Papers by Yang Du

Language Models as Inductive Reasoners (2024.eacl-long)

Challenge:	Large Language Models (LLMs) have demonstrated promising capabilities in topic discovery, but their direct application to topic modeling suffers from issues such as incomplete topic coverage, misalignment of topics, and inefficiency.
Approach:	They propose a novel LLM-in-the-loop framework that integrates Large Language Models with Neural Topic Models (NTMs) global topics and document representations are learned through the NTM, while an LLM refines these topics using an Optimal Transport (OT)-based alignment objective.
Outcome:	The proposed framework improves topic interpretability while preserving the efficiency of existing NTMs.

Copied to clipboard

Zonglin Yang, Li Dong, Xinya Du, Hao Cheng, Erik Cambria, Xiaodong Liu, Jianfeng Gao, Furu Wei

Model Composition for Multimodal Large Language Models (2024.acl-long)

Challenge:	Inductive reasoning is a core component of human intelligence.
Approach:	They propose a task to induce natural language rules from natural language facts using natural language as representation for knowledge instead of formal language.
Outcome:	The proposed task surpasses baselines in both automatic and human evaluations.

Copied to clipboard

Chi Chen, Yiyang Du, Zheng Fang, Ziyue Wang, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)

Challenge:	Existing methods for creating versatile MLLMs rely on joint training with paired instruction data, which is resource-intensive and challenging to extend to new modalities.
Approach:	They propose a new paradigm for multimodal large language models by reusing modality encoders and merging LLM parameters.
Outcome:	The proposed model retains the modal understanding capabilities of each original model.

Copied to clipboard

Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, null Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong

FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval (2026.findings-acl)

Challenge:	Large language models exhibit significant performance discrepancies between high- and low-resource languages.
Approach:	They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset.
Outcome:	The proposed model achieves consistent multilingual representations across languages.

Copied to clipboard

Caishuang Huang, Yang Qiao, Rongyu Zhang, Junjie Ye, Pu Lu, null Wuwenxi, Meng Zhou, Xiku Du, Qi Zhang, Tao Gui, Xuanjing Huang

Dialogue Systems & Conversational Agents

Challenge:	Existing data synthesis methods rely on static tools to generate queries . this approach fails to capture the implicit, event-driven nature of real-world needs .
Approach:	They propose a forward synthesis framework to generate high-quality financial dialogues . they construct a repository of 43,066 tools and synthesize over 148k dialogue instances .
Outcome:	Experiments show that models trained on FinToolSyn achieve a 21.06% improvement . the framework is designed to generate high-quality financial dialogues .

Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment (2025.findings-acl)

Copied to clipboard

Hongda Sun, Jiaren Peng, Wenzhong Yang, Liang He, Bo Du, Rui Yan

Dialogue Systems & Conversational Agents

Challenge:	Medical dialogue systems (MDS) struggle to identify relevant medical knowledge and generate accurate responses.
Approach:	They propose a medical dialogue system that integrates knowledge refining and dynamic prompt adjustment to improve medical knowledge and accuracy.
Outcome:	The proposed system outperforms state-of-the-art systems in both generation quality and medical entity accuracy.

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models (2026.acl-long)

Copied to clipboard

Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen

Relation-Aware Question Answering for Heterogeneous Knowledge Graphs (2023.findings-emnlp)

Challenge:	Existing adapter-based transfer methods treat instruction-tuned models as passive targets . direct fine-tuning can disrupt this delicate balance and lead to instability or performance degradation.
Approach:	They propose a framework that incorporates instruction-level guidance into task adaptation.
Outcome:	The proposed framework outperforms direct fine-tuning and representative transfer-based baselines while maintaining robust generalization and favorable test-time scaling behavior.

Copied to clipboard

Haowei Du, Quzhe Huang, Chen Li, Chen Zhang, Yang Li, Dongyan Zhao

Structured Data in NLP

Challenge:	Existing retrieval-based approaches to solve multihop Knowledge Base Question Answering (KBQA) fail to utilize information from head-tail entities and the semantic connection between relations to enhance the information capturing of relations in KGs.
Approach:	They propose to use a dual relation graph to find the answer entity in a knowledge graph . they use primal entity graph reasoning, dual relation grafitment and interaction .
Outcome:	The proposed approach achieves significant performance gain over the prior state-of-the-art on two public datasets, WebQSP and CWQ.

IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Web (2025.findings-acl)

Copied to clipboard

Hongcheng Guo, Wei Zhang, Junhao Chen, Yaonan Gu, Jian Yang, Junjia Du, Shaosheng Cao, Binyuan Hui, Tianyu Liu, Jianxin Ma, Chang Zhou, Zhoujun Li

Unveiling Project-Specific Bias in Neural Code Models (2024.lrec-main)

Challenge:	Existing models have been introduced to improve image comprehension, but there is no robust benchmark for imagetoweb conversion.
Approach:	They propose a benchmark to assess imagetoweb conversion proficiency of large multimodal models . they propose to measure layout information of web pages by parsing the Document Object Model tree .
Outcome:	The proposed benchmark measures the layout information of web pages—i.e., the positional relationships between elements—which has been overlooked by prior work.

Copied to clipboard

Zhiming Li, Yanzhou Li, Tianlin Li, Mengnan Du, Bozhi Wu, Yushi Cao, Junzhe Jiang, Yang Liu

MISP-Meeting: A Real-World Dataset with Multimodal Cues for Long-form Meeting Transcription and Summarization (2025.acl-long)

Challenge:	Large Language Models (LLMs) based neural code models struggle to generalize effectively to real-world inter-project out-of-distribution data.
Approach:	They propose a Cond-Idf measurement to measure the relatedness of a token with a label and its project-specificness.
Outcome:	The proposed framework improves both inter-project OOD generalization and adversarial robustness while not sacrificing accuracy on intra-project IID data.

Copied to clipboard

HangChen HangChen, Chao-Han Huck Yang, Jia-Chen Gu, Sabato Marco Siniscalchi, Jun Du

Large Language Models for Automated Open-domain Scientific Hypotheses Discovery (2024.findings-acl)

Challenge:	Existing systems that can recognize spoken content, extract key information, and produce concise summaries are lacking in meeting transcription and summarization.
Approach:	They propose a multimodal dataset that integrates information from speech, vision, and text modalities to facilitate automatic meeting transcription and summarization (AMTS).
Outcome:	The proposed dataset reduces the character error rate (CER) by 36.60% to 20.27% and improves speech recognition and large language models.

Copied to clipboard

Zonglin Yang, Xinya Du, Junxian Li, Jie Zheng, Soujanya Poria, Erik Cambria

ZSEE: A Dataset based on Zeolite Synthesis Event Extraction for Automated Synthesis Platform (2024.findings-naacl)

Challenge:	Existing research on hypothetical induction is limited by the observation annotations in the dataset and the ground truth hypotheses are mostly commonsense knowledge.
Approach:	They propose a first dataset for social science academic hypotheses discovery using raw web corpus as observations and propose valid, useful scientific hypothese . they propose 'a multi-module framework' that includes feedback mechanisms to boost performance.
Outcome:	The proposed dataset generates valid, novel, and helpful scientific hypotheses, even new to humanity, using open-domain data and a web corpus as observations.

Copied to clipboard

Song He, Xin Peng, Yihan Cai, Xin Li, Zhiqing Yuan, WenLi Du, Weimin Yang

Information Extraction & Text Mining

Challenge:	Automated synthesis of zeolite holds great significance for attaining economic and environmental benefits.
Approach:	They propose an event extraction task to mine structural synthesis actions from experimental narratives for modular automated synthesis.
Outcome:	The proposed method can significantly expedite automated synthesis of zeolites owing to its machine readability.

GLM: General Language Model Pretraining with Autoregressive Blank Infilling (2022.acl-long)

Copied to clipboard

Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)

Challenge:	Existing pretraining frameworks do not perform well for all tasks of three main categories, such as natural language understanding (NLU), unconditional generation, and conditional generation.
Approach:	They propose a general language model based on autoregressive blank infilling to address this challenge.
Outcome:	The proposed model outperforms BERT, T5, and GPT on a wide range of tasks across NLU, conditional and unconditional generation tasks.

Copied to clipboard

Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

Each graph is a new language: Graph Learning with LLMs (2025.findings-acl)

Challenge:	Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs.
Approach:	They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.
Outcome:	Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 .

Copied to clipboard

Huachi Zhou, Jiahe Du, Chuang Zhou, Chang Yang, Yilin Xiao, Yuxuan Xie, Xiao Huang

Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu

Challenge:	Natural language is used to describe graphs, but graph descriptions become verbose and only relying on attribute embeddings limits LLM’s ability to capture adequate graph structural information.
Approach:	They propose a graph-defined language for large language model that translates the graph into a corpus instead of graph descriptions and pre-trains LLMs on this corpus to adequately understand the graph.
Outcome:	Experiments on five datasets show that the proposed framework outperforms description-based and embedding-based baselines by efficiently modeling different orders of neighbors.

Copied to clipboard

Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction (2020.acl-main)

Challenge:	Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer.
Approach:	They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions.
Outcome:	The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios.

Copied to clipboard

Chuang Fan, Chaofa Yuan, Jiachen Du, Lin Gui, Min Yang, Ruifeng Xu

Med-SRAF: A Multi-Agent Framework for Medical Reasoning via Semantic Routing and Agentic Fusion (2026.findings-acl)

Challenge:	Existing methods to extract emotions and causes from unannotated text are pipelined, causing error propagation.
Approach:	They propose to transform a task into a procedure of parsing-like directed graph construction . they propose to generate a directed graph with labeled edges based on a sequence of actions .
Outcome:	The proposed method outperforms the state-of-the-art methods by 6.71% (p0.01) in F1 measure.

Copied to clipboard

Xiao Li, Zhuo Chen, Jun Xia, Hongxin Xiang, Chao Wang, Wenjie Du, Yang Wang

Information Retrieval

Challenge:	Existing RAG methods suffer from a two-part problem: semantic drift and concatenation fallacy . et al.: rapid development of Large Language Models has led to a paradigm shift in artificial intelligence .
Approach:	They propose a multi-agent retrieval augmentation framework guided by medical domain knowledge to address these challenges.
Outcome:	The proposed framework outperforms existing general RAG baselines on five widely used medical benchmarks.

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification (2026.acl-long)

Copied to clipboard

Penghui Yang, Cunxiao Du, Fengzhuo Zhang, Haonan Wang, Tianyu Pang, Chao Du, Bo An

VPL: Visual Proxy Learning Framework for Zero-Shot Medical Image Diagnosis (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) can process extremely long contexts, requiring efficient inference over extended inputs.
Approach:	They propose a model that uses a constant-sized key-value cache to train long-context models.
Outcome:	Experimental results show that LongSpec achieves 3.26x speedup over strong Flash Attention baselines and 2.34x wall clock time on four math reasoning tasks.

Copied to clipboard

Jiaxiang Liu, Tianxiang Hu, Huimin Xiong, Jiawei Du, Yang Feng, Jian Wu, Joey Zhou, Zuozhu Liu

SEMGraph: Incorporating Sentiment Knowledge and Eye Movement into Graph Model for Sentiment Analysis (2022.emnlp-main)

Challenge:	Insufficient medical text precision and the modal disparity between text and vision spaces pose challenges for vision-language models like CLIP.
Approach:	They propose a visual proxy learning framework that combines a text refinement module and a stable Sinkhorn algorithm to enhance the diagnostic performance.
Outcome:	The proposed model outperforms the state-of-the-art CLIP inference by 1.69% to 15.31% on five datasets covering various diseases.

Copied to clipboard

Bingbing Wang, Bin Liang, Jiachen Du, Min Yang, Ruifeng Xu

Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)

Challenge:	Existing research on sentiment analysis based on eye movement signals has been attributed importance.
Approach:	They propose a linguistic probing eye movement paradigm to extract eye movement features based on the relationship between linguistic features and human reading behavior.
Outcome:	The proposed graph architecture achieves state-of-the-art performance on two sentiment analysis datasets with eye movement signals and three sentiment analysis data without eye movement signal.

Copied to clipboard

Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han

Challenge:	Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents.
Approach:	They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation.
Outcome:	Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks.

MolTC: Towards Molecular Relational Modeling In Language Models (2024.findings-acl)

Copied to clipboard

Junfeng Fang, Shuai Zhang, Chang Wu, Zhengyi Yang, Zhiyuan Liu, Sihang Li, Kun Wang, Wenjie Du, Xiang Wang

Agentic-R1: Distilled Dual-Strategy Reasoning (2025.emnlp-main)

Challenge:	Molecular Relational Learning (MRL) is a promising way to understand interactions between molecular pairs.
Approach:	They propose a novel LLM-based multi-modal framework for molecular interaction modeling following Chain-of-Thought (CoT) theory which integrates graphical information of two molecules in pair.
Outcome:	The proposed framework integrates graphical information of two molecules in pair.

Copied to clipboard

Weihua Du, Pranjal Aggarwal, Sean Welleck, Yiming Yang

Adversarial Preference Optimization: Enhancing Your Alignment via RM-LLM Game (2024.findings-acl)

Challenge:	Current long chain-of-thought models rely on slow and error-prone natural language traces.
Approach:	They propose a framework that distills complementary reasoning strategies from multiple teachers into a unified student model.
Outcome:	The proposed framework improves accuracy on computation-intensive tasks and reduces inference latency on standard benchmarks.

Copied to clipboard

Pengyu Cheng, Yifan Yang, Jian Li, Yong Dai, Tianhao Hu, Peixin Cao, Nan Du, Xiaolong Li

Robustness in NLP

Challenge:	Existing methods for training large language models require additional annotations to adjust to shifted distributions.
Approach:	They propose an algorithm that allows LLMs and reward models to update alternatively via a min-max game to improve their alignment.
Outcome:	The proposed framework improves existing alignment baselines in terms of LLM helpfulness and harmlessness.

Instance-Guided Prompt Learning for Few-Shot Text Matching (2022.findings-emnlp)

Copied to clipboard

Jia Du, Xuanyu Zhang, Siyi Wang, Kai Wang, Yanquan Zhou, Lei Li, Qing Yang, Dongliang Xu

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights (2025.acl-long)

Challenge:	Few-shot text matching is a more practical technique to determine whether two texts are semantically identical.
Approach:	They propose a pluggable prompt learning method for few-shot text matching . they use the semantics of instances to regulate the effects of the gate on the prompt tokens .
Outcome:	The proposed method outperforms baselines on MRPC and QQP.

Copied to clipboard

Yufang Liu, Yao Du, Tao Ji, Jianing Wang, Yang Liu, Yuanbin Wu, Aimin Zhou, Mengdi Zhang, Xunliang Cai

Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting (2023.findings-emnlp)

Challenge:	Existing models that leverage visual information do not improve math reasoning performance . authors suggest that visual information is important for multimodal reasoning .
Approach:	They propose a dataset to require image reliance for problem-solving and challenge models with similar, yet distinct, images that change the correct answer.
Outcome:	The proposed model performance is unaffected by changes to or removal of images in the dataset.

Copied to clipboard

Haowei Du, Dinghao Zhang, Chen Li, Yang Li, Dongyan Zhao

Paraphrasing

Challenge:	Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, introducing words from irrelevant utterances.
Approach:	They propose a framework to capture the multi-granularity of semantic information and fetch the relevant utterance.
Outcome:	The proposed framework outperforms state-of-the-art models on two benchmark datasets . it can capture the source of important words and fetch the relevant utterance .

Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning (2026.acl-long)

Copied to clipboard

Yifan Li, YuKai Gu, Yingqian Min, Zikang Liu, Yifan Du, Kun Zhou, Min Yang, Xin Zhao, Minghui Qiu

Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum Learning (2025.acl-long)

Challenge:	Existing evaluation frameworks often rely on single-frame assessments, which can lead to outcome-hacking.
Approach:	They propose a process-aware evaluation paradigm that uses a hierarchical rubric to evaluate the validity of the intermediate steps and the final result.
Outcome:	The proposed model achieves POC@1.0 only about 20% and exhibits significant outcome-hacking.

Copied to clipboard

Yexing Du, Youcheng Pan, Ziyang Ma, Bo Yang, Yifan Yang, Keqi Deng, Xie Chen, Yang Xiang, Ming Liu, Bing Qin

Text Generation

Challenge:	Existing studies on English-centric translation tasks have focused on multimodal large language models, but the exploration of many-to-many translation is limited by the scarcity of parallel data.
Approach:	They propose a three-stage curriculum learning strategy that leverages the machine translation capabilities of large language models and adapts them to S2TT tasks.
Outcome:	The proposed strategy achieves state-of-the-art average performance in 1514 language pairs, requiring fewer than 10 hours of speech data per language to achieve competitive results.

A Generative Model for End-to-End Argument Mining with Reconstructed Positional Encoding and Constrained Pointer Mechanism (2022.emnlp-main)

Copied to clipboard

Jianzhu Bao, Yuhang He, Yang Sun, Bin Liang, Jiachen Du, Bing Qin, Min Yang, Ruifeng Xu

Self-contradictory reasoning evaluation and detection (2024.findings-emnlp)

Challenge:	Argument mining (AM) is a challenging task as it requires recognizing complex argumentation structures involving multiple subtasks.
Approach:	They propose a generative framework where expected outputs of AM are framed as a simple target sequence.
Outcome:	The proposed framework achieves state-of-the-art on two AM benchmarks.

Copied to clipboard

Ziyi Liu, Soumya Sanyal, Isabelle Lee, Yongkang Du, Rahul Gupta, Yang Liu, Jieyu Zhao

Type Enhanced BERT for Correcting NER Errors (2023.findings-acl)

Challenge:	Large language models (LLMs) have shown impressive reasoning ability, but many downstream reasoning tasks focus on performance-wise evaluation.
Approach:	They define and assess the Self-Contra rate across three datasets and delve into finer-grained categories of Self-contra reasoning.
Outcome:	The proposed model can detect self-contra reasoning with a 52.2% F1 score, much lower than for humans.

Copied to clipboard

Kuai Li, Chen Chen, Tao Yang, Tianming Du, Peijie Yu, Dong Du, Feng Zhang

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents (2025.acl-long)

Challenge:	Named entity recognition (NER) is the task of identifying spans that belong to particular categories, such as person, location, organization, etc.
Approach:	They propose a method that integrates named entity’s type information into BERT by an adapter layer and integrates it into a gazetteer.
Outcome:	The proposed method outperforms baselines in multiple corpus.

Copied to clipboard

Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji

SeCuRepair: Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework (2026.acl-long)

Challenge:	Existing language model agents excel in planning and reasoning, but lack creativity in unfamiliar environments.
Approach:	They propose a benchmark suite of room escape game environments to challenge agents with creative reasoning, unconventional tool use and iterative problem-solving to uncover implicit goals.
Outcome:	The proposed framework can perform with 40% fewer steps and hints and performs robustly across difficulty levels.

Copied to clipboard

Chengran Yang, Ting Zhang, Jinfeng Jiang, Xin Zhou, Haoye Tian, Mingzhe Du, Jieke Shi, Junkai Chen, Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, David Lo

FaithLM: Towards Faithful Explanations for Large Language Models (2026.eacl-long)

Challenge:	Existing methods for automating vulnerability repair suffer from syntactic overfitting . nvd published 49,230 Common Vulnerabilities and Exposures (CVE) records in 2025 alone .
Approach:	They propose a semantic-aware reward framework that optimizes for code semantic equivalence rather than lexical mimicry.
Outcome:	The proposed framework outperforms state-of-the-art frameworks on repository-level splits . it incorporates expert-aligned reasoning mechanism that grounds patch generation in structured diagnosis.

Copied to clipboard

Yu-Neng Chuang, Guanchu Wang, Chia-Yuan Chang, Ruixiang Tang, Shaochen Zhong, Fan Yang, Andrew Wen, Mengnan Du, Xuanting Cai, Vladimir Braverman, Xia Hu

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) produce natural language explanations, but they lack faithfulness and do not reflect the evidence the model uses to decide.
Approach:	They propose a model-agnostic framework that evaluates and improves the faithfulness of LLM explanations without token masking or task-specific heuristics.
Outcome:	The proposed framework improves faithfulness of large language models without masking or heuristics.

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)

Copied to clipboard

Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale (2026.findings-acl)

Challenge:	Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths.
Approach:	They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO.
Outcome:	The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages.

Copied to clipboard

Canran Wang, Yuwen Yang, Zhen Wang, Ming MA, Ding Yu, Chentai Wang, Keman Huang, Xiaoyong Du

Speech-to-Speech Translation for a Real-world Unwritten Language (2023.findings-acl)

Challenge:	a large-scale empirical dataset involving 57,954 essays from 10,195 students across 120 schools over two years is presented in this paper.
Approach:	They propose a triadic collaboration system that supports K-12 writing learning . they propose linguistic expansion as a pedagogical gatekeeper and bridge .
Outcome:	The proposed system improves writing quality through a strategic labor division . authors find that excessive linguistic expansion yields diminishing marginal utility .

Copied to clipboard

Peng-Jen Chen, Kevin Tran, Yilin Yang, Jingfei Du, Justine Kao, Yu-An Chung, Paden Tomasello, Paul-Ambroise Duquenne, Holger Schwenk, Hongyu Gong, Hirofumi Inaguma, Sravya Popuri, Changhan Wang, Juan Pino, Wei-Ning Hsu, Ann Lee

Structure-Discourse Hierarchical Graph for Conditional Question Answering on Long Documents (2023.findings-acl)

Challenge:	a new study examines speech-to-speech translation (S2ST) that translates speech from one language into another . the research area for unwritten languages remains a research area with little exploration due to the lack of training data.
Approach:	They propose a system that translates speech from one language into another . they use Taiwanese Hokkien as an example of an unwritten language .
Outcome:	The proposed system can be used to train models in languages without standard writing systems.

Copied to clipboard

Haowei Du, Yansong Feng, Chen Li, Yang Li, Yunshi Lan, Dongyan Zhao

Structured Data in NLP

Challenge:	Existing approaches to conditional question answering on long documents ignore document structure and discourse relations between sentences in document sections.
Approach:	They construct a Structure-Discourse Hierarchical Graph and conduct bottom-up information propagation to address this issue.
Outcome:	The proposed approach outperforms the existing methods on the conditional question answering on long documents by 3.0 EM score and 2.4 F1 score on answer measuring, and 2.2 EM and 1.9 F1 scores on jointly answer and condition measuring.

VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding (2022.findings-emnlp)

Copied to clipboard

Dou Hu, Xiaolong Hou, Xiyang Du, Mengyuan Zhou, Lianxin Jiang, Yang Mo, Xiaofeng Shi

When FLUE Meets FLANG: Benchmarks and Large Pretrained Language Model for Financial Domain (2022.emnlp-main)

Challenge:	Pre-trained language models have been widely applied to standard benchmarks due to the limited resources available in a domain.
Approach:	They propose a Transformer-based language model called VarMAE for domain-adaptive language understanding that encodes the context of a token into a smooth latent distribution.
Outcome:	Experiments on science- and finance-domain NLU tasks show that the proposed model can be efficiently adapted to new domains with limited resources.

Copied to clipboard

Raj Shah, Kunal Chawla, Dheeraj Eidnani, Agam Shah, Wendi Du, Sudheer Chava, Natraj Raman, Charese Smiley, Jiaao Chen, Diyi Yang

FOFO: A Benchmark to Evaluate LLMs’ Format-Following Capability (2024.acl-long)

Challenge:	Pre-trained language models have shown impressive performance on a variety of tasks and domains.
Approach:	They propose a domain specific financial LANGuage model which uses financial keywords and phrases for better masking.
Outcome:	The proposed model outperforms existing models on a variety of tasks and domains.

Copied to clipboard

Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, Ran Xu, Wenpeng Yin, Caiming Xiong

Challenge:	Existing benchmarks fail to assess large language models’ format-following proficiency adequately.
Approach:	They propose a benchmark to evaluate large language models' ability to follow complex, domain-specific formats.
Outcome:	The proposed framework evaluates large language models' ability to follow complex, domain-specific formats across open-source and closed-source models.

Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement (2025.acl-long)

Copied to clipboard

Yaxuan Kong, Yiyuan Yang, Yoontae Hwang, Wenjie Du, Stefan Zohren, Zhangyang Wang, Ming Jin, Qingsong Wen

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)

Challenge:	Existing time series models focus on a narrow spectrum of tasks, such as forecasting or anomaly detection.
Approach:	They propose a framework that enables natural language queries across multiple time series tasks such as numerical analytical tasks and open-ended question answering with reasoning.
Outcome:	The proposed framework enables natural language queries across multiple time series tasks and allows for more advanced and intuitive interactions with temporal data.

Copied to clipboard

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Challenge:	Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood.
Approach:	They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction .
Outcome:	The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones .

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus (2026.findings-acl)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Yexing Du, Kaiyuan Liu, Bihe Zhang, Youcheng Pan, Bo Yang, Liangyu Huo, Xiyuan Zhang, Jian Xie, Daojing He, Yang Xiang, Ming Liu, Bing Qin

ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation (2025.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced Chinese Classical Studies (CCS) but the audio dimension of CCS remains underexplored due to a lack of high-quality, domain-specific audio corpora.
Approach:	They propose a 119-hour audio corpus comprising 22,000 audio samples to bridge this gap . it encompasses a diverse range of literary genres across six tasks .
Outcome:	The proposed corpus encompasses a diverse range of literary genres across six tasks: Automatic Speech Recognition (ASR), Speech-to-Text Translation (S2TT), Speech Emotion Captioning (SEC), Spoken Question Answering ( SQA), Speech Understanding (SU), and Speech Reasoning (SR).

Copied to clipboard

Kaiyuan Liu, Youcheng Pan, Yang Xiang, Daojing He, Jing Li, Yexing Du, Tianrun Gao

Programming Languages in NLP

Challenge:	Existing benchmarks lack the ability to automatically evaluate from users’ perspective and lack the explainability of the results of LLM agents’ code generation capabilities.
Approach:	They propose a new benchmark for LLM agents' automated evaluation by simulating user interaction.
Outcome:	The proposed benchmark can evaluate the generated projects by user interaction simulation and by code similarity through existing objective indicators.

One for All: Update Parameterized Knowledge Across Multiple Models with Once Edit (2025.acl-long)

Copied to clipboard

Weitao Ma, Xiyuan Du, Xiaocheng Feng, Lei Huang, Yichong Huang, Huiyi Zhang, Xiaoliang Yang, Baohang Li, Xiachong Feng, Ting Liu, Bing Qin

Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation (2025.acl-long)

Challenge:	Existing methods for modifying large language models focus on individual models, resulting in errors and hallucinations.
Approach:	They propose an ensemble-based approach that employs a plug-in model as the editing module and a dynamic weight mechanism to enhance its effectiveness.
Outcome:	The proposed approach outperforms existing methods while achieving superior editing efficiency.

Copied to clipboard

Junyi Chen, Shihao Bai, Zaijun Wang, Siyu Wu, Chuheng Du, Hailong Yang, Ruihao Gong, Shengzhong Liu, Fan Wu, Guihai Chen

MultiAgentBench : Evaluating the Collaboration and Competition of LLM agents (2025.acl-long)

Challenge:	Existing methods for structured generation of outputs are inefficient under large inference batches.
Approach:	They propose a new LLM-based method that parses LR(1) grammars into a pushdown automaton and exploits deterministic pushdown automation to optimize the constrained LLM decoding efficiency.
Outcome:	The proposed method improves time per output token (TPOT) by 40% and throughput by 36% .

Copied to clipboard

Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Robert Tang, Heng Ji, Jiaxuan You

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition.
Approach:	They propose a benchmark to evaluate LLM-based multi-agent systems across diverse, interactive scenarios.
Outcome:	The proposed framework measures task completion and quality of collaboration and competition using novel, milestone-based key performance indicators.

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

Retrieval-Augmented Language Models are Mimetic Theorem Provers (2025.findings-emnlp)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Wenjie Yang, Ruiyuan Huang, Jiaxing Guo, Zicheng Lyu, Tongshan Xu, Shengzhong Zhang, Lun Du, Da Zheng, Zengfeng Huang

Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge (C18-1)

Challenge:	Large language models often fail to provide rigorous proof-based reasoning for research-level mathematics.
Approach:	They propose a simple yet effective RAG framework that augments retrieved proofs with queries and document contexts to improve retrieval performance.
Outcome:	The proposed framework improves retrieval performance by 34.19% . dual RAG can be used to prove research-level theorems in theoretical machine learning .

Copied to clipboard

Yang Deng, Ying Shen, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei

Question Answering

Challenge:	Existing approaches to answer selection are limited in domains with limited labeled data.
Approach:	They propose a Knowledge-aware Attentive Network framework for cross-domain answer selection that uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domain.
Outcome:	The proposed model outperforms strong competitors by a noticeable margin in cross-domain answer selection.

DYNTEXT: Semantic-Aware Dynamic Text Sanitization for Privacy-Preserving LLM Inference (2025.findings-acl)

Copied to clipboard

Juhua Zhang, Zhiliang Tian, Minghang Zhu, Yiping Song, Taishu Sheng, Siyi Yang, Qiunan Du, Xinwang Liu, Minlie Huang, Dongsheng Li

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)

Challenge:	Existing methods to protect privacy of sensitive data are differential privacy (DP) and DP is used to protect users from privacy leakage.
Approach:	They propose an LDP-based Dynamic Text sanitization for privacy-preserving LLM inference that dynamically constructs semantic-aware adjacency lists of sensitive tokens to sample non-sensitive tokens for perturbation.
Outcome:	The proposed model excels on three datasets.

Copied to clipboard

Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

Explainable Text Classification with LLMs: Enhancing Performance through Dialectical Prompting and Explanation-Guided Training (2025.findings-emnlp)

Challenge:	Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs.
Approach:	They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn.
Outcome:	The proposed framework improves strategy selection preferences at each dialogue turn.

Copied to clipboard

Huaming Du, Lei Yuan, Cancan Feng, Guisong Liu, Gang Kou, Carl Yang

Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study (2025.coling-main)

Challenge:	Existing explanation methods that generate keywords may be less effective due to missing critical contextual information.
Approach:	They propose a new method to generate explanations for possible labels using LLMs and a dialectical prompt.
Outcome:	The proposed method significantly improves accuracy and explanation quality over state-of-the-art methods on multiple datasets from diverse domains.

Copied to clipboard

Bowen Li, Wenhan Wu, Ziwei Tang, Lin Shi, John Yang, Jinyang Li, Shunyu Yao, Chen Qian, Binyuan Hui, Qicheng Zhang, Zhiyin Yu, He Du, Ping Yang, Dahua Lin, Chao Peng, Kai Chen

GrandGuard: Taxonomy, Benchmark, and Safeguards for Elderly-Chatbot Interaction Safety (2026.findings-acl)

Challenge:	Existing benchmarks focused on simplified or isolated aspects of coding, ignoring the full spectrum of programming challenges.
Approach:	They propose a case study that examines the performance of large language models across the entire software development lifecycle with four programming languages, multiple domains, and carefully designed and verified metrics for each task.
Outcome:	The proposed model performs across the entire software development lifecycle, including design, environment setup, implementation, acceptance testing, and unit testing.

Copied to clipboard

Changxuan Fan, Xi Yang, Yueyuan Zheng, Bin Zhou, Yuanping Wang, Wenbin Hu, Huihao Jing, Ki Sen Hung, Dazhao Du, Haoran Li, Janet Hui-wen Hsiao, Yangqiu Song

Powering Verifiable Learning via Automated Evolutionary Data Synthesis (2026.acl-long)

Challenge:	a survey of older adults shows that many LLMs mishandle elderly-specific contextual risks.
Approach:	They propose a framework to assess elderly-specific contextual risks in LLM interactions . they use a taxonomy to identify 50 fine-grained risk types across mental well-being, financial, medical, toxicity, and privacy domains .
Outcome:	a new framework assesses elderly-specific contextual risks in LLM interactions . it achieves 96.2% and 90.9% unsafe-prompt detection accuracy, respectively .

Copied to clipboard

He Du, Bowen Li, Aijun Yang, Siyang He, Qipeng Guo, Kai Chen, Dacheng Tao

CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling (2025.findings-emnlp)

Challenge:	Existing approaches to building generalizable verifiable data are task-specific and lack a principled, universal evaluator of verifikatability.
Approach:	They propose a task-agnostic, strategy-guided, executably-checkable data synthesis framework that synthesizes problems, diverse candidate solutions and verification artifacts from a single source.
Outcome:	The proposed framework synthesizes problems, candidates, and verification artifacts from human-annotated and strategy-induced checks and iteratively discovers strategies.

Copied to clipboard

Xinze Wang, Chen Chen, Yinfei Yang, Hong-You Chen, Bowen Zhang, Aditya Pal, Xiangxin Zhu, Xianzhi Du

Improving Event Duration Prediction via Time-aware Pre-training (2020.findings-emnlp)

Challenge:	Mixture-of-Experts (MoE) models are crucial for scaling model capacity while controlling inference costs.
Approach:	They propose an alternative training strategy that converts a dense CLIP model into a sparse MoE architecture.
Outcome:	The proposed training strategy outperforms dense models on COCO and Flickr30k benchmarks.

Copied to clipboard

Zonglin Yang, Xinya Du, Alexander Rush, Claire Cardie

E-Verify: A Paradigm Shift to Scalable Embedding-based Factuality Verification (2025.findings-emnlp)

Challenge:	Understanding duration of event expressed in text is crucial task in NLP . current methods focus on developing features and cannot utilize external textual knowledge.
Approach:	They propose two models that incorporate external knowledge by reading temporal-related news sentences.
Outcome:	The proposed models outperform baseline models and capture duration information more accurately.

Copied to clipboard

Zeyang Liu, Jingfeng Xue, Xiuqi Yang, Wenbiao Du, Jiarun Fu, Junbao Chen, Wenjie Guo, Yong Wang

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use (2025.findings-emnlp)

Challenge:	Existing factuality verification methods follow a Decompose-Then-Verify paradigm, which improves granularity but suffers from poor scalability and efficiency.
Approach:	They propose a Decompose-Embed-Interact paradigm that shifts factuality verification from costly text-level reasoning to efficient alignment in embedding space.
Outcome:	The proposed paradigm shifts factuality verification from costly text-level reasoning to efficient alignment in embedding space .

Copied to clipboard

Junjie Ye, Yilong Wu, Sixian Li, Yuming Yang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Peng Wang, Zhongchao Shi, Jianping Fan, Zhengyin Du

Robustness in NLP

Challenge:	a new approach to training large language models (LLMs) overlooks task-specific characteristics in tool use, leading to performance bottlenecks.
Approach:	They propose a task-feature-based framework that mitigates the effects of suboptimal training data . they use a dataset to train large-scale LLMs and a reward mechanism tailored to error categories .
Outcome:	The proposed framework matches or surpasses open- and closed-source LLMs in tool-use performance using only 1,217 training data points.

Cooperative Denoising for Distantly Supervised Relation Extraction (C18-1)

Copied to clipboard

Kai Lei, Daoyuan Chen, Yaliang Li, Nan Du, Min Yang, Wei Fan, Ying Shen

Information Extraction & Text Mining

Challenge:	Existing methods for distantly supervised relation extraction suffer from noisy labeling problem, which can severely degrade its performance.
Approach:	They propose a framework for distantly supervised relation extraction that leverages text corpus and knowledge graph and a cooperative module involving their mutual learning.
Outcome:	The proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods.

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidance (2025.emnlp-main)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Yilun Liu, Minggui He, Feiyu Yao, Yuhe Ji, Shimin Tao, Jingzhou Du, Justin Li, Jian Gao, Zhang Li, Hao Yang, Boxing Chen, Osamu Yoshie

Low-Resource NLP

Challenge:	Existing solutions for text-to-image synthesis are sensitive on textual prompts, posing a challenge for novice users.
Approach:	They propose a dialogue-based TIS prompt generation model that emphasizes user experience for novice users.
Outcome:	The proposed model emphasizes user experience for novice users . it improves user-centricity score while maintaining a competitive quality of synthesized images.

Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning (2024.findings-acl)

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Zhouhao Sun, Shi Jun, Ting Liu, Bing Qin

A Knowledge Regularized Hierarchical Approach for Emotion Cause Analysis (D19-1)

Challenge:	Existing studies have suggested that the composition of the pretraining corpus exerts a significant impact upon the performance of LLMs.
Approach:	They analyze the impact of 48 datasets from 5 major categories of pretraining data of Large Language Models and measure their impacts on LLMs using benchmarks about nine major categories.
Outcome:	The proposed analysis provides insights into the organization of data to support more efficient pretraining of Large Language Models.

Copied to clipboard

Chuang Fan, Hongyu Yan, Jiachen Du, Lin Gui, Lidong Bing, Min Yang, Ruifeng Xu, Ruibin Mao

Sentiment Analysis

Challenge:	Emotion cause analysis aims to identify the reasons behind emotions . previous models focus on learning architecture with local textual information .
Approach:	They propose a method to extract emotion cause with hierarchical neural model and knowledge-based regularizations by sentiment lexicon and common knowledge.
Outcome:	The proposed method outperforms baselines on two public datasets in different languages and outperformed competitive baselines by 2.08%.

Soft-Prompting with Graph-of-Thought for Multi-modal Representation Learning (2024.lrec-main)

Copied to clipboard

Jun Cheng Yang, Zuchao Li, Shuai Xie, Wei Yu, Shijun Li, Bo Du

Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns (2025.acl-long)

Challenge:	Existing approaches to learn multi-modal tasks are based on chain-of-thought . however, human thought processes are non-linear and employ dynamic adjustment and updating mechanisms.
Approach:	They propose a chain-of-thought technique that adjusts the length of the chain to improve the performance of generated prompts.
Outcome:	The proposed model improves multi-modal representation learning in visual, visual, and audio-visual tasks and also has good domain generalization performance due to better reasoning.

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin

Explicit and Implicit Data Augmentation for Social Event Detection (2025.acl-long)

Challenge:	Currently, LLMs learn in a data-driven schema while the instructions about complex tasks are both scarce and hard to collect or construct.
Approach:	They employ a gradient-based method to dissect the process that the Supervised Fine-tuning Process (SFT) adapts LLMs to downstream tasks via the perspective of attention patterns.
Outcome:	The proposed method dissects the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns.

Copied to clipboard

Congbo Ma, Yuxia Wang, Jia Wu, Jian Yang, Jing Du, Zitai Qiu, Qing Li, Hu Wang, Preslav Nakov

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization (2026.findings-acl)

Challenge:	Social event detection relies on labeled data, but annotation is costly and labor-intensive.
Approach:	They propose a plug-and-play dual augmentation framework that combines explicit text-based and implicit feature-space augmentation to enhance data diversity and model robustness.
Outcome:	The proposed framework outperforms the best baseline model by 17.67% on the Twitter2012 dataset and 15.57% on the twitter2018 dataset in terms of the average F1 score.

Copied to clipboard

Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang

End-to-end Case-Based Reasoning for Commonsense Knowledge Base Completion (2023.eacl-main)

Challenge:	Large Language Models (LLMs) can solve complex tasks through iterative information retrieval.
Approach:	They propose a turn-level stage-aware policy optimization approach to solve this problem . they introduce a first-occurrence latent reward mechanism to allocate partial rewards .
Outcome:	Experiments show that TSPO outperforms state-of-the-art models on Qwen2.5-3B and 7B models.

Copied to clipboard

Zonglin Yang, Xinya Du, Erik Cambria, Claire Cardie

GPS: Genetic Prompt Search for Efficient Few-Shot Learning (2022.emnlp-main)

Challenge:	Pretrained language models have been shown to store knowledge in their parameters and have achieved reasonable performance in knowledge-intensive tasks.
Approach:	They propose to provide retrieved passages that contain relevant knowledge as additional input to the commonsense knowledge base completion (CKBC) task.
Outcome:	The proposed framework generates more valid, informative, and novel knowledge than the state-of-the-art COMET model for commonsense knowledge base completion (CKBC) tasks.

Copied to clipboard

Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Wang Yanggang, Haiyu Li, Zhilin Yang

MiMoTable: A Multi-scale Spreadsheet Benchmark with Meta Operations for Table Reasoning (2025.coling-main)

Challenge:	Pretrained language models are often finetuned for downstream tasks, which has been shown to improve performance over non-pretrained models.
Approach:	They propose a genetic algorithm to automatically search for the best prompt for few-shot learning with pretrained language models by gradient-free algorithm.
Outcome:	Experiments on diverse datasets show that the proposed method outperforms manual prompts by 2.6 points.

Copied to clipboard

Zheng Li, Yang Du, Mao Zheng, Mingyang Song

NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs (2026.acl-long)

Challenge:	Existing benchmarks for table reasoning are incomplete due to the complexity of the tables and user questions in real-world applications.
Approach:	They propose a Multi-scale spreadsheet benchmark with Meta operations for Table reasoning that incorporates two key features and a new criterion with six categories of meta operations for measuring the difficulty of each question.
Outcome:	The proposed model outperforms Claude-3.5-Sonnet with 77.4% accuracy on the existing benchmarks.

Copied to clipboard

Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang, MuRun Yang, DingYang Lin, Kaiyan Chang, Tong Zheng, Bei Li, Peinan Feng, Quan Du, Tong Xiao, JingBo Zhu

Multilinguality

Challenge:	Large language models have significantly advanced Multilingual Machine Translation (MMT) yet scaling to many languages while maintaining robust performance across directions remains challenging.
Approach:	They propose a strategy to reduce the number of translations in one direction . they propose auxiliary parallel sentences to promote cross-lingual transfer .
Outcome:	The proposed model performs on par with or better than substantially larger baselines.

Understanding Gender Bias in Knowledge Base Embeddings (2022.acl-long)

Copied to clipboard

Yupei Du, Qi Zheng, Yuanbin Wu, Man Lan, Yan Yang, Meirong Ma

AXIS: Efficient Human-Agent-Computer Interaction with API-First LLM-Based Agents (2025.acl-long)

Challenge:	Knowledge base (KB) embeddings have been shown to contain gender biases . authors develop two new bias measures to quantify them and trace their origins in KB .
Approach:	They propose two ways to quantify gender biases in knowledge base (KB) embeddings . they use the influence function to inspect the contribution of each triple in KB to the overall group bias .
Outcome:	The proposed measures are compared with real-world census data to examine gender biases.

Copied to clipboard

Junting Lu, Zhiyang Zhang, Fangkai Yang, Jue Zhang, Lu Wang, Chao Du, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

Quantification of Large Language Model Distillation (2025.acl-long)

Challenge:	Multimodal large language models (MLLMs) have enabled LLM-based agents to directly interact with application user interfaces (UIs), enhancing agents’ performance in complex tasks.
Approach:	They propose a novel agent framework that prioritizes actions through application programming interfaces over UI actions and facilitates the creation and expansion of APIs through automated exploration of applications.
Outcome:	The proposed framework reduces task completion time by 65%-70% and cognitive workload by 38%-53% while maintaining accuracy of 97%-98% compared to humans.

Copied to clipboard

Sunbowen Lee, Junting Zhou, Chang Ao, Kaige Li, Xeron Du, Sirui He, Haihong Wu, Tianci Liu, Jiaheng Liu, Hamid Alinejad-Rokny, Min Yang, Yitao Liang, Zhoufutu Wen, Shiwen Ni

Large Language Models Are Still Misled by Simple Bias Ensembles (2026.findings-acl)

Challenge:	Existing studies have revealed the robustness degra-dation caused by data distillation.
Approach:	They propose a framework to evaluate and quantify model distillation . they aim to identify identity cognition contradictions and analyse multi-granularity response similarities across models to measure the extent of homogenization.
Outcome:	The proposed framework addresses two key aspects: (1) Identifying identity cognition contradictions to assess discrepancies in how models perceive and represent identity-related information; (2) Analyzing multi-granularity response similarities across models to measure the extent of homogenization.

Copied to clipboard

Zhouhao Sun, Zhiyuan Kan, Xiao Ding, Li Du, Bibo Cai, Yang Zhao, Bing Qin, Ting Liu

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Challenge:	Existing benchmarks for large language models are constrained to datasets where each sample is manually injected with only one type of bias.
Approach:	They propose a multi-bias benchmark where each sample contains multiple types of biases.
Outcome:	The proposed benchmark shows that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating compounded biases.

Copied to clipboard

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao

P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and Tasks (2022.acl-short)

Challenge:	Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach:	They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome:	The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.

Copied to clipboard

Xiao Liu, Kaixuan Ji, Yicheng Fu, Weng Tam, Zhengxiao Du, Zhilin Yang, Jie Tang

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Challenge:	Existing methods of prompt tuning cannot handle hard sequence labeling tasks.
Approach:	They propose to optimize prompt tuning to tune continuous prompts with a frozen language model.
Outcome:	The proposed method matches finetuning with prompt tuning while having only 0.1%-3% tuned parameters.

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

SRAP-Agent: Simulating and Optimizing Scarce Resource Allocation Policy with LLM-based Agent (2024.findings-emnlp)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Jiarui Ji, Yang Li, Hongtao Liu, Zhicheng Du, Zhewei Wei, Qi Qi, Weiran Shen, Yankai Lin

UNIVID: Unified Vision-Language Model for Video Moderation (2026.acl-industry)

Challenge:	Existing research on the allocation of public scarce resources has limitations due to data scarcity and data scariness.
Approach:	They propose a framework that integrates Large Language Models into economic simulations . they conduct extensive policy simulation experiments to verify the framework's effectiveness .
Outcome:	The proposed framework bridges the gap between theoretical models and real-world dynamics by integrating large language models into economic simulations.

Copied to clipboard

Kejuan Yang, Yizhuo Zhang, Mingyuan Du, Yue Zhang, Dixin Zheng, Kaili Zhao, Yang Xiao, Hanzhong Liang, Kenan Xiao

VC4VG: Optimizing Video Captions for Text-to-Video Generation (2025.emnlp-main)

Challenge:	Existing video moderation systems rely on fragmented black-box classification models that are difficult to maintain and lack transparency.
Approach:	They propose a Unified Vision-Language model for Video Moderation that generates policy-aware captions that serve as an interpretable intermediate representation.
Outcome:	The proposed model reduces violation leakage and overkill rate by 42.7% while reducing maintenance costs.

Copied to clipboard

Yang Du, Zhuoran Lin, Kaiqiang Song, Biao Wang, Zhicheng Zheng, Tiezheng Ge, Bo Zheng, Qin Jin

The Fall of ROME: Understanding the Collapse of LLMs in Model Editing (2024.findings-emnlp)

Challenge:	Recent advances in text-to-video generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos.
Approach:	They propose a caption optimization framework tailored to the needs of T2V models.
Outcome:	The proposed framework improves video caption quality and video generation performance.

Copied to clipboard

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Du Su, Dawei Yin, Huawei Shen

BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026.acl-long)

Challenge:	Recent studies have found that model editing methods can cause large language models to collapse with just a single edit.
Approach:	They propose a method that uses prefixed keys and adds prefixes during testing to prevent model collapse.
Outcome:	The proposed method prevents model collapse while maintaining effectiveness, the authors show . Rank-One Model Editing (ROME) has been found to cause model collapse with just a single edit .

Copied to clipboard

Hexiang Tan, Wanli Yang, Junwei Zhang, Xin Chen, Rui Tang, Du Su, Jingang Wang, Yuanzhuo Wang, Fei Sun, Xueqi Cheng

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering (2026.findings-eacl)

Challenge:	Post-trained LLMs typically compromise reliability with severe overconfidence, resulting in inaccurate responses.
Approach:	They propose a solution that feeds PoLLMs into the base LLM to get confidence.
Outcome:	The proposed solution reduces expected calibration error (ECE) by 42.90% compared to the best unsupervised baselines.

Copied to clipboard

Haiyan Zhao, Xuansheng Wu, Fan Yang, Bo Shen, Ninghao Liu, Mengnan Du

Multi-grained Named Entity Recognition (P19-1)

Challenge:	Existing methods for steering concept vectors suffer from noisy features in diverse datasets that undermine steering robustness.
Approach:	They propose a Sparse Autoencoder-Denoised Concept Vector (SDCV) which selectively keeps the most discriminative SAE latents while reconstructing hidden representations.
Outcome:	The proposed method improves steering success rates by 4-16% across six challenging concepts while maintaining topic relevance.

Copied to clipboard

Congying Xia, Chenwei Zhang, Tao Yang, Yaliang Li, Nan Du, Xian Wu, Wei Fan, Fenglong Ma, Philip Yu

Information Extraction & Text Mining

Challenge:	Existing approaches treat Named Entity Recognition (NER) as a sequence labeling task.
Approach:	They propose a framework for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested.
Outcome:	The proposed framework outperforms current state-of-the-art frameworks by 4.4% in terms of the F1 score among nested/non-overlapping NER tasks.

ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization (2022.findings-emnlp)

Copied to clipboard

Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Wang Yanggang, Haiyu Li, Zhilin Yang

LDEDE: LRP-Driven Efficient Detection and Editing Framework for LLM Privacy Neurons (2026.findings-acl)

Challenge:	a recent study shows that task scaling can be an efficient alternative to model scaling.
Approach:	They propose a multitask pretraining approach ZeroPrompt for zero-shot generalization . they focus on task scaling and zero-shooting to improve model performance .
Outcome:	The proposed approach improves zero-shot generalization efficiency by 30 times with task scaling.

Copied to clipboard

Zhao Zhengyuan, Cao Lifeng, null Sunhaodong, Shi Haotian, Du Xuehui, Liu Aodi, Niu Lanjie, Yang Xiaocheng