alignment-as-Preference Optimization (2024.acl-long)

Challenge:	a recent study explores efficient ultra-long context modeling.
Approach:	They propose to use Hierarchical Sparse Attention to achieve efficient ultra-long context modeling.
Outcome:	The proposed model performs comparable to full-attention baselines on in-domain and out-of-domain tasks.

Copied to clipboard

Shuaijie She, Wei Zou, Shujian Huang, Wenhao Zhu, Xiang Liu, Xiang Geng, Jiajun Chen

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Challenge:	Existing models exhibit inconsistent reasoning abilities across different languages . existing models lack consistency across languages due to imbalance of training data .
Approach:	They propose a multilingual alignment-as-preference optimization framework to align reasoning processes in other languages with the dominant language.
Outcome:	The proposed framework improves multilingual reasoning across languages on three benchmarks.

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization (2025.emnlp-demos)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Dawei Xiang, Wenyan Xu, Kexin Chu, Tianqi Ding, Zixu Shen, Yiming Zeng, Jianchang Su, Wei Zhang

Low-Resource NLP

Challenge:	PromptSculptor automates the iterative prompt optimization process for Text-to-Image models . previous work focused on generating detailed, high-quality prompts based on user feedback .
Approach:	They propose a framework that decomposes a task into four specialized agents . they use Chain-of-Thought reasoning to transform a short, vague user prompt into a comprehensive, refined prompt.
Outcome:	The proposed framework significantly improves output quality and reduces iterations needed for user satisfaction.

LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning (2026.acl-long)

Copied to clipboard

Zerui Chen, Qinggang Zhang, Zhishang Xiang, Zhimin Wei, Linfeng Gao, Xiao Huang, Zhihong Zhang, Jinsong Su

Encoding and Fusing Semantic Connection and Linguistic Evidence for Implicit Discourse Relation Recognition (2022.findings-acl)

Challenge:	Graph-based Retrieval-Augmented Generation (GraphRAG) is a new approach to document retrieval, but it is not suitable for legal reasoning.
Approach:	They propose a framework for reliable legal reasoning that structures knowledge as relational graphs and uses a multi-agent system to verify validity.
Outcome:	The proposed framework outperforms existing GraphRAG models in accurate and trustworthy legal analysis.

Copied to clipboard

Wei Xiang, Bang Wang, Lu Dai, Yijun Mo

Challenge:	Existing studies use one attention mechanism to improve contextual semantic representation learning for implicit discourse relation recognition (IDRR).
Approach:	They propose a Multi-Attentive Neural Fusion model to fuse linguistic evidence and semantic connection for IDRR by using a Dual Attention Network and an Offset Matrix Network.
Outcome:	The proposed model achieves state-of-the-art on the PDTB 3.0 corpus.

Improved Pseudo Data for Machine Translation Quality Estimation with Constrained Beam Search (2023.emnlp-main)

Copied to clipboard

Xiang Geng, Yu Zhang, Zhejian Lai, Shuaijie She, Wei Zou, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang

Text Generation

Challenge:	evaluating the quality of machine translation outputs becomes increasingly essential with the rapid development of machine language (MT).
Approach:	They propose to generate pseudo data using the MT model with constrained beam search (CBSQE) they propose to preserve the reference parts with high MT probabilities as correct translations .
Outcome:	The proposed model outperforms strong baselines in both supervised and unsupervised settings.

Stephanie: Step-by-Step Dialogues for Mimicking Human Interactions in Social Conversations (2025.findings-naacl)

Copied to clipboard

Hao Yang, Hongyuan Lu, Xinhua Zeng, Yang Liu, Xiang Zhang, Haoran Yang, Yumeng Zhang, Shan Huang, Yiran Wei, Wai Lam

Dialogue Systems & Conversational Agents

Challenge:	a new paradigm for dialogue systems is being developed to mimic human interactions . the current single-step dialogue paradigm lacks the depth and fluidity of human interactions.
Approach:	They propose a step-by-step dialogue paradigm that mimics human interactions . they use a dataset to fine-tune existing language models .
Outcome:	The proposed system mimics the dynamic nature of human conversations . it is compared with existing paradigms and will be released later this year .

Open Set Relation Extraction via Unknown-Aware Training (2023.acl-long)

Copied to clipboard

Jun Zhao, Xin Zhao, WenYu Zhan, Qi Zhang, Tao Gui, Zhongyu Wei, Yun Wen Chen, Xiang Gao, Xuanjing Huang

Information Extraction & Text Mining

Challenge:	Existing supervised relation extraction methods can still misclassify unknown relations into known relations due to the lack of supervision signals.
Approach:	They propose a method that regularizes the model by dynamically synthesizing negative instances that can provide the missing supervision signals.
Outcome:	The proposed method achieves SOTA unknown relation detection without compromising the classification of known relations.

FusionFlow: Enabling Deep Structural Exploration for Automated Agentic Workflow Generation (2026.acl-long)

Copied to clipboard

Xiang Wang, Zongtao Yang, Zhuojian Hong, Shuhao Zhang, Wei Wei

Symbolic Working Memory Enhances Language Models for Complex Rule Application (2024.emnlp-main)

Challenge:	Existing workflow generation methods rely on incremental refinement or tree-based search over a single evolving workflow.
Approach:	They propose a framework centered on workflow fusion that synthesizes multiple independently evolved workflows and allows exploration of deeper regions of the workflow space within a finite budget.
Outcome:	Experiments show that FusionFlow outperforms existing workflow generation methods on six reasoning benchmarks.

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs (2026.findings-eacl)

Challenge:	Large Language Models (LLMs) excel in single-step rule application but struggle with multi-step deductive reasoning when rules are presented non-sequentially.
Approach:	They propose to augment LLMs with external working memory and introduce a neurosymbolic framework for rule application that stores facts and rules in both natural language and symbolic forms, enabling precise tracking.
Outcome:	The proposed framework iteratively performs symbolic rule grounding and LLM-based rule implementation.

Copied to clipboard

Paiheng Xu, Gang Wu, Xiang Chen, Tong Yu, Chang Xiao, Franck Dernoncourt, Tianyi Zhou, Wei Ai, Viswanathan Swaminathan

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation (2021.acl-long)

Challenge:	Large Language Models (LLMs) can generate code from natural language queries, but runtime code generation is limited due to unverified code, security risks, longer response times, and higher computational costs.
Approach:	They propose an offline simulation framework to curate a software-specific skillset by exploiting large language models and publicly available scripting guides.
Outcome:	The proposed framework significantly improves automation success rates, reduces response time, and saves runtime token costs compared to traditional runtime code generation.

Copied to clipboard

Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, Ben Kao

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models (2025.emnlp-main)

Challenge:	Recent studies report improvements when equipping models with multimodal information, but it remains unclear whether such improvements actually come from the multimodal part.
Approach:	They propose to extend conventional text-only translation models with multimodal information by extending them with visual input.
Outcome:	The proposed models replicate similar gains as recently developed multimodal-integrated systems achieved, but learn to ignore multimodal information.

Copied to clipboard

Bajian Xiang, Shuaijiang Zhao, Tingwei Guo, Wei Zou

LLM Inductive Reasoning Through Multi-Agent Enhanced Monte Carlo Tree Search (2026.findings-acl)

Challenge:	LSLMs have impressive conversational generation abilities, but consistently fall short of traditional pipeline systems on semantic understanding benchmarks.
Approach:	They propose to analyze the performance gap between speech and text inputs through a systematic experiment . they find that representation similarity is strongly correlated with the modality gap .
Outcome:	The proposed models improve the accuracy of speech inputs and their semantic understanding benchmarks.

Copied to clipboard

Xiang Li, Yucheng Zhou, Xiangzhi Wei, Zesheng Shi, Haiyuan Wan, Gong Yifan, Fangming Liu, Jing Li

MaDS: Long-Horizon GUI Automation via Synergizing Dual-Layer Memory and Multi-Round Debate (2026.acl-long)

Challenge:	Existing methods for enhancing inductive reasoning of large language models often lack explicit optimization guidance and effective error correction.
Approach:	They propose a plug-and-play test-time framework that integrates multi-agent coordination with Monte Carlo Tree Search to improve inductive reasoning.
Outcome:	The proposed framework outperforms existing methods on four benchmarks and shows consistent improvements on QWQ-32B and Deepseek-V3 .

Copied to clipboard

Pengchen Chen, Shi Chen, Qiming Ye, Xinli Chen, Xinran Li, Wei Xiang

Challenge:	Current methods struggle to distinguish targets in low Signal-to-Noise Ratio environments and lack sufficient pre-execution verification to prevent error accumulation.
Approach:	They propose a Memory-augmented Debate System to ensure precise grounding across diverse interfaces and handle irreversible errors in extended workflows.
Outcome:	The proposed system achieves a 90.23% task success rate on MaDS-Benchmark and strong performance on public benchmarks including AITW, AITZ, CAGUI, and GUIOdyssey.

Multi-level Relevance Document Identifier Learning for Generative Retrieval (2025.acl-long)

Copied to clipboard

Fuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang, Shuai Zhang, Xiang Li, Fuzhen Zhuang, Wei Lin, Zhao Zhang

Information Retrieval

Challenge:	Existing methods generate DocIDs based on textual content, which may result in weak semantic connections for similar documents due to variations in expression.
Approach:	They propose a new retrieval paradigm that generates unique document identifiers . they propose to use queries as a bridge to connect documents with varying relevance levels .
Outcome:	The proposed approach outperforms existing methods on multilingual e-commerce search datasets.

Supporting Clustering with Contrastive Learning (2021.naacl-main)

Copied to clipboard

Dejiao Zhang, Feng Nan, Xiaokai Wei, Shang-Wen Li, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Balancing Visual Context Understanding in Dialogue for Image Retrieval (2024.findings-emnlp)

Challenge:	Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space, but different categories overlap with each other at the beginning of the learning process.
Approach:	They propose a framework to leverage contrastive learning to promote better separation between different categories by optimizing a clustering objective defined in the representation space.
Outcome:	The proposed framework improves state-of-the-art accuracy and normalized mutual information on short text clustering and combines top-down and bottom-up instance discrimination to achieve better distances.

Copied to clipboard

Zhaohui Wei, Lizi Liao, Xiaoyu Du, Xinguang Xiang

Rotation Control Unlearning: Quantifying and Controlling Continuous Unlearning for LLM with The Cognitive Rotation Space (2026.findings-acl)

Challenge:	Existing methods neglect the nuanced nature of conversational context, causing a disconnect between dialogue context and visual content.
Approach:	They propose a framework to enhance the comprehension of dialogue history and improve cross-modal matching for image retrieval.
Outcome:	The proposed framework outperforms existing methods in dialogue-to-image retrieval tasks.

Copied to clipboard

Xiang Zhang, Kun Wei, Xu Yang, Jiahua Li, Su Yan, Cheng Deng

Challenge:	Existing methods to remove undesirable data from Large Language Models suffer from cumulative catastrophic utility loss under continuous unlearning requests.
Approach:	They propose a method that leverages the rotational salience weight of RCU to quantify and control the unlearning degree in the continuous unlearning process.
Outcome:	The proposed method achieves SOTA performance without a retained dataset.

VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation (2024.acl-long)

Copied to clipboard

Max Ku, Dongfu Jiang, Cong Wei, Xiang Yue, Wenhu Chen

Explainability & Interpretability in NLP

Challenge:	Existing metrics for conditional image generation are opaque and lack explainability . evaluators of these metrics have limited ability to evaluate image synthesis tasks .
Approach:	They propose a Visual Instruction-guided Explainable metric for evaluating conditional image models.
Outcome:	The proposed model achieves a high Spearman correlation with human evaluations, but is weaker than GPT-4o and GPT-v in evaluating synthetic images.

S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering (2023.acl-short)

Copied to clipboard

Fangyu Lei, Xiang Li, Yifan Wei, Shizhu He, Yiming Huang, Jun Zhao, Kang Liu

Lexical Knowledge Internalization for Neural Dialog Generation (2022.acl-long)

Challenge:	Existing question answering systems use a retriever-reader framework to answer multi-hop questions . existing models lack retrieval, selector, and reasoner capabilities .
Approach:	They propose a three-stage text tableQA framework which comprises of retriever, selector, and reasoner.
Outcome:	The proposed framework outperforms baseline methods in the few-shot setting and ranks first on the HybridQA leaderboard.

Copied to clipboard

Zhiyong Wu, Wei Bi, Xiang Li, Lingpeng Kong, Ben Kao

Dialogue Systems & Conversational Agents

Challenge:	Existing knowledge-grounded dialog models ignore the knowledge that resides in people's minds during a conversation.
Approach:	They propose to integrate lexical knowledge internally into the model's parameters instead of further conditioning them on external knowledge . they adopt contrastive learning approach and use a dictionary-based token-level lexicon retriever that requires only weak supervision.
Outcome:	The proposed model can relate J.K Rowling to Khalsa Aid with the knowledge retrieved from Wikipedia.

AutoDSL: Automated domain-specific language design for structural representation of procedures with constraints (2024.acl-long)

Copied to clipboard

Yu-Zhe Shi, Haofei Hou, Zhangqian Bi, Fanxu Meng, Xiang Wei, Lecheng Ruan, Qining Wang

Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction (2022.emnlp-main)

Challenge:	Domain-specific Language (DSL) is an effective tool to express constraints structurally, but requires case-by-case hand-crafting.
Approach:	They propose a framework to automate domain-specific language constraint design . they propose 'autoDSL' framework to optimize syntactic and semantic constraints .
Outcome:	The framework automates constraint design across domains and abstracts semantic constraints.

Copied to clipboard

Lu Dai, Bang Wang, Wei Xiang, Yijun Mo

Encoding Hierarchical Schema via Concept Flow for Multifaceted Ideology Detection (2024.findings-acl)

Challenge:	Existing prompt-tuning methods for event argument extraction lack entity information . eAE is a key step of event extraction, but it requires a pre-trained language model to extract event arguments.
Approach:	They propose a prompt-tuning method that takes advantage of entity information and pre-trained language models.
Outcome:	The proposed method outperforms the state-of-the-art prompt-tuning methods on an english dataset.

Copied to clipboard

Songtao Liu, Bang Wang, Wei Xiang, Han Xu, Minghua Xu

Challenge:	Existing studies on ideology detection focus on one generic facet and ignore label semantics and explanatory descriptions of ideologies.
Approach:	They propose a concept semantics-enhanced framework for multifaceted ideology detection . it enables concepts to flow across levels of the schema tree and enriches concept representations with multi-granularity semantics.
Outcome:	The proposed framework achieves state-of-the-art in the cross-topic scenario and on the benchmark dataset.

Doc-V*: Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA (2026.acl-long)

Copied to clipboard

Yuanlei Zheng, Pei Fu, Hang Li, Ziyang Wang, Yuyi Zhang, Wenyu Ruan, Xiaojin Zhang, Zhongyu Wei, Zhenbo Luo, Jian Luan, Wei Chen, Xiang Bai

Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)

Challenge:	Existing OCR-free approaches to document visual question answering are brittle and passive.
Approach:	They propose an OCR-free agentic framework that casts multi-page DocVQA as sequential evidence aggregation.
Outcome:	The proposed framework outperforms open-source and proprietary models in five benchmarks and improves out-of-domain performance by 47.9% over baseline.

Copied to clipboard

Xiang Fei, Jinghui Lu, Qi Sun, Hao Feng, Yanjie Wang, Wei Shi, An-Lan Wang, Jingqun Tang, Can Huang

Challenge:	Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences.
Approach:	They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences.
Outcome:	Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs.

Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora (2022.naacl-main)

Copied to clipboard

Xisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao, Shang-Wen Li, Xiaokai Wei, Andrew Arnold, Xiang Ren

Pairwise Supervised Contrastive Learning of Sentence Representations (2021.emnlp-main)

Challenge:	Pretrained language models are typically learned over a large, static corpus and fine-tuned for various downstream tasks.
Approach:	They propose to continuously update a pretrained language model to adapt to emerging data and to keep track of the model's performance.
Outcome:	The proposed model can adapt to new corpora while retaining knowledge in earlier domains.

Copied to clipboard

Dejiao Zhang, Shang-Wen Li, Wei Xiao, Henghui Zhu, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)

Challenge:	Recent efforts to improve sentence representation learning have a common weakness . siamese or triplet loss only learns from individual sentence pairs or tripletes .
Approach:	They propose a discrimination-based approach to bridge entailment and contradiction understanding with categorical concept encoding.
Outcome:	The proposed method outperforms the state-of-the-art method on downstream tasks . it improves 10%–13% on clustering tasks and 5%–6% on STS tasks compared with the previous method .

Copied to clipboard

Shaokai He, Kaiwen Wei, Xinyi Zeng, Xiang Chen, Xue Yang, Zhenyang Li, Jiang Zhong, Yu Tian

ConnPrompt: Connective-cloze Prompt Learning for Implicit Discourse Relation Recognition (2022.coling-1)

Challenge:	Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs .
Approach:	They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations .
Outcome:	The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation .

Copied to clipboard

Wei Xiang, Zhenglin Wang, Lu Dai, Bang Wang

TEPrompt: Task Enlightenment Prompt Learning for Implicit Discourse Relation Recognition (2023.findings-acl)

Challenge:	Existing paradigms for Implicit Discourse Relation Recognition (IDRR) do not exploit linguistic evidence embedded in the pre-training process.
Approach:	They propose a new paradigm to detect and classify relation sense between two text segments without an explicit connective.
Outcome:	The proposed method significantly outperforms the state-of-the-art algorithms even with fewer training data.

Copied to clipboard

Wei Xiang, Chao Liang, Bang Wang

Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale (2024.acl-long)

Challenge:	Existing prompt learning models for IDRR use multiple-prompt decisions from three different yet much similar connective prediction templates.
Approach:	They propose to fuse three related tasks to fuse the learned features of auxiliary tasks to create a prompt learning model that can be used to boost the main task.
Outcome:	The proposed model outperforms the ConnPrompt in the training phase and in the testing phase.

Copied to clipboard

Xiang Hu, Pengyu Ji, Qingyang Zhu, Wei Wu, Kewei Tu

What Would Happen Next? Predicting Consequences from An Event Causality Graph (2024.findings-emnlp)

Challenge:	Existing syntactic language models require a gold tree and sequential training to generate sentences.
Approach:	They propose an unsupervised syntactic language model that incrementally generates a sentence with its syntaktic tree in a left-to-right manner.
Outcome:	The proposed model outperforms existing models on grammar induction and comprehension tasks while holding a substantial acceleration on training.

Copied to clipboard

Chuanhong Zhan, Wei Xiang, Liang Chao, Bang Wang

Structured Data in NLP

Challenge:	Existing script event prediction task forcasts the subsequent event based on an event script chain, but the evolution of historical events is more complicated in real world scenarios.
Approach:	They propose a Causality Graph Event Prediction task that forecasts consequential event based on an Event Causity Graph (ECG).
Outcome:	The proposed model outperforms the advanced competitors for the CGEP task.

Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs (2024.acl-long)

Copied to clipboard

Siyuan Wang, Zhongyu Wei, Yejin Choi, Xiang Ren

Ideology Takes Multiple Looks: A High-Quality Dataset for Multifaceted Ideology Detection (2023.emnlp-main)

Challenge:	Large language models (LLMs) have impressive human-like performance across various reasoning tasks, but their mastery of underlying inferential rules falls short of human capabilities.
Approach:	They propose a logic scaffolding inferential rule generation framework to construct an infer- ential rule base, ULogic, comprising both primitive and compositional rules across five domains.
Outcome:	The proposed model improves the ability to generate accurate, complex and abstract conclusions and premises and improves various commonsense reasoning tasks.

Copied to clipboard

Songtao Liu, Ziling Luo, Minghua Xu, Lixiao Wei, Ziyao Wei, Han Yu, Wei Xiang, Bang Wang

Challenge:	Existing datasets for the ID task only label a text as ideologically left- or right-leaning as a whole, regardless whether the text containing one or more different issues.
Approach:	They construct an ideological schema for a multifaceted ideology detection task using MITweet and an English Twitter dataset.
Outcome:	The proposed task uses a MITweet dataset with 12,594 English Twitter posts, each annotated with a Relevance and an Ideology label for all twelve facets.

Evaluating Instructively Generated Statement by Large Language Models for Directional Event Causality Identification (2025.findings-acl)

Copied to clipboard

Wei Xiang, Chuanhong Zhan, Qing Zhang, Bang Wang

Identifying while Learning for Document Event Causality Identification (2024.acl-long)

Challenge:	Existing studies focus on identifying existence of causality between two event mentions, but the direction of causalities is crucial for understanding the causal relation.
Approach:	They propose to instruct a GLM to generate causality statements and identify directional event causality by evaluating the generated statements.
Outcome:	The proposed method significantly outperforms state-of-the-art methods even with fewer training data.

Copied to clipboard

Cheng Liu, Wei Xiang, Bang Wang

Challenge:	Existing studies focus on causality existence, but ignore causal direction.
Approach:	They propose a new identifying while learning mode for the ECI task that takes care of the causal direction and updates events’ representations for boosting next round of causality identification.
Outcome:	The proposed method outperforms the state-of-the-art methods on two public datasets.

Route Sparse Autoencoder to Interpret Large Language Models (2025.emnlp-main)

Copied to clipboard

Wei Shi, Sihang Li, Tao Liang, Mingyang Wan, Guojun Ma, Xiang Wang, Xiangnan He

Explainability & Interpretability in NLP

Challenge:	Sparse autoencoders (SAEs) extract interpretable and monosemantic features in large language models . prior work focused on feature extraction from a single layer, failing to capture activations that span multiple layers.
Approach:	They propose a framework that integrates a routing mechanism with a shared SAE to efficiently extract features from multiple layers.
Outcome:	The proposed framework extracts features from multiple layers while incurring minimal parameter overhead while achieving high interpretability and flexibility.

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)

Copied to clipboard

Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang

Responsible & Trustworthy NLP

Challenge:	Current document image parsing solutions rely on specialized models or generate content autoregressively.
Approach:	They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation.
Outcome:	The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency.

Structured Optimal Brain Pruning for Large Language Models (2024.emnlp-main)

Copied to clipboard

Jiateng Wei, Quan Lu, Ning Jiang, Siqi Li, Jingyang Xiang, Jun Chen, Yong Liu