Papers by Wei Zeng

Unsupervised Non-transferable Text Classification (2022.emnlp-main)

Challenge:	Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility .
Approach:	They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning.
Outcome:	The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.

Copied to clipboard

Guangtao Zeng, Wei Lu

Information Extraction & Text Mining

Challenge:	Existing methods to train a good deep learning model require labeled data for the target domain which can be difficult to obtain.
Approach:	They propose an unsupervised non-transferable learning method that does not require annotated target domain data and introduce a secret key component for recovering the model’s access to the target domain.
Outcome:	The proposed method reduces model generalization ability in specific target domains while still recovering access to the target domain.

Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning (2022.acl-short)

Copied to clipboard

Yutao Mou, Keqing He, Yanan Wu, Zhiyuan Zeng, Hong Xu, Huixing Jiang, Wei Wu, Weiran Xu

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

Challenge:	Existing methods to find out out-of-domain (OOD) intents do not take prior knowledge of in-domain data into account.
Approach:	They propose a disentangled knowledge transfer method to bridge the gap between IND pre-training and OOD clustering by using a unified multi-head contrastive learning framework.
Outcome:	The proposed method is able to group new unknown intents into different clusters, enabling future development of the system.

Copied to clipboard

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

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning (2025.emnlp-main)

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.

Copied to clipboard

Ziqing Qiao, Yongheng Deng, Jiali Zeng, Dong Wang, Lai Wei, Guanbo Wang, Fandong Meng, Jie Zhou, Ju Ren, Yaoxue Zhang

Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation (2023.acl-long)

Challenge:	Existing methods for fine-tuning-based compression suffer from verbose outputs, increasing computational overhead.
Approach:	They propose a framework to generate concise reasoning chains using Confidence Injection and Early Stopping.
Outcome:	The proposed framework reduces the length of the model by up to 50% while maintaining high task accuracy.

Copied to clipboard

Weihao Zeng, Lulu Zhao, Keqing He, Ruotong Geng, Jingang Wang, Wei Wu, Weiran Xu

Dialogue Systems & Conversational Agents

Challenge:	Existing controllable dialogue generation models focus on single attribute and lack generalization capability to out-of-distribution multiple attribute combinations.
Approach:	They propose a compositional generalization model that learns from seen attributes and generalizes to unseen combinations.
Outcome:	The proposed model can learn from seen attribute values and generalize to unseen combinations.

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

AdaFuse: Adaptive Ensemble Decoding for Large Language Models (2026.acl-long)

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

Copied to clipboard

Chengming Cui, Tianxin Wei, Ziyi Chen, Ruizhong Qiu, Zhichen Zeng, Zhining Liu, Xuying Ning, Duo Zhou, Jingrui He

Synthesize, Prompt and Transfer: Zero-shot Conversational Question Generation with Pre-trained Language Model (2023.acl-long)

Challenge:	Existing ensemble approaches to large language models lack flexibility for mid-generation adaptation.
Approach:	They propose an adaptive ensemble decoding framework that dynamically selects semantically appropriate fusion units during generation.
Outcome:	The proposed framework outperforms existing ensemble frameworks on open-domain QA, arithmetic reasoning, and machine translation tasks.

Copied to clipboard

Hongwei Zeng, Bifan Wei, Jun Liu, Weiping Fu

NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

Challenge:	Existing research on QG focuses on generating single-turn questions, which are formalized as independent interactions.
Approach:	They propose a multi-stage knowledge transfer framework to leverage knowledge from single-turn question generation instances.
Outcome:	The proposed framework achieves 14.81 BLEU-4 (88.2% absolute improvement compared to T5) in CoQA with knowledge transferred from three single-turn datasets.

Copied to clipboard

Changyu Zeng, Yifan Wang, Zimu Wang, Wei Wang, Zhengni Yang, Muyi Bao, Jimin Xiao, Anh Nguyen, Yutao Yue

Helios: A Foundational Language Model for Smart Energy Knowledge Reasoning and Application (2026.eacl-long)

Challenge:	Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach:	They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome:	The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.

Copied to clipboard

Haoyu Jiang, Fanjie Zeng, Boan Qu, Xiaojie Lin, Wei Zhong

Harnessing Consistency for Robust Test-Time LLM Ensemble (2026.findings-eacl)

Challenge:	Enersys is a collaborative framework for end-to-end dataset construction that combines a large-scale pretraining, SFT, and RLHF datasets to improve performance.
Approach:	They propose a large language model tailored to the smart energy domain and a collaborative framework to advance LLM research in this field.
Outcome:	The proposed model improves domain knowledge mastery, task execution accuracy, and alignment with human preferences.

Copied to clipboard

Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong

Robustness in NLP

Challenge:	Existing efforts to improve LLM ensemble quality have focused on model consistency, but failures are often due to heterogeneous tokenization schemes and varying model expertise.
Approach:	They propose a plug-and-play technique that harnesses model consistency for robust LLM ensemble.
Outcome:	The proposed technique improves ensemble performance and robustness against erroneous signals.

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction (2024.acl-long)

Copied to clipboard

Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Lixiang Lixiang, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

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

Challenge:	None. None.. None!
Approach:	None. None.. None!
Outcome:	None. None. No. :

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.

Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language Models (2023.findings-acl)

Copied to clipboard

Fengzhu Zeng, Wei Gao

BizCompass: Benchmarking the Reasoning Capabilities of LLMs in Business Knowledge and Applications (2026.findings-acl)

Challenge:	Existing methods for few-shot and zero-shot fact verification require a large set of training data.
Approach:	They propose a method to prompt pre-trained language models to be consistent to improve the factuality assessment capability of PLMs.
Outcome:	The proposed method outperforms state-of-the-art few-shot fact verification models with a small number of unlabeled instances on zero-shot verification.

Copied to clipboard

Jianing Hao, Yuhe Wu, Yuanjian Xu, Shichang Meng, Shuai Yuan, Wei Zeng, Zixuan Wang, Guang Zhang

Uncovering Main Causalities for Long-tailed Information Extraction (2021.emnlp-main)

Challenge:	Existing benchmarks focus on narrow tasks and leave a fundamental question unanswered . Existing models only focus on specific tasks, requiring rigorous reasoning and knowledge .
Approach:	They propose a benchmark to connect theoretical foundations with practical business knowledge and applications.
Outcome:	The benchmark systematically evaluates both open-source and commercial LLMs . it reveals how theoretical knowledge translates into practical performance in business .

Copied to clipboard

Guoshun Nan, Jiaqi Zeng, Rui Qiao, Zhijiang Guo, Wei Lu

Information Extraction & Text Mining

Challenge:	Information Extraction (IE) aims to extract structural information from unstructured texts.
Approach:	They propose a framework that aims to uncover the main causalities behind data in the view of causal inference.
Outcome:	The proposed framework can detect the main causalities behind data in the view of causal inference.

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 .

Sailor: Open Language Models for South-East Asia (2024.emnlp-demo)

Copied to clipboard

Longxu Dou, Qian Liu, Guangtao Zeng, Jia Guo, Jiahui Zhou, Xin Mao, Ziqi Jin, Wei Lu, Min Lin

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding (2025.emnlp-industry)

Challenge:	Large language models (LLMs) rely on English data for training, but are often not comparable across other languages.
Approach:	They propose to develop a family of open language models for SEA languages . they use BPE dropout, aggressive data cleaning and deduplication to improve model robustness .
Outcome:	The proposed models perform well across four benchmarks, including commonsense reasoning, question answering, reading comprehension and examination.

Copied to clipboard

Xiangfeng Wang, Xiao Li, Yadong Wei, null Songxueyu, Yang Song, null Xiaxiaoqiang, Fangrui Zeng, Zaiyi Chen, null Liuliu, Gu Xu, Tong Xu

Large Language and Protein Assistant for Protein-Protein Interactions Prediction (2025.acl-long)

Challenge:	Existing methods for video editing rely on textual cues from ASR transcripts and segment selection, often neglecting rich visual context.
Approach:	They propose a human-inspired automatic video editing framework that leverages multimodal narrative understanding to address these limitations.
Outcome:	The proposed framework outperforms existing baselines across general and advertisement-oriented editing tasks.

Copied to clipboard

Peng Zhou, Pengsen Ma, Jianmin Wang, Xibao Cai, Haitao Huang, Wei Liu, Longyue Wang, Lai Hou Tim, Xiangxiang Zeng

Challenge:	Existing methods for predicting protein-protein interactions oversimplify the problem of PPI prediction in a semi-supervised manner.
Approach:	They propose a multimodal large language model that integrates proteins and PPI networks.
Outcome:	Experiments show that LLaPA can predict protein-protein interactions (mPPI) types and affinities based on sequence data.

Learning to Edit: Aligning LLMs with Knowledge Editing (2024.acl-long)

Copied to clipboard

Yuxin Jiang, Yufei Wang, Chuhan Wu, Wanjun Zhong, Xingshan Zeng, Jiahui Gao, Liangyou Li, Xin Jiang, Lifeng Shang, Ruiming Tang, Qun Liu, Wei Wang

Challenge:	Existing knowledge editing techniques rely on memorizing updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions.
Approach:	They propose a Learning to Edit framework that equips LLMs with the ability to apply updated knowledge to input questions through a two-phase process .
Outcome:	The proposed framework outperforms existing methods in knowledge editing tasks and compares it with four benchmarks and two LLM architectures.

What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? (2024.naacl-long)

Copied to clipboard

Yan Zeng, Hanbo Zhang, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong, Ruihua Song

Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads (2025.emnlp-industry)

Challenge:	Recent advances in GPT-4V have demonstrated remarkable multi-modal capabilities in processing image inputs and following open-ended instructions.
Approach:	They propose a plug-and-play technique to enhance multi-modal LLMs . they propose 'lynx' to train multi-modal LLM models .
Outcome:	The proposed training strategy improves understanding accuracy and instruction-following proficiency of multi-modal models.

Copied to clipboard

Yingxue Zhou, Tan Zhu, Tao Zeng, Zigeng Wang, Wei Shen

Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization (2022.naacl-main)

Challenge:	Existing NER-based transformer models are expensive and lack contextual dependencies, making them less reliable when handling unseen or ad-specific terms, e.g., brand names.
Approach:	They propose a two-stage approach to casing correction in e-commerce ad content that leverages Chain-of-Actions to enforce content policies while accurately handling ads-specific terms.
Outcome:	The proposed model outperforms existing NER-based models and achieves near-LLM performance at a fraction of the cost.

Copied to clipboard

Lulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Weiran Xu, Huixing Jiang, Wei Wu, Yanan Wu

Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction (2026.findings-acl)

Challenge:	Existing methods for domain adaptation of abstractive dialogue summarization lack generalization ability on new domains.
Approach:	They propose a domain-oriented prefix-tuning model that uses a prefix module to alleviate domain entanglement and discrete prompts to guide the model to focus on key contents of dialogues.
Outcome:	The proposed model can be generalized to two multi-domain dialogue summarization datasets.

Copied to clipboard

Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Huanqian Yan, Xinyi Zeng, Jingyuan Zhang, Yu Tian

Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)

Challenge:	Existing Large Language Model (LLM)-based mobile agents follow explicit user instructions without personalized needs.
Approach:	They propose a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance.
Outcome:	The proposed agent achieves state-of-the-art performance while maintaining competitive instruction execution performance.

Copied to clipboard

Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li

RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation (2024.emnlp-demo)

Challenge:	Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge.
Approach:	They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage.
Outcome:	The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold.

Copied to clipboard

Xuanwang Zhang, Yun-Ze Song, Yidong Wang, Shuyun Tang, Xinfeng Li, Zhengran Zeng, Zhen Wu, Wei Ye, Wenyuan Xu, Yue Zhang, Xinyu Dai, Shikun Zhang, Qingsong Wen

KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment (2023.acl-long)

Challenge:	Existing research on Retrieval Augmented Generation (RAG) does not address the problem of hallucinations and real-time updating of knowledge.
Approach:	They propose a modular open-source library to equip LLMs with external knowledge.
Outcome:	The proposed approach reduces the need for expensive open-source tools and lacks fair comparisons between novel RAG algorithms.

Copied to clipboard

Lingzhi Wang, Tong Chen, Wei Yuan, Xingshan Zeng, Kam-Fai Wong, Hongzhi Yin

Challenge:	Recent legislation of the "right to be forgotten" has led to the interest in machine unlearning . MU can be used to forget specific training instances as if they have never existed .
Approach:	They propose a general unlearning framework called KGA to induce forgetfulness . they propose several unlearning evaluation metrics with pertinence .
Outcome:	The proposed framework improves on large-scale datasets and provides insight into unlearning for NLP tasks.

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

Green & Sustainable NLP

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Attention Basin: Why Contextual Position Matters in Large Language Models (2026.acl-long)

Copied to clipboard

Zihao Yi, Zhenqing Ling, Delong Zeng, Haohao Luo, Zhe Xu, Wei Liu, Jian Luan, Wanxia Cao, Ying Shen

FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models (2024.acl-long)

Challenge:	Large Language Models (LLMs) are sensitive to the contextual position of information in input.
Approach:	They introduce Attention-Driven Reranking (AttnRank) which estimates a model’s intrinsic positional attention preferences using a small calibration set and reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions.
Outcome:	Experiments on multi-hop QA and few-shot in-context learning tasks show that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures.

Copied to clipboard

Yuxin Jiang, Yufei Wang, Xingshan Zeng, Wanjun Zhong, Liangyou Li, Fei Mi, Lifeng Shang, Xin Jiang, Qun Liu, Wei Wang

DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router (2026.findings-eacl)

Challenge:	Existing benchmarks focus on evaluating pure response quality, rather than assessing whether the response follows constraints stated in the instruction.
Approach:	They propose a Multi-level Fine-grained Constraints Following Benchmark for Large Language Models that adds a single constraint to the initial instruction at each increased level.
Outcome:	The proposed model can follow instructions with more constraints, and is deemed to have better instruction-following ability.

Copied to clipboard

Minghao Guo, Qingcheng Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, Wei Cheng

VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding (2025.emnlp-main)

Challenge:	Existing RAG methods lack fine-grained control over query and source sides, resulting in noisy retrieval and shallow reasoning.
Approach:	They propose an agentic RAG framework that integrates information sieving via LLM-as-a-knowledge-router.
Outcome:	Experiments on multi-hop QA tasks across heterogeneous sources demonstrate improved reasoning depth, retrieval precision, and interpretability over conventional approaches.

Copied to clipboard

Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang

Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold (2022.naacl-main)

Challenge:	Existing benchmarks focus on text comprehension, but MLLMs lack the ability to integrate visual data over financial visuals.
Approach:	They evaluate 21 state-of-the-art multimodal large language models in a zero-shot setting . they use an annotated question–answer pair from eight common financial image modalities .
Outcome:	The new benchmark outperforms existing models but trailed financial experts by 14 percentage points.

Copied to clipboard

Yanan Wu, Keqing He, Yuanmeng Yan, QiXiang Gao, Zhiyuan Zeng, Fujia Zheng, Lulu Zhao, Huixing Jiang, Wei Wu, Weiran Xu

Joint Optimization of Training Data and Policy in RLHF (2026.findings-acl)

Challenge:	Existing methods for OOD detection are based on labeled in-domain data . detecting out-of-domain (OOD) or unknown intents is challenging .
Approach:	They propose a novel reassigned contrastive learning method to discriminate IND intents for over-confident OOD and an adaptive class-dependent local threshold mechanism to separate similar IND and OOD intents.
Outcome:	The proposed method is effective for both aspects of overconfidence issues.

Copied to clipboard

Zhuohao Yu, Jiali Zeng, Weizheng Gu, Mengyuan Sun, Yidong Wang, Fandong Meng, Jie Zhou, Shikun Zhang, Wei Ye

Challenge:	JODP optimizes policies on fixed training inputs, limiting the diversity of learning signals.
Approach:	They propose a framework where policy generates improved variants of training problems to enhance its own learning.
Outcome:	The proposed framework improves on safety alignment tasks by allowing 4B models to reach 8B model performance with less than 1% additional computational overhead.

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning (2026.acl-long)

Copied to clipboard

Yizhe Zeng, Wei Zhang, Yunpeng Li, Juxin Xiao, Xiao Wang, Yuling Liu

Robustness in NLP

Challenge:	Existing CoT backdoor attacks manipulate intermediate reasoning steps to steer the model toward incorrect answers, but these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses.
Approach:	They propose a backdoor attack that exploits the model's post-output space to preserve clean CoTs while selectively steering the final answer toward a specific target.
Outcome:	Experiments show that MirageBD achieves over 90% success rate across four datasets and five models with a poison ratio of only 5%.

Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling (2025.acl-long)

Copied to clipboard

Jiayi Zeng, Yizhe Feng, Mengliang He, Wenhui Lei, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou

TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Data (2025.findings-emnlp)

Challenge:	Current error-handling works are performed in a passive manner, with explicit error- handling instructions.
Approach:	They propose a new benchmark to analyze LLMs' performance on a mis-prompt benchmark and a dataset to promote further research.
Outcome:	The proposed benchmark shows that current LLMs show poor performance on proactive error handling, and that SFT improves on error handling instances.

Copied to clipboard

Changjiang Jiang, Fengchang Yu, Haihua Chen, Wei Lu, Jin Zeng

Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings (2025.naacl-industry)

Challenge:	Large language models often underperform due to complex queries, noisy data, and limited numerical capabilities.
Approach:	They propose a framework that integrates seamlessly with mainstream LLMs to improve tabular reasoning.
Outcome:	The proposed framework outperforms existing methods in state-of-the-art analysis.

Copied to clipboard

Xuanqing Liu, Luyang Kong, Wei Niu, Afshin Khashei, Belinda Zeng, Steve Johnson, Jon Jay, Davor Golac, Matt Pope

Text Classification

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning.
Approach:	They propose a framework that combines the scalability of LLM-generated labels with the precision of human annotations to achieve higher speed and accuracy comparable to larger models.
Outcome:	The proposed framework significantly improves accuracy across utterance-level dialogue tasks, including sentiment detection (over 2%), dialogue act classification (over 1.5%), etc.

One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning (2023.acl-long)

Copied to clipboard

Guangtao Zeng, Peiyuan Zhang, Wei Lu

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

Challenge:	Parameter-efficient transfer learning methods can be expensive in storage when applied to broader ranges of tasks.
Approach:	They propose a method that enables efficient sharing of a single PETL network across layers and tasks.
Outcome:	The proposed method outperforms other methods with 10% parameters required by the latter on various downstream tasks.

Copied to clipboard

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

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

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

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance Identification (2024.findings-emnlp)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Ruike Zhang, Yuan Tian, Penghui Wei, Daniel Zeng, Wenji Mao

Low-Resource NLP

Challenge:	Existing research is conducted in monolingual setting on English datasets, whereas in other low-resource languages, it lacks sufficient data for training quality stance detection models.
Approach:	They propose a knowledge elicitation and retrieval framework that leverages the capability of large language models for stance knowledge acquisition and matches the target language input to the most relevant stance information.
Outcome:	The proposed framework improves on multilingual datasets and competitive baselines.

Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capability (2025.findings-acl)

Copied to clipboard

Mengliang He, Jiayi Zeng, Yankai Jiang, Wei Zhang, Zeming Liu, Xiaoming Shi, Aimin Zhou

Programming Languages in NLP

Challenge:	Existing code generation benchmarks neglect flowchart-based code generation . existing benchmarks lack flowcharting-based evaluation, limiting the potential of large language models and minimizing human error.
Approach:	They propose to use flowcharts to evaluate existing LLMs' code generation capabilities.
Outcome:	The proposed benchmarks show that the supervised fine-tuning technique contributes greatly to the models’ performance.

MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation (2025.naacl-long)

Copied to clipboard

Jinsheng Huang, Liang Chen, Taian Guo, Fu Zeng, Yusheng Zhao, Bohan Wu, Ye Yuan, Haozhe Zhao, Zhihui Guo, Yichi Zhang, Jingyang Yuan, Wei Ju, Luchen Liu, Tianyu Liu, Baobao Chang, Ming Zhang

FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models (2024.emnlp-demo)

Challenge:	Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, but many benchmarks suffer from systematic biases.
Approach:	They propose a benchmark to avoid Type-I errors by creating one perception question and one knowledge anchor question through a meticulous annotation process.
Outcome:	The proposed benchmark avoids Type-I errors while maintaining reliability of MCQ evaluations.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Zhengran Zeng, Wei Ye, Jindong Wang, Yue Zhang, Shikun Zhang

Multimodal Misinformation Detection by Learning from Synthetic Data with Multimodal LLMs (2024.findings-emnlp)

Challenge:	Large language models (LLMs) have revolutionized natural language processing with impressive performance across various tasks.
Approach:	They propose a framework for automated evaluations of large language models . they open-source their code at https://github.com/WisdomShell/FreeEval .
Outcome:	The framework is open-source and can be used to develop and validate new evaluation methods.

Copied to clipboard

Fengzhu Zeng, Wenqian Li, Wei Gao, Yan Pang