Papers by Chen Qu

UQ-Merge: Uncertainty Guided Multimodal Large Language Model Merging (2025.findings-acl)

Challenge:	Bit-flip errors (BFEs) are hardware faults where individual bits in memory or processing units are unintentionally flipped.
Approach:	They propose a novel defense strategy to mitigate bit-flip errors (BFEs) they propose bfe protection and a self-correction mechanism to minimize performance degradation .
Outcome:	The proposed defense strategy minimizes performance degradation while significantly improving robustness against BFEs.

Copied to clipboard

Huaizhi Qu, Xinyu Zhao, Jie Peng, Kwonjoon Lee, Behzad Dariush, Tianlong Chen

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Existing models merging methods often lead to suboptimal performance due to harmful models . et al., 2018; 59: 59-64.
Approach:	They propose an uncertainty-guided MLLM merging algorithm that integrates models into a single MLML.
Outcome:	The proposed algorithm improves on held-in and held-out vision-language benchmarks.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models (2024.findings-acl)

Copied to clipboard

Zhenyi Lu, Jie Tian, Wei Wei, Xiaoye Qu, Yu Cheng, Wenfeng Xie, Dangyang Chen

Text Classification

Challenge:	a new text classification framework for large language models addresses the problem of boundary ambiguity and inherent biases in LLMs.
Approach:	They propose a two-stage classification framework for large language models to mitigate bottlenecks . their approach uses pairwise comparisons to efficiently narrow down options .
Outcome:	The proposed framework reduces the number of options and improves on four datasets.

How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing? (2022.findings-acl)

Copied to clipboard

Hailong Jin, Tiansi Dong, Lei Hou, Juanzi Li, Hui Chen, Zelin Dai, Qu Yincen

Multilinguality

Challenge:	Extensive experiments on multi-lingual datasets show that our method significantly outperforms multiple baselines and can robustly handle negative transfer.
Approach:	They propose to transfer semantic knowledge from rich-resourced languages to low-resource languages by using multilingual transfer learning.
Outcome:	The proposed model outperforms baselines and can handle negative transfer.

Label-Aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition (N18-1)

Copied to clipboard

Zhenghui Wang, Yanru Qu, Liheng Chen, Jian Shen, Weinan Zhang, Shaodian Zhang, Yimei Gao, Gen Gu, Ken Chen, Yong Yu

Automatic rule generation for time expression normalization (2021.findings-emnlp)

Challenge:	NER is a fundamental problem for medical text mining because of the difference of specialties and cost of human annotation.
Approach:	They propose a label-aware double transfer learning framework for medical NER from electronic medical records.
Outcome:	The proposed framework improves accuracy over strong baselines on 12 cross-specialty NER tasks.

Copied to clipboard

Wentao Ding, Jianhao Chen, Jinmao Li, Yuzhong Qu

Challenge:	Existing SOTA methods for normalization rely on expert-designed rules or grammars . current methods are domain sensitive and not sufficient on emerging corpora .
Approach:	They propose a method that generates normalization rules from annotated data without expert intervention.
Outcome:	The proposed method surpasses existing rule-based methods on the Tweets benchmark and on the TempEval-3 benchmark.

Evaluating Memory Capability in Continuous Lifelog Scenario (2026.findings-acl)

Copied to clipboard

Jianjie Zheng, Zhichen Liu, Zhanyu Shen, Jingxiang Qu, Guanhua Chen, Yile Wang, Yang Xu, Yang Liu, Sijie Cheng

Challenge:	Existing benchmarks focus on online one-on-one chatting or human-AI interactions, neglecting real-world scenarios.
Approach:	They propose a framework to curate a lifelog benchmark that combines two subsets of audio data to address temporal leakage in offline settings.
Outcome:	The proposed framework outperforms existing benchmarks on live chats and AI interactions.

TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System (2025.findings-naacl)

Copied to clipboard

Zeyu Zhang, Jianxun Lian, Chen Ma, Yaning Qu, Ye Luo, Lei Wang, Rui Li, Xu Chen, Yankai Lin, Le Wu, Xing Xie, Ji-Rong Wen

Robustness in NLP

Challenge:	Trending topics bring in a new channel for poisoning attacks, resulting in negative impacts on society.
Approach:	They propose an LLM-based multi-agent system to simulate trending topics in social media . they propose a time-aware interaction mechanism, centralized message dissemination, and an interactive system .
Outcome:	The proposed system simulates trending topics under poisoning attacks on social media platforms.

Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering (2025.emnlp-main)

Copied to clipboard

Zixin Chen, Sicheng Song, KaShun Shum, Yanna Lin, Rui Sheng, Weiqi Wang, Huamin Qu

Multi-level Association Refinement Network for Dialogue Aspect-based Sentiment Quadruple Analysis (2025.acl-long)

Challenge:	Misleading visualizations can distort perception and lead to incorrect conclusions.
Approach:	They propose a large-scale multimodal dataset to evaluate MLLMs on misleading chart reasoning.
Outcome:	The proposed framework evaluates MLLMs on misleading chart reasoning on a large-scale multimodal dataset spanning 21 misleader types and 10 chart types . it contains 3,026 curated examples spanning standard chart code, CSV data, multiple-choice questions, and labeled explanations, validated through iterative MLML checks and exhausted expert human review.

Copied to clipboard

Zeliang Tong, Wei Wei, Xiaoye Qu, Rikui Huang, Zhixin Chen, Xingyu Yan

Sentiment Analysis

Challenge:	Existing methods for identifying quadruples rely on predefined dialogue structure and word semantics to achieve accurate and comprehensive sentiment associations between utterances and words.
Approach:	They propose a multi-level association refinement network to achieve more accurate sentiment associations between utterances and words.
Outcome:	The proposed framework achieves state-of-the-art performance under low-resource conditions.

Semantic Framework based Query Generation for Temporal Question Answering over Knowledge Graphs (2022.emnlp-main)

Copied to clipboard

Wentao Ding, Hao Chen, Huayu Li, Yuzhong Qu

DuReader-Retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine (2022.emnlp-main)

Challenge:	Existing methods for temporal question answering ignore intrinsic connections between events that can make them temporally related.
Approach:	They propose a temporal question answering method that generates query graphs by exploring relevant facts of mentioned entities.
Outcome:	The proposed method outperforms existing methods on two benchmarks over different knowledge graphs.

Copied to clipboard

Yifu Qiu, Hongyu Li, Yingqi Qu, Ying Chen, QiaoQiao She, Jing Liu, Hua Wu, Haifeng Wang

Information Retrieval

Challenge:	Existing datasets for non-English passage retrieval are lacking in quality and accuracy.
Approach:	They present a large-scale Chinese dataset for passage retrieval . they reduce false negatives by manually annotating results pooled from multiple retrievers .
Outcome:	The proposed dataset reduces false negatives in development and testing sets and removes similar training queries.

Commonsense Knowledge Salience Evaluation with a Benchmark Dataset in E-commerce (2022.findings-emnlp)

Copied to clipboard

Yincen Qu, Ningyu Zhang, Hui Chen, Zelin Dai, Chengming Wang, Xiaoyu Wang, Qiang Chen, Huajun Chen

Commonsense Reasoning

Challenge:	Existing models rank statements solely by confidence scores, and there is no information about which ones are salient from a human perspective.
Approach:	They propose a task where a model is required to learn whether a triple is salient . they propose supervised salience evaluation using a new Benchmark dataset .
Outcome:	The proposed task is based on a new Benchmark dataset of salience evaluation in e-commerce . it shows that saliency evaluation is hard, where models perform poorly on evaluation set .

BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation (2022.acl-long)

Copied to clipboard

Yanling Xiao, Lemao Liu, Guoping Huang, Qu Cui, Shujian Huang, Shuming Shi, Jiajun Chen

Multilinguality

Challenge:	Existing IMT systems relying on lexical constrained decoding (LCD) are limited in translation efficiency and quality due to LCD.
Approach:	They propose a novel interactive neural machine translation system that uses lexical constraints to decode missing words in a manually revised translation.
Outcome:	The proposed system performs significantly better and faster than state-of-the-art IMT on three translation tasks.

Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare Dictator (2026.findings-acl)

Copied to clipboard

Zhengliang Shi, Ruotian Ma, Jen-tse Huang, Xinbei Ma, Xingyu Chen, Mengru Wang, Qu Yang, Yue Wang, Fanghua Ye, Ziyang Chen, Shanyi Wang, Cixing LI, Wenxuan Wang, Zhaopeng Tu, Xiaolong Li, Zhaochun Ren, Liefeng Bo

Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)

Challenge:	Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare.
Approach:	They evaluate 20 state-of-the-art Large language models (LLMs) and 20 LLM dictators to create a social welfare function benchmark.
Outcome:	The proposed model creates dilemma between maximizing collective efficiency and ensuring distributive fairness.

Copied to clipboard

Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li

Green & Sustainable NLP

Challenge:	Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization .
Approach:	They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume.
Outcome:	Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency.

Too Good to be Bad: On the Failure of LLMs to Role-Play Villains (2026.findings-acl)

Copied to clipboard

Zihao Yi, Qingxuan Jiang, Ruotian Ma, Xingyu Chen, Qu Yang, Mengru Wang, Fanghua Ye, Ying Shen, Zhaopeng Tu, Xiaolong Li, Liefeng Bo

Challenge:	Large Language Models (LLMs) are increasingly tasked with creative generation, but their ability to portray non-prosocial, antagonistic personas remains largely unexamined.
Approach:	They propose a moral alignment benchmark to test the safety of large language models . they find that models struggle with traits directly antithetical to safety principles .
Outcome:	The proposed model fails to accurately portray morally ambiguous or villainous characters . the model fails most with traits directly antithetical to safety principles .

Dream to Chat: Model-based Reinforcement Learning on Dialogues with User Belief Modeling (2025.findings-emnlp)

Copied to clipboard

Yue Zhao, Xiaoyu Wang, Dan Wang, Zhonglin Jiang, Qingqing Gu, Teng Chen, Ningyuan Xi, Jinxian Qu, Yong Chen, Luo Ji

Dialogue Systems & Conversational Agents

Challenge:	a framework for constructing dialogue world models for natural language tasks is currently lacking.
Approach:	They propose a framework that can be used to train a dialogue world model.
Outcome:	The proposed framework can predict future utterances and user beliefs . it can achieve state-of-the-art performance on emotion classification and sentiment identification .

AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension (2022.acl-long)

Copied to clipboard

Xiao Li, Gong Cheng, Ziheng Chen, Yawei Sun, Yuzhong Qu

Reasoning

Challenge:	Existing methods and limitations for machine reading comprehension are insufficient for logical reasoning over text.
Approach:	They propose a neural-symbolic approach which passes messages over a graph representing logical relations between text units to predict an answer.
Outcome:	The proposed approach outperforms existing methods on ReClor and LogiQA.

Collaborative Policy Learning for Open Knowledge Graph Reasoning (D19-1)

Copied to clipboard

Cong Fu, Tong Chen, Meng Qu, Woojeong Jin, Xiang Ren

GeoAgent: To Empower LLMs using Geospatial Tools for Address Standardization (2024.findings-acl)

Challenge:	Existing models of knowledge graph reasoning suffer from limited performance when working on sparse and incomplete graphs due to the lack of evidential paths that can reach target entities.
Approach:	They propose a framework to train two collaborative agents to reason for missing facts over a graph augmented by a text corpus.
Outcome:	Experiments on two public datasets show the proposed approach is effective on a knowledge graph reasoning task.

Copied to clipboard

Chenghua Huang, Shisong Chen, Zhixu Li, Jianfeng Qu, Yanghua Xiao, Jiaxin Liu, Zhigang Chen

Mirror: A Universal Framework for Various Information Extraction Tasks (2023.emnlp-main)

Challenge:	Existing approaches to address address standardization are lacking in the current field.
Approach:	They propose a framework that incorporates spatial knowledge into address texts and achieves efficient address standardization.
Outcome:	The proposed framework incorporates spatial knowledge into address texts and achieves efficient address standardization.

Copied to clipboard

Tong Zhu, Junfei Ren, Zijian Yu, Mengsong Wu, Guoliang Zhang, Xiaoye Qu, Wenliang Chen, Zhefeng Wang, Baoxing Huai, Min Zhang

Information Extraction & Text Mining

Challenge:	Recent studies often formulate IE tasks as a triplet extraction problem, but this paradigm does not support multi-span and n-ary extraction, leading to weak versatility.
Approach:	They propose a multi-span cyclic graph extraction problem and a non-autoregressive graph decoding algorithm to extract all spans in a single step.
Outcome:	The proposed model outperforms or reaches competitive performance with SOTA systems under few-shot and zero-shot settings and it is compatible with 57 datasets.

Miracle: Towards Personalized Dialogue Generation with Latent-Space Multiple Personal Attribute Control (2023.findings-emnlp)

Copied to clipboard

Zhenyi Lu, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Dangyang Chen, Jixiong Chen

Confidence is not Timeless: Modeling Temporal Validity for Rule-based Temporal Knowledge Graph Forecasting (2024.acl-long)

Challenge:	Personalized dialogue systems aim to endow the chatbot agent with more anthropomorphic traits for human-like interactions.
Approach:	They propose a method to generate personalized dialogues using latent-space energy-based models by using a latent space energy-model.
Outcome:	The proposed method outperforms baselines in personality controllability and response quality.

Copied to clipboard

Rikui Huang, Wei Wei, Xiaoye Qu, Shengzhe Zhang, Dangyang Chen, Yu Cheng

Large Dual Encoders Are Generalizable Retrievers (2022.emnlp-main)

Challenge:	Existing literature on temporal knowledge Graph Forecasting lacks in-depth investigation into how confidence evolves with time.
Approach:	They propose a framework to model the temporal validity of rules for Temporal Knowledge Graph Forecasting (TKGF) they propose rule-adversarial negative sampling and time-aware negative sampling strategies to facilitate TempValid learning.
Outcome:	The proposed framework outperforms state-of-the-art (SOTA) rule-based methods on six TKGF datasets.

Copied to clipboard

Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernandez Abrego, Ji Ma, Vincent Zhao, Yi Luan, Keith Hall, Ming-Wei Chang, Yinfei Yang

Adaptive Textual Label Noise Learning based on Pre-trained Models (2023.findings-emnlp)

Challenge:	Experimental results show that dual encoders outperform sparse and dense retrievers on the BEIR dataset significantly.
Approach:	They challenge belief that bottleneck layer is too limited for out-of-domain generalization . they scale up the model while keeping bottleneck as a single dot-product with a fixed size .
Outcome:	The proposed model outperforms sparse and dense retrievers on the BEIR dataset significantly.

Copied to clipboard

Shaohuan Cheng, Wenyu Chen, Fu Mingsheng, Xuanting Xie, Hong Qu

FCGCL: Fine- and Coarse-Granularity Contrastive Learning for Speech Translation (2022.findings-emnlp)

Challenge:	Existing approaches to learning with noisy labels are limited due to the time and labor costs involved.
Approach:	They propose an adaptive warm-up and hybrid training frameworks to learn with noisy labels based on pre-trained models.
Outcome:	The proposed approach performs comparable or even surpasses state-of-the-art methods in various noise scenarios, including scenarios with the mixture of multiple types of noise.

Copied to clipboard

Hao Zhang, Nianwen Si, Yaqi Chen, Zhen Li, Tong Niu, Xukui Yang, Dan Qu

TREA: Tree-Structure Reasoning Schema for Conversational Recommendation (2023.acl-long)

Challenge:	Existing methods to perform implicit knowledge transfer from machine translation to ST model are difficult because of the task complexity and data scarcity.
Approach:	They recommend a method which conducts explicit knowledge transfer from MT to ST model by fine and coarse granularity contrastive learning.
Outcome:	The proposed method improves the performance of the end-to-end speech translation model on all 8 languages.

Copied to clipboard

Wendi Li, Wei Wei, Xiaoye Qu, Xian-Ling Mao, Ye Yuan, Wenfeng Xie, Dangyang Chen

Natural Language Interfaces

Challenge:	Recent reasoning-based models cannot fully figure out complex causal relationships between mentioned entities with external knowledge.
Approach:	They propose a Tree structure Reasoning schEmA that constructs a multi-hierarchical scalable tree as the reasoning structure to clarify the causal relationships between mentioned entities.
Outcome:	Extensive experiments on two public CRS datasets show the proposed model works.

Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts (2025.naacl-long)

Copied to clipboard

Tong Zhu, Daize Dong, Xiaoye Qu, Jiacheng Ruan, Wenliang Chen, Yu Cheng

Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations (2026.findings-acl)

Challenge:	Mixture-of-Experts (MoE) models are constrained by their fixed model capacities when the number of tasks grows in instruction tuning.
Approach:	They propose to combine all training tasks and apply fixed sampling weights without considering the importance of different tasks as the model training state changes.
Outcome:	The proposed method can be used on knowledge & reasoning tasks and open-ended queries with limited training budget.

Copied to clipboard

Nanxu Gong, Zixin Chen, Haotian Li, Zishu Zhao, Jianxun Lian, Huamin Qu, Yanjie Fu, Xing Xie

Linguistics & Cognitive NLP

Challenge:	Existing benchmarks measure ToM capability improvement through story-reading, multiple-choice questions from a third-person perspective, while ignoring the first-person, dynamic nature of human-AI interactions.
Approach:	They propose a new paradigm of interactive ToM evaluation with both perspective and metric shifts.
Outcome:	The proposed approach improves the performance of four representative LLM enhancement techniques using real-world datasets and a user study.

MusTQ: A Temporal Knowledge Graph Question Answering Dataset for Multi-Step Temporal Reasoning (2024.findings-acl)

Copied to clipboard

Tingyi Zhang, Jiaan Wang, Zhixu Li, Jianfeng Qu, An Liu, Zhigang Chen, Hongping Zhi

MetaMixSpeech: Meta Task Augmentation for Low-Resource Speech Recognition (2025.findings-emnlp)

Challenge:	Existing studies focus on fact-centered reasoning with limited attention to temporal reasoning.
Approach:	They propose a new TKGQA dataset, MusTQ, which contains 666K multi-step temporal reasoning questions and a TKG.
Outcome:	The proposed model achieves state-of-the-art multi-step temporal reasoning ability with entity-time attention mechanism and optimized temporal knowledge graph representation.

Copied to clipboard

Yaqi Chen, Hao Zhang, Wenlin Zhang, XuKui Yang, Dan Qu, Yunpeng Liu

Meta-Adapter for Self-Supervised Speech Models: A Solution to Low-Resource Speech Recognition Challenges (2024.lrec-main)

Challenge:	Meta-learning has proven to be a powerful paradigm for improving speech recognition performance . however, multilingual meta learning also faces challenges such as task overfitting and learner overfit .
Approach:	a new method is proposed to augment meta-training tasks with "more data" the method incorporates both support and query augmentations .
Outcome:	The proposed method achieves a 6.35% improvement in the word error rate on FLEURS and Common Voice datasets.

Copied to clipboard

Yaqi Chen, Hao Zhang, Xukui Yang, Wenlin Zhang, Dan Qu

QuantumQA: Enhancing Scientific Reasoning via Physics-Consistent Dataset and Verification-Aware Reinforcement Learning (2026.acl-long)

Challenge:	Existing self-supervised learning models can learn latent representations from large amounts of unlabeled data, but they are expensive to fine-tune.
Approach:	They develop a meta-adapter to obtain meta-initialized parameters for self-supervised models . meta-Adapters show better generalization and extensibility than traditional pretraining methods .
Outcome:	Experiments on common voice and FLEURS datasets show Meta-Adapter performs better on low-resource languages . authors show it can be used on 12 low-source languages, but it requires huge computational resources .

Copied to clipboard

Songxin Qu, Tai-Ping Sun, Yun-Jie Wang, Huan-Yu Liu, Cheng Xue, Xiao-Fan Xu, Han Fang, Yang Yang, Yu-Chun Wu, Guo-Ping Guo, Zhao-Yun Chen

Reasoning

Challenge:	Large language models lack reliability in scientific domains that require strict adherence to physical constraints.
Approach:	They propose a large-scale dataset constructed via a task-adaptive strategy and a hybrid verification protocol that combines deterministic solvers with semantic auditing to guarantee scientific rigor.
Outcome:	The proposed model outperforms baselines and general-purpose preference models and is competitive with proprietary models.

Exploring Dual Encoder Architectures for Question Answering (2022.emnlp-main)

Copied to clipboard

Zhe Dong, Jianmo Ni, Dan Bikel, Enrique Alfonseca, Yuan Wang, Chen Qu, Imed Zitouni

FaLA: Fast Linear Adaptation for Replacing Backbone Models on Edge Devices (2023.findings-emnlp)

Challenge:	Dual encoders have been used for question-answering and information retrieval tasks with good results.
Approach:	They propose to use two different versions of dual encoders for QA retrieval tasks . they propose to share parameters in projection layers between two encoder towers .
Outcome:	The proposed architectures outperform SDE and ADE on QA retrieval tasks.

Copied to clipboard

Shuo Huang, Lizhen Qu, Xingliang Yuan, Chunyang Chen

FedDQC: Data Quality Control in Federated Instruction-tuning of Large Language Models (2025.findings-acl)

Challenge:	Current NLP models heavily rely on pre-trained models, such as BERT and RoBERTa.
Approach:	They propose a lightweight method for personalized NLP classification tasks post-backbone replacement using a personalized matrix calculated from documents corresponding to users' old and new backbones.
Outcome:	The proposed method achieves over 1000 times computation reduction in Flops for backpropagation and brings the user-specific initialization for personal matrix yielding significant performance boost compared with popular transfer learning methods.

Copied to clipboard

Yaxin Du, Rui Ye, Fengting Yuchi, Wanru Zhao, Jingjing Qu, Yanfeng Wang, Siheng Chen

More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection (2026.findings-acl)

Challenge:	Federated Learning (FL) enables privacy-preserving collaborative instruction tuning of large language models.
Approach:	They propose a federated instruction tuning framework with dynamic data quality control to solve this problem.
Outcome:	The proposed framework improves performance on mixed-quality datasets on synthetic and real-world datasets.

Copied to clipboard

Runze Sun, Yu Zheng, Zexuan Xiong, Zhongjin Qu, Lei Chen, Jie Zhou, Jiwen Lu