Papers by Bai Li

Semantics of the Unwritten: The Effect of End of Paragraph and Sequence Tokens on Text Generation with GPT2 (2021.acl-srw)

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

Copied to clipboard

He Bai, Peng Shi, Jimmy Lin, Luchen Tan, Kun Xiong, Wen Gao, Jie Liu, Ming Li

Generalizable Cross-Lingual Cognitive Distortion Detection with Standardized Annotations and Multi-Task Learning (2025.findings-acl)

Challenge:	Experimental results show that pre-trained language model GPT2 can generate better continuations by learning to generate the in the fine-tuning stage.
Approach:	They conduct experiments on an English essay dataset using Chinese-GPT2 . they find that the model can generate better continuations by learning to generate the in the fine-tuning stage.
Outcome:	The pre-trained language model GPT2 can generate better continuations by learning to generate the in the fine-tuning stage.

Copied to clipboard

Hongzhi Qi, Nan Bai, Jianqiang Li, Wei Zhai, Qing Zhao, Qi Gao, Bing Xiang Yang, Guanghui Fu

RoadMapper: A Multi-Agent System for Roadmap Generation of Solving Complex Research Problems (2026.findings-acl)

Challenge:	Existing studies on cognitive distortion have limited generalizability and performance of models in large-scale and cross-linguistic contexts.
Approach:	They propose a multi-task learning model based on teacher student architecture solution which improves generalization performance.
Outcome:	The proposed model improves generalizability and interpretability of the proposed model.

Copied to clipboard

Jiacheng Liu, Zichen Tang, Zhongjun Yang, Xinyi Hu, Xueyuan Lin, Linwei Jia, Ruofei Bai, Rongjin Li, Shiyao Peng, Haocheng Gao, Haihong E

LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-Context QA (2025.findings-acl)

Challenge:	Existing tools to generate structured content for research tasks are limited in their ability to generate high-quality roadmaps.
Approach:	They propose a benchmark to evaluate the ability of large language models (LLMs) to generate high-quality roadmaps for solving complex research problems.
Outcome:	The proposed system can improve LLMs’ ability for roadmap generation while saving 84% of the time required by human experts.

Copied to clipboard

Jiajie Zhang, Yushi Bai, Xin Lv, Wanjun Gu, Danqing Liu, Minhao Zou, Shulin Cao, Lei Hou, Yuxiao Dong, Ling Feng, Juanzi Li

Question Answering

Challenge:	Current long-context large language models lack citations to support their responses, making verification difficult due to potential hallucinations.
Approach:	They propose to use off-the-shelf LLMs to automatically construct long-context QA instances with precise sentence-level citations and leverage this pipeline to construct a large-scale SFT dataset for LQAC.
Outcome:	The proposed pipeline can generate responses with fine-grained citations on the fly, surpassing existing models including GPT-4o.

Chart-MRAG: Benchmarking Multimodal Retrieval Augmented Generation on Chart-based Documents (2026.acl-long)

Copied to clipboard

null Ymyang, Jiang Zhong, Li Jin, Xiao Sun, Jingwang Huang, null Gaojinpeng, Qing Liu, Yang Bai, Jingyuan Zhang, Rui Jiang, Qin Lei, Kaiwen Wei

Temporal Knowledge Graph Reasoning Based on N-tuple Modeling (2023.findings-emnlp)

Challenge:	Existing benchmarks focus on simple image-text interactions, overlooking complex visual formats like charts.
Approach:	They propose a semi-automatic framework for generating evaluation samples through multi-modal keypoint extraction, knowledge graph construction, and qa pair synthesis.
Outcome:	The proposed framework generates 4,738 question-answering pairs across 8 domains from real-world documents.

Copied to clipboard

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Saiping Guan, Yutao Zeng, Jiafeng Guo, Xueqi Cheng

Knowledge Representation

Challenge:	Existing Temporal Knowledge Graphs (TKGs) only contain their core entities and form them as quadruples.
Approach:	They propose to describe a temporal fact more accurately as an n-tuple . they propose to use a neural network to learn evolutional representations of entities .
Outcome:	The proposed model oversimplifies and causes information loss on two datasets.

WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models (2024.acl-long)

Copied to clipboard

Shangqing Tu, Yuliang Sun, Yushi Bai, Jifan Yu, Lei Hou, Juanzi Li

Rule-Aware Reinforcement Learning for Knowledge Graph Reasoning (2021.findings-acl)

Challenge:	Recent studies have developed watermarking algorithms which restrict the generation process to leave an invisible trace for watermark detection.
Approach:	They propose a benchmarking procedure that compares different methods to ensure consistent watermarking strength and jointly evaluates their generation and detection performance.
Outcome:	The proposed benchmark compares 4 open-source watermarks on 2 LLMs under 2 watermarking strengths and observes the common struggles for current methods on maintaining the generation quality.

Copied to clipboard

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai

Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality (2023.eacl-main)

Challenge:	Existing methods to reason missing facts on Knowledge Graphs face with serious incompleteness due to their black-box nature.
Approach:	They propose a multi-hop reasoning method that injects high quality symbolic rules into the model's reasoning process and employs partially random beam search.
Outcome:	The proposed method outperforms existing multi-hop reasoning methods in terms of Hit@1 and MRR.

Copied to clipboard

Xinnian Liang, Shuangzhi Wu, Chenhao Cui, Jiaqi Bai, Chao Bian, Zhoujun Li

I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing (2026.acl-long)

Challenge:	Experimental results show that our model outperforms strong baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.
Approach:	They propose a topic-aware global-local centrality model to help select the salient context from all sub-topics.
Outcome:	The proposed model outperforms baselines on three public dialogue summarization datasets: CSDS, MC, and SAMSUM.

Copied to clipboard

Jinghan Yu, Junhao Xiao, Chenyu Zhu, Jiaming Li, Jia Li, HanMing Deng, Xirui Wang, Guoli Jia, Jianjun Li, Xiang Bai, Bowen Zhou, Zhiyuan Ma

Detecting dementia in Mandarin Chinese using transfer learning from a parallel corpus (N19-1)

Challenge:	Existing text-guided image editing methods rely on end-to-end pixel-level inpainting paradigm . existing models lack such intermediate representations and Reasoning-then-action process .
Approach:	They propose a "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment.
Outcome:	The proposed paradigm outperforms existing methods in compositional editing tasks.

Copied to clipboard

Bai Li, Yi-Te Hsu, Frank Rudzicz

On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions (2025.findings-emnlp)

Challenge:	Existing methods for automatic detection of Alzheimer's disease (AD) are limited by a lack of data.
Approach:	They propose a method to learn a correspondence between independently engineered lexicosyntactic features in two languages, using a large parallel corpus of out-of-domain movie dialogue data.
Outcome:	The proposed method outperforms both unilingual and machine translation-based baselines in Mandarin Chinese and is the first to transfer feature domains in detecting cognitive decline.

Copied to clipboard

Weiqi Wang, Tianqing Fang, Haochen Shi, Baixuan Xu, Wenxuan Ding, Liyu Zhang, Wei Fan, Jiaxin Bai, Haoran Li, Xin Liu, Yangqiu Song

Anchoring-Guidance Fine-Tuning (AnGFT): Elevating Professional Response Quality in Role-Playing Conversational Agents (2025.emnlp-main)

Challenge:	Conceptualization is a fundamental element of human cognition and plays a pivotal role in generalizable reasoning.
Approach:	They propose to categorize different types of conceptualizations into four levels based on the types of instances being conceptualized.
Outcome:	The proposed categorization of different types of conceptualizations into four levels based on the types of instances being conceptualized .

Copied to clipboard

Qibin Li, Zhen Xu, Shengyuan Bai, Nianmin Yao, Kaili Sun, Bowen Wu, Ying Li, Baoxun Wang

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

Challenge:	Large Language Models (LLMs) have demonstrated significant advancements in various fields, notably in Role-Playing Conversational Agents (RPCAs).
Approach:	They propose an Anchoring-Guidance Fine-Tuning Framework to integrate relevant expert knowledge into RPCAs' training process to mitigate this issue.
Outcome:	The proposed framework significantly improves the RPCAs’ performance in handling role-specific professional queries while preserving their robust role-playing abilities.

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

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction (2026.findings-acl)

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.

Copied to clipboard

Yulin Chen, Haoran Li, Yuan Sui, Yue Liu, Yufei He, Xiaoling Bai, Chi Fei, Li Yabo, Haozhe Ma, Yangqiu Song, Bryan Hooi

Clear Up Confusion: Advancing Cross-Domain Few-Shot Relation Extraction through Relation-Aware Prompt Learning (2024.naacl-short)

Challenge:	Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions.
Approach:	They propose a prompt injection defense method that suppresses the model's instruction-following tendencies rather than suppressing them.
Outcome:	The proposed method outperforms prompt-engineering-based approaches and fine-tuning methods and reduces the ASR to nearly 0% in some scenarios.

Copied to clipboard

Ge Bai, Chenji Lu, Daichi Guo, Shilong Li, Ying Liu, Zhang Zhang, Guanting Dong, Ruifang Liu, Sun Yong

Low-Resource NLP

Challenge:	Existing approaches to few-shot Relation Extraction (RE) are prone to confusion when applying knowledge to a target domain with entirely new types of relations.
Approach:	They propose a relation-aware prompt learning method with pre-training to clear confusion by decomposing relation types through an innovative label prompt.
Outcome:	The proposed method outperforms previous sota methods and yields better results on cross-domain few-shot RE tasks.

How is BERT surprised? Layerwise detection of linguistic anomalies (2021.acl-long)

Copied to clipboard

Bai Li, Zining Zhu, Guillaume Thomas, Yang Xu, Frank Rudzicz

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning (2025.emnlp-main)

Challenge:	a number of studies have shown that transformer-based language models detect when a word is anomalous in context, but likelihood scores do not tell the cause of the anomaly.
Approach:	They propose to use Gaussian models for density estimation at intermediate layers of three language models to evaluate grammaticality.
Outcome:	The proposed method on BLiMP shows that language models employ different mechanisms to detect different types of linguistic anomalies.

Copied to clipboard

Yu Sun, Xingyu Qian, Weiwen Xu, Hao Zhang, Chenghao Xiao, Long Li, Deli Zhao, Wenbing Huang, Tingyang Xu, Qifeng Bai, Yu Rong

Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching (2025.findings-acl)

Challenge:	Existing medical reasoning datasets are limited in scale and typically rely on incomplete data.
Approach:	They propose to use ReasonMed to train medical reasoning models using a multi-agent generation, verification, and refinement pipeline.
Outcome:	The largest medical reasoning dataset to date surpasses the prior best sub-10B models by 4.17% and even exceeds LLaMA3.1-70B on PubMedQA by 4.60%.

Copied to clipboard

Jianfei Zhang, Bei Li, Jun Bai, Rumei Li, Yanmeng Wang, Chenghua Lin, Wenge Rong

New Intent Discovery with Attracting and Dispersing Prototype (2024.lrec-main)

Challenge:	In-Context Learning (ICL) empowers Large Language Models for rapid task adaptation without fine-tuning.
Approach:	They propose a method that aligns fine-tuning gradients between entire training set and selected examples to enable in-context learning and fine-uning.
Outcome:	The proposed method outperforms random selection on large LLMs from 4-shot to 128-shot scenarios across 9 datasets.

Copied to clipboard

Shun Zhang, Jian Yang, Jiaqi Bai, Chaoran Yan, Tongliang Li, Zhao Yan, Zhoujun Li

Text Clustering

Challenge:	Existing methods for detecting new intents with labeled data are not cluster-friendly . a robust prototypical attracting learning (RPAL) method is designed to compel instances to gravitate toward their corresponding prototype .
Approach:	They propose a robust and adaptive prototypical learning framework for globally distinct decision boundaries for both known and new intent categories.
Outcome:	The proposed method improves on CLINC, BANKING, and StackOverflow benchmarks on three challenging benchmarks.

Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun

Syntactic Text Processing

Challenge:	Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence.
Approach:	They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary.
Outcome:	Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training.

Towards Explainable Chinese Native Learner Essay Fluency Assessment: Dataset, Tasks, and Method (2024.findings-emnlp)

Copied to clipboard

Xinshu Shen, Hongyi Wu, Yadong Zhang, Man Lan, Xiaopeng Bai, Shaoguang Mao, Yuanbin Wu, Xinlin Zhuang, Li Cai

Syntactic Text Processing

Challenge:	Existing GEC datasets in Chinese fail to consider specific grammatical error types and overlook cross-sentence grammamatical errors.
Approach:	They propose to use Chinese essay fluency assessment to assess essay fluencies along with coarse and fine-grained errors and corrections to improve explainability.
Outcome:	The proposed dataset encapsulates essay fluency scores along with both coarse and fine-grained errors and corrections.

MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)

Copied to clipboard

Wei Zhai, Nan Bai, Qing Zhao, Jianqiang Li, Fan Wang, Hongzhi Qi, Meng Jiang, Xiaoqin Wang, Bing Xiang Yang, Guanghui Fu

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)

Challenge:	Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability.
Approach:	They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions.
Outcome:	The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications.

Copied to clipboard

Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks (2025.acl-long)

Challenge:	Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps.
Approach:	They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts.
Outcome:	The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models.

Copied to clipboard

Yushi Bai, Shangqing Tu, Jiajie Zhang, Hao Peng, Xiaozhi Wang, Xin Lv, Shulin Cao, Jiazheng Xu, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

Always the Best Fit: Adaptive Domain Gap Filling from Causal Perspective for Few-Shot Relation Extraction (2023.findings-emnlp)

Challenge:	Existing benchmarks on longcontext large language models fail to reflect their deep understanding capabilities across diverse tasks.
Approach:	They propose a benchmark to assess the ability of long-context large language models to handle long-text problems.
Outcome:	The proposed model achieves 50.1% accuracy when directly answering the questions . human experts achieve only 53.7% accuracy under a 15-minute time constraint .

Copied to clipboard

Ge Bai, Chenji Lu, Jiaxiang Geng, Shilong Li, Yidong Shi, Xiyan Liu, Ying Liu, Zhang Zhang, Ruifang Liu

Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation (2024.acl-long)

Challenge:	Existing approaches to cross-domain relation extraction have been limited by domains . data bias between domains can be difficult to fill, especially in few-shot scenarios .
Approach:	They propose a framework to bridge the semantic gap caused by data bias between domains . they use syntactic structure, label distribution, and entities to calculate causal effects .
Outcome:	The proposed framework fills the domain gap and yields better results on the few-shot task.

Copied to clipboard

Wen Wu, Bo Li, Chao Zhang, Chung-Cheng Chiu, Qiujia Li, Junwen Bai, Tara Sainath, Phil Woodland

TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis (2026.findings-acl)

Challenge:	Experimental results show that incorporating utterances without majority-agreed labels into an additional class reduces the classification performance of the other emotion classes.
Approach:	They propose to combine utterances without majority-agreed labels into an additional class . they propose to quantify uncertainty in emotion classification using evidential deep learning .
Outcome:	The proposed method retains classification accuracy while effectively detects ambiguous emotion expressions.

Copied to clipboard

Sikai Bai, Haoxi Li, Jie Zhang, Yongjiang Liu, Song Guo

Low-Resource NLP

Challenge:	Existing test-time methods are limited in specialized or novel domains where supervision is prohibitively expensive or unavailable.
Approach:	They propose a framework that augments training stream from unlabeled test queries.
Outcome:	Extensive experiments show TTVS outperforms state-of-the-art RL-based techniques on unlabeled test-time data.

Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)

Copied to clipboard

Yuanxing Liu, Weinan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che

IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact (2024.findings-acl)

Challenge:	E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations .
Approach:	They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues.
Outcome:	The proposed methods can be very effective in some cases, the authors say .

Copied to clipboard

Ruikang Liu, Haoli Bai, Haokun Lin, Yuening Li, Han Gao, Zhengzhuo Xu, Lu Hou, Jun Yao, Chun Yuan

Neural reality of argument structure constructions (2022.acl-long)

Challenge:	Existing quantization methods are compromising performance of large language models (LLMs) despite their high computational intensity, LLMs are still demanding intensive computation.
Approach:	They propose to generate the KV cache of pivot tokens losslessly from the full-precision model.
Outcome:	The proposed method generates the KV cache of pivot tokens losslessly from the full-precision model with no extra inference overhead.

Copied to clipboard

Bai Li, Zining Zhu, Guillaume Thomas, Frank Rudzicz, Yang Xu

Linguistics & Cognitive NLP

Challenge:	lexicalist linguistic theories assume argument structure is predictable from meaning of verbs . construction grammarians propose argument structure constructions distinct from verbs.
Approach:	They adapt psycholinguistic studies to probe for the existence of argument structure constructions in Transformer-based language models.
Outcome:	The proposed method could be used to probe argument structure constructions in LMs . the study shows that LM learners prefer grouping by construction over verb grouping .

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time (2025.emnlp-main)

Copied to clipboard

Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang

Towards Robust Universal Information Extraction: Dataset, Evaluation, and Solution (2025.acl-long)

Challenge:	Existing monotonic scaling methods for large reasoning models are not reliable.
Approach:	They propose a universal framework for modulating reasoning progress in large reasoning models at test time.
Outcome:	The proposed framework unifies and generalizes existing monotonic scaling methods and enables flexible and dense slow-to-fast reasoning modulation.

Copied to clipboard

Jizhao Zhu, Akang Shi, Zixuan Li, Long Bai, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Robustness in NLP

Challenge:	Existing robust benchmark datasets generate only a limited range of perturbations for a single Information Extraction (UIE) task, which fails to evaluate the robustness of UIE models effectively.
Approach:	They propose a new benchmark dataset that utilizes Large Language Models to generate more diverse and realistic perturbations across different IE tasks.
Outcome:	The proposed model performs better with only 15% of the data and is more robust with other models.

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

A Multi-Modal Knowledge Graph for Classical Chinese Poetry (2022.findings-emnlp)

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

Copied to clipboard

Yuqing Li, Yuxin Zhang, Bin Wu, Ji-Rong Wen, Ruihua Song, Ting Bai

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment (2024.findings-emnlp)

Challenge:	Existing studies in classical Chinese poetry area focus on generation and analysis of poetry.
Approach:	They propose to integrate the visual information of words in classical Chinese poetry into a multi-modal knowledge graph.
Outcome:	The proposed model bridges the semantic gap between two modalities and achieves state-of-the-art performance on the poetry-image retrieval task.

Copied to clipboard

Heyan Huang, Yinghao Li, Huashan Sun, Yu Bai, Yang Gao

Challenge:	Recent studies have demonstrated that In-Context Learning (ICA) can align Large Language Models (LLMs) with human preferences without requiring parameter adjustments.
Approach:	They investigate the effectiveness of each part in enabling ICA to function effectively and examine how variants in these parts impact alignment performance.
Outcome:	The proposed model can comprehend human instructions without parameter adjustments.

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Copied to clipboard

Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu

CogBench: Benchmarking Cognitive Alignment of Large Language Models in Educational Question Answering (2026.findings-acl)

Challenge:	Existing solutions for visual document understanding lack granularity of document textlines.
Approach:	They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome:	The proposed system performs better on various VDU tasks in English and Chinese.

Copied to clipboard

Tong Lu, Zhichun Wang, Yuanhao Sun, Yaoyu Zhou, Mingrui Li, Yiming Guan, Zhiyong Bai

Question Answering

Challenge:	Large language models (LLMs) possess strong capabilities in language understanding and generation, as well as remarkable problem-solving abilities.
Approach:	They propose a benchmark to assess the cognitive alignment capabilities of large language models in educational QA.
Outcome:	The proposed evaluation benchmark assesses the cognitive alignment capabilities of large language models in educational QA.

ART: rule bAsed futuRe-inference deducTion (2023.emnlp-main)

Copied to clipboard

Mengze Li, Tianqi Zhao, Bai Jionghao, Baoyi He, Jiaxu Miao, Wei Ji, Zheqi Lv, Zhou Zhao, Shengyu Zhang, Wenqiao Zhang, Fei Wu

MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios (2025.findings-acl)

Challenge:	Existing studies focus on language-based premises and deduce valid conclusions from visual observations.
Approach:	They propose a rule-based deductive reasoning task that uses video to deduce the correct future event . they use commonsense knowledge to annotate video and a strong baseline to conduct reasoning .
Outcome:	Empirical studies validate the rationality of ARTNet in deductive reasoning upon visual observations . ART is a method that rigorously follows a set of explicit constraints to deduce valid conclusions from empirical facts .

Copied to clipboard

JinYang Huang, Xiachong Feng, Qiguang Chen, Hanjie Zhao, Zihui Cheng, Jiesong Bai, Jingxuan Zhou, Min Li, Libo Qin

Programming Languages in NLP

Challenge:	MLDebugging is a benchmark designed to assess debugging challenges within multi-library Python code.
Approach:	They propose to introduce a benchmark to assess debugging challenges within multi-library Python code using 126 Python libraries.
Outcome:	The proposed benchmark covers 126 Python libraries and a wide range of multi-library code issues.

A New Pipeline for Knowledge Graph Reasoning Enhanced by Large Language Models Without Fine-Tuning (2024.emnlp-main)

Copied to clipboard

Zhongwu Chen, Long Bai, Zixuan Li, Zhen Huang, Xiaolong Jin, Yong Dou

M2C: Towards Automatic Multimodal Manga Complement (2023.findings-emnlp)

Challenge:	Conventional knowledge Graph Reasoning models learn the embeddings of KG components over the structure of a KG.
Approach:	They propose a pipeline to integrate knowledge from LLMs into KGs without fine-tuning . they propose knowledge alignment, KG reasoning and entity reranking to enhance conventional models .
Outcome:	The proposed pipeline can enhance the performance of conventional KGR models in incomplete and general situations.

Copied to clipboard

Hongcheng Guo, Boyang Wang, Jiaqi Bai, Jiaheng Liu, Jian Yang, Zhoujun Li

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale (2025.acl-long)

Challenge:	Multimodal manga analysis focuses on enhancing manga understanding with visual and textual features.
Approach:	They propose a task to enhance manga understanding with visual and textual features by providing a shared semantic space for vision and language understanding.
Outcome:	The proposed task provides a shared semantic space for vision and language understanding.

Copied to clipboard

Jiawei Guo, Tianyu Zheng, Yizhi Li, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Graham Neubig, Wenhu Chen, Xiang Yue

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment (2025.coling-main)

Challenge:	Current instruction-tuning datasets focus on simplistic visual question answering tasks, and provide phrase-level answers without any intermediate rationales.
Approach:	They propose to use open-source multimodal large language models to train MLLMs on a dataset with 12M instruction-response pairs to elicit CoT reasoning.
Outcome:	The proposed model achieves state-of-the-art performance on benchmarks such as MathVerse, MMMU-Pro, and MuirBench, and gains improvements of up to 4% on non-reasoning-based benchmarks.

Copied to clipboard

Jianfei Zhang, Jun Bai, Bei Li, Yanmeng Wang, Rumei Li, Chenghua Lin, Wenge Rong

Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio (2026.acl-long)

Challenge:	Human values are inherently diverse, making it insufficient to align LLMs solely with general preferences.
Approach:	They propose a flexible paradigm for individual preference alignment that disentangles preference representation from text generation in LLMs.
Outcome:	The proposed method produces aligned quality and better than PEFT-based methods while reducing training time for each new individual preference by 80% to 90%.

Copied to clipboard

Kaixiong Gong, Kaituo Feng, Bohao Li, Yibing Wang, Mofan Cheng, Shijia Yang, Jiaming Han, Benyou Wang, Yutong Bai, Zhuoran Yang, Xiangyu Yue

MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints (2026.findings-acl)

Challenge:	Recent multimodal large language models lack robust audio-visual integration ability and performance on DeafTest is highly correlated with AV-Odyssey accuracy.
Approach:	They propose a benchmarking tool that integrates audio-visual reasoning with audio-video cues to infer solutions.
Outcome:	The proposed model performs well on DeafTest, but lacks audio perception in simple audio tasks.

Copied to clipboard

Kangyang Luo, Shuzheng Si, Yuzhuo Bai, Cheng Gao, Zhitong Wang, Cheng Huang, Yingli Shen, Yufeng Han, Wenhao Li, Cunliang Kong, Maosong Sun

KnowCoder-X: Boosting Multilingual Information Extraction via Code (2025.findings-acl)

Challenge:	Existing supervised neural methods are underexplored for coreference resolution, especially in incremental clustering.
Approach:	They propose a dual-threshold incremental clustering approach based on a lightweight Transformer.
Outcome:	Experiments on common benchmarks show that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints.

Copied to clipboard

Yuxin Zuo, Wenxuan Jiang, Wenxuan Liu, Zixuan Li, Long Bai, Hanbin Wang, Yutao Zeng, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education? (2025.acl-short)

Challenge:	Empirical evidence indicates that Large Language Models exhibit spontaneous cross-lingual alignment in Information Extraction (IE) however, a significant imbalance across languages persists, highlighting an underlying deficiency.
Approach:	They propose a code LLM with advanced cross-lingual and multilingual capabilities for universal IE that standardizes the representation of multilingual schemas using Python classes and conducts IE alignment instruction tuning on translated instance prediction task.
Outcome:	The proposed model surpasses ChatGPT and SoTA by 30.17% without training in 29 unseen languages and significantly improves cross-lingual IE transferability.

Copied to clipboard

Tianshi Zheng, Weihan Li, Jiaxin Bai, Weiqi Wang, Yangqiu Song

Robustness in NLP

Challenge:	Existing knowledge discrepancies between textbooks and large language models can undermine RAG systems' performance.
Approach:	They propose to use a dataset to test RAG system robustness against knowledge discrepancies.
Outcome:	The proposed dataset shows that RAG systems suffer performance degradation when faced with knowledge discrepancies.

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models (2026.findings-acl)

Copied to clipboard

Yuhao Wu, Yushi Bai, Zhiqiang Hu, Juanzi Li, Roy Ka-Wei Lee

Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value Evaluation (2025.acl-demo)

Challenge:	Long-form text generation remains a challenge for large language models . generating extended sequences often leads to degraded coherence and logical consistency .
Approach:	They propose a framework that integrates explicit structured thinking into long-form text generation.
Outcome:	The proposed framework surpasses even larger-scale models in evaluation and human evaluation.

Copied to clipboard

Jing Yao, Xiaoyuan Yi, Shitong Duan, Jindong Wang, Yuzhuo Bai, Muhua Huang, Yang Ou, Scarlett Li, Peng Zhang, Tun Lu, Zhicheng Dou, Maosong Sun, James Evans, Xing Xie

Challenge:	Current evaluation methods for large language models face two key challenges: 1. evaluation validity and 2. Result interpretation reduce the pluralistic and incommensurable values to one-dimensional scores.
Approach:	They propose a platform for comprehensive value diagnosis of large language models (LLMs) that provides a generative evaluation paradigm that automatically creates real-world test items co-evolving with ever-advancing LLMs.
Outcome:	The proposed platform provides a framework for comprehensive value diagnosis of large language models (LLMs) with fine-grained scores and case studies across 27 value dimensions for 33 leading LLMs, customized comparisons, and visualized analysis of LLM’s alignment with cultural values.

EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoning (2026.acl-long)

Copied to clipboard

Chuanrui Hu, Xingze Gao, Zuyi Zhou, Dannong Xu, Yi Bai, Xintong Li, Hui Zhang, Tong Li, Chong Zhang, Lidong Bing, Yafeng Deng

Selective Temporal Knowledge Graph Reasoning (2024.lrec-main)

Challenge:	Existing memory systems for LLMs store isolated records and retrieve fragments . Existing systems store isolated data and fragments, limiting their ability to consolidate evolving experience and resolve conflicts.
Approach:	They propose an engram-inspired memory operating system that implements an 'engram'-inspired lifecycle for computational memory.
Outcome:	Experiments on LoCoMo, LongMemEval, and PersonaMeM-v2 show that EverMemeOS outperforms state-of-the-art methods on memory-augmented reasoning tasks.

Copied to clipboard

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, Xueqi Cheng

Knowledge Representation

Challenge:	Existing models cannot abstain from uncertain predictions, which will bring risks in real-world applications.
Approach:	They propose to abstain from uncertain future facts by using a confidence estimator . they take both the certainty of the current prediction and the accuracy of historical predictions into account .
Outcome:	The proposed abstention mechanism helps existing models make selective predictions instead of indiscriminate ones.

Fundamental Capabilities of Large Language Models and their Applications in Domain Scenarios: A Survey (2024.acl-long)

Copied to clipboard

Jiawei Li, Yizhe Yang, Yu Bai, Xiaofeng Zhou, Yinghao Li, Huashan Sun, Yuhang Liu, Xingpeng Si, Yuhao Ye, Yixiao Wu, 林一冠林一冠, Bin Xu, Ren Bowen, Chong Feng, Yang Gao, Heyan Huang

On the data requirements of probing (2022.findings-acl)

Challenge:	Existing benchmark-based evaluations cannot accurately reflect the performance of real-world applications.
Approach:	They propose a reliable strategy for domains to choose more robust LLMs for real-world applications.
Outcome:	The proposed strategy addresses the challenges faced by domains to choose more robust LLMs for real-world applications.

Copied to clipboard

Zining Zhu, Jixuan Wang, Bai Li, Frank Rudzicz

Challenge:	Existing methods to probe neural networks are expensive and require large datasets.
Approach:	They propose a method to estimate the required number of data samples in probing datasets . they use a classification task to encode a text with a deep neural network .
Outcome:	The proposed method estimates the required number of data samples in two probing configurations and proves it is statistically powerful.

Speech-to-Speech Translation with Discrete-Unit-Based Style Transfer (2024.acl-srw)

Copied to clipboard

Yongqi Wang, Bai Jionghao, Rongjie Huang, Ruiqi Li, Zhiqing Hong, Zhou Zhao

RAIDEN Benchmark: Evaluating Role-playing Conversational Agents with Measurement-Driven Custom Dialogues (2025.coling-main)

Challenge:	Existing methods to translate spoken utterances from one language to another are unable to preserve speaker timbre of source speech.
Approach:	They propose a pipeline with style-transfer capability on the basis of self-supervised speech representations and codec units.
Outcome:	The proposed model achieves zero-shot cross-lingual style transfer on previously unseen source languages.

Copied to clipboard

Bowen Wu, Kaili Sun, Ziwei Bai, Ying Li, Baoxun Wang

Natural Language Interfaces

Challenge:	Existing benchmarks for RPCA evaluation are lacking for dialogues . authors introduce specialized judging LLM for automatic RPca evaluation . compelling role-playing agent is expected to lead to more in-depth conversations .
Approach:	They propose a benchmark to assess the effectiveness of RPCA interactions using dialogues . they introduce a specialized judging LLM tailored for automatic RPca evaluation .
Outcome:	The proposed benchmark focuses on assessing particular dimensions at different stages of a conversation, facilitated through interactions conducted by annotators.

LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning (2025.emnlp-main)

Copied to clipboard

Tianshi Zheng, Cheng Jiayang, Chunyang Li, Haochen Shi, Zihao Wang, Jiaxin Bai, Yangqiu Song, Ginny Wong, Simon See

CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models (2025.coling-main)

Challenge:	Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning.
Approach:	They analyze the comparative dynamics of inductive (System 1) versus abductive/deductive (system 2) inference in large language models by using a controlled analogical reasoning environment and a MCQ/free-text task format.
Outcome:	The proposed methods can significantly scale LLM reasoning.

Copied to clipboard

Zhongzhi Li, Ming-Liang Zhang, Pei-Jie Wang, Jian Xu, Rui-Song Zhang, Yin Fei, Zhi-Long Ji, Jin-Feng Bai, Zhen-Ru Pan, Jiaxin Zhang, Cheng-Lin Liu

Numerical Reasoning

Challenge:	Large language models excel in various language tasks, while large multimodal models effectively handle visual-language problems.
Approach:	They propose to use a multimodal multimodal model evaluation benchmark to evaluate model performance in Chinese K12 classrooms.
Outcome:	The proposed model evaluation tool is integrated with the CMMaTH dataset.

How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey (2023.findings-emnlp)

Copied to clipboard

Jun Bai, Xiaofeng Zhang, Chen Li, Hanhua Hong, Xi Xu, Chenghua Lin, Wenge Rong

LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing (2026.findings-acl)

Challenge:	Transferability estimation has been a topic of great interest in computer vision fields . a lack of a comprehensive comparison between these estimation methods is a problem .
Approach:	They conduct a thorough survey of existing methods to find the most suitable model . they also outline difficulties of consideration of training details and applicability to text generation .
Outcome:	The proposed methods perform well with superiorities in effectiveness and efficiency.

Copied to clipboard

Hao Li, Yiqun Zhang, Zhaoyan Guo, Chenxu Wang, Shengji Tang, Qiaosheng Zhang, Yang Chen, Biqing Qi, Peng Ye, Lei Bai, Zhen Wang, Shuyue Hu

Challenge:	Large language model (LLM) routing assigns each query to the best suitable model from an ensemble.
Approach:	They introduce a large-scale benchmark and unified framework for LLM routing . they find that many routing methods exhibit similar performance under unified evaluation .
Outcome:	The proposed benchmark provides comprehensive metrics for both performance-oriented and performance-cost trade-off routing.

PiKGL: Leveraging Pruned Knowledge Graphs for Explainable Stance Detection (2026.tacl-1)

Copied to clipboard

Bingbing Wang, Jingjie Lin, Zhixin Bai, Xintong Song, Qianlong Wang, Min Yang, Xi Zeng, Jing Li, Ruifeng Xu

Sentiment Analysis

Challenge:	Experimental results demonstrate that a Pruned interpretable knowledge Graph Learning framework for explainable stance detection is state-of-the-art for social media stance prediction.
Approach:	They propose a Pruned interpretable knowledge Graph Learning framework for explainable stance detection that incorporates commonsense knowledge and prunes redundant information to ensure precision and minimize noise.
Outcome:	The proposed framework achieves state-of-the-art on three public datasets.

EduBench: A Comprehensive Benchmarking Dataset for Evaluating Large Language Models in Diverse Educational Scenarios (2026.acl-long)

Copied to clipboard

Bin Xu, Yu Bai, Huashan Sun, Yiguan Lin, Siming Liu, Xinyue Liang, Yaolin Li, Zhuangzhi Dong, Jingren Zhang, Yufan Deng, Xinyu Zou, Yang Gao, Heyan Huang

Enhancing Transformers for Generalizable First-Order Logical Entailment (2025.acl-long)

Challenge:	Existing benchmarks that focus on knowledge-intensive tasks do not reflect diverse educational scenarios.
Approach:	They propose a benchmark that incorporates 9 major scenarios and 4,000 educational contexts.
Outcome:	The proposed model performs comparable to state-of-the-art large models on the test set.

Copied to clipboard

Tianshi Zheng, Jiazheng Wang, Zihao Wang, Jiaxin Bai, Hang Yin, Zheye Deng, Yangqiu Song, Jianxin Li

Nested Event Extraction upon Pivot Element Recognition (2024.lrec-main)

Challenge:	Moreover, transformers have demonstrated proficiency in logical reasoning over natural language.
Approach:	They propose a logic-aware architecture that improves the performance in generalizable first-order logical entailment by combining distribution shifts and unseen knowledge.
Outcome:	The proposed architecture outperforms methods designed specifically for knowledge graph query answering on a dataset with a large dataset.

Copied to clipboard

Weicheng Ren, Zixuan Li, Xiaolong Jin, Long Bai, Miao Su, Yantao Liu, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases (2022.coling-1)

Challenge:	Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively.
Approach:	They propose a new model that extracts nested events mainly based on recognizing PEs.
Outcome:	The proposed model can extract nested events based on recognizing PEs . it incorporates information from both event types and argument roles to improve performance .

Copied to clipboard

Kun Zhang, Yunqi Qiu, Yuanzhuo Wang, Long Bai, Wei Li, Xuhui Jiang, Huawei Shen, Xueqi Cheng

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent (2025.emnlp-main)

Challenge:	Existing methods train one encoder-decoder-based model to fit all questions . however, such a one-size-fits-all strategy may not perform well for complex questions involving multiple KB relations or functional constraints.
Approach:	They propose a meta-learning framework for complex question generation over knowledge bases . they propose he meta-trained generator can acquire universal meta-knowledge .
Outcome:	The proposed framework can acquire universal and transferable meta-knowledge and quickly adapt to long-tailed samples under different dimensions.

Copied to clipboard

Xingzuo Li, Kehai Chen, Yunfei Long, Xuefeng Bai, Yong Xu, Min Zhang

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Existing approaches to integrate thoughts with actions can cause irreversible error propagation . Xi et al., 2023; Zhang eet coll., 2023) have focused on enhancing large language model (LLM) agents capable of helping humans tackle real-world challenges.
Approach:	They propose a framework called Generator-Assistant Stepwise Rollback to induce better decision-making for LLM agents by integrating a generator and an assistant to examine each action produced by the generator.
Outcome:	The proposed framework improves on three widely used benchmarks and can integrate seamlessly with other methods.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Jiaxin Bai, Wei Fan, Qi Hu, Qing Zong, Chunyang Li, Hong Ting Tsang, Hongyu Luo, Yauwai Yim, Haoyu Huang, Xiao Zhou, Feng Qin, Tianshi Zheng, Xi Peng, Xin Yao, Huiwen Yang, Leijie Wu, JI Yi, Gong Zhang, Renhai Chen, Yangqiu Song

Jointly Learning to Repair Code and Generate Commit Message (2021.emnlp-main)

Challenge:	Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach:	They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome:	The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.

Copied to clipboard

Jiaqi Bai, Long Zhou, Ambrosio Blanco, Shujie Liu, Furu Wei, Ming Zhou, Zhoujun Li

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)

Challenge:	Existing work performs code repair and commit message generation independently.
Approach:	They propose a cascaded method to repair program codes and generate commit messages in a unified framework.
Outcome:	The proposed model significantly outperforms baselines on a buggy-fixed-commit dataset.

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun

MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension (2024.findings-emnlp)

Challenge:	Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks.
Approach:	They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies.
Outcome:	The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%.

Copied to clipboard

Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, Yu Li

Question Answering

Challenge:	Existing models generate erroneous information and evaluations fail to assess factual correctness of models.
Approach:	They propose to use MoleculeQA to evaluate molecular factual correctness in large language models by organizing molecules into a taxonomy and building QA pairs through human and LLM efforts.
Outcome:	The proposed model improves the factual correctness of generated information and enables the development of new models.

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

PromptRank: Unsupervised Keyphrase Extraction Using Prompt (2023.acl-long)

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

Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xiaoyan Bai

Semantic Structure Enhanced Event Causality Identification (2023.acl-long)

Challenge:	Existing keyphrase extraction methods struggle with document and candidate length discrepancies or fail to fully utilize the pre-trained language model without further fine-tuning.
Approach:	They propose an unsupervised keyphrase extraction approach that uses a pre-trained language model to rank candidates based on document embeddings.
Outcome:	The proposed approach outperforms the existing keyphrase extraction approach on six benchmarks.

Copied to clipboard

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Challenge:	Existing methods for Event Causality Identification (ECI) capture implicit associations between events, which are difficult because they lack the ability to understand the associations between two events.
Approach:	They propose a model that captures the implicit associations between two events and integrates the event-centric structure information into a GNN-based event aggregator.
Outcome:	The proposed model improves on three widely used datasets showing that it integrates event-centric and event-associated semantic elements and captures event associations.

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction (2025.emnlp-main)

Copied to clipboard

Wenxuan Liu, Zixuan Li, Long Bai, Yuxin Zuo, Daozhu Xu, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

ImCoref-CeS: An Improved Lightweight Pipeline for Coreference Resolution with LLM-based Checker-Splitter Refinement (2026.acl-long)

Challenge:	Event Extraction (EE) is a long-standing target, but lacks an efficient and effective annotation framework to construct the corresponding datasets.
Approach:	They propose an LLM-based collaborative annotation framework that refines annotations of triggers from distant supervision and carries out argument annotation.
Outcome:	The proposed framework outperforms state-of-the-art methods on the largest EE dataset to date . it achieves the F1 scores of 90% and 85.3% on the human-annotated test set .

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao, Zhitong Wang, Yingli Shen, Wenhao Li, Zhu Liu, Yufeng Han, Jiayi Wu, Cunliang Kong, Maosong Sun

From Scaffolding to Assimilation: Progressive Structural Internalization for Format-Constrained Creative Text Generation (2026.findings-acl)

Challenge:	Existing supervised neural methods for coreference resolution are underexplored . current methods rely on small language models, but their potential is underexploited .
Approach:	They propose a framework that integrates an enhanced supervised model with LLM-based reasoning.
Outcome:	The proposed method surpasses existing state-of-the-art methods in coreference resolution.

Copied to clipboard

Wenhao Li, Yuwei Yang, Xiaoqing Wu, Yufeng Han, Cunliang Kong, Yuzhuo Bai, Xin Cong, Maosong Sun

Text Generation

Challenge:	Existing paradigms rely on unreliable prompting or rigid constrained decoding strategies to achieve aesthetic unity.
Approach:	They propose a framework to embed external constraints into the model’s intrinsic intuition and use it to generate open-ended creative texts.
Outcome:	The proposed framework surpasses baselines in both strict constraint adherence and literary aesthetics.

Word class flexibility: A deep contextualized approach (2020.emnlp-main)

Copied to clipboard

Bai Li, Guillaume Thomas, Yang Xu, Frank Rudzicz

MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models (2026.findings-acl)

Challenge:	Existing studies on word class flexibility have been fraught with difficulties in quantifying it accurately and at scale.
Approach:	They propose a method to quantify word class flexibility in 37 languages using contextualized word embeddings.
Outcome:	The proposed method builds on recent work in contextualized word embeddings to quantify semantic shift between word classes and uncovers shared tendencies in class flexibility across languages.

Copied to clipboard

Zhang He, Wenqian Cui, Haoning Xu, Xiao-Hui Li, Lei Zhu, Haoli Bai, Ma Shaohua, Irwin King

G2S: A General-to-Specific Learning Framework for Temporal Knowledge Graph Forecasting with Large Language Models (2025.findings-acl)

Challenge:	Existing benchmarks focus on evaluating single-round interactions, neglecting other critical aspects.
Approach:	They propose a benchmark to evaluate full-duplex speech language models in multi-round settings . they segment continuous full-dual dialogues into discrete turns for evaluation .
Outcome:	The proposed benchmark compared full-duplex speech language models with full-dual speech models . the results show that the models perform better in multi-round settings than standard models compared to benchmarks .

Copied to clipboard

Long Bai, Zixuan Li, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng, Tat-Seng Chua

ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities (2025.findings-naacl)

Challenge:	Recent studies have introduced Large Language Models (LLMs) for this task to enhance the models’ generalization abilities.
Approach:	They propose a General-to-Specific learning framework that disentangles the learning processes of two kinds of knowledge in a temporal temporal structure.
Outcome:	The proposed framework disentangles the learning processes of the above two kinds of knowledge and improves their generalization abilities.

Copied to clipboard

Jiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Haoping Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, Zirui Wang, Ruoming Pang

Benchmarking Post-Training Quantization of Large Language Models under Microscaling Floating Point Formats (2026.acl-long)

Challenge:	Recent advances in large language models have led to a growing interest in tool assisted LLMs . toolSandbox includes stateful tool execution, implicit state dependencies between tools .
Approach:	a new tool-based evaluation tool is released to help LLMs evaluate their tool-use capabilities. a tool-driven evaluation tool includes stateful tool execution, implicit state dependencies between tools and a built-in user simulator.
Outcome:	the toolSandbox evaluation benchmark shows that open source and proprietary models have a performance gap . the benchmarks show that even the most capable LLMs are challenged by state dependent tasks .

Copied to clipboard

Manyi Zhang, Ji-Fu Li, Zhongao Sun, Haoli Bai, Hui-Ling Zhen, Zhenhua Dong, Xianzhi Yu

Where Am I From? Identifying Origin of LLM-generated Content (2024.emnlp-main)

Challenge:	Microscaling Floating-Point (MXFP) is a low-precision format for large language models (LLMs).
Approach:	They conduct systematic evaluations of PTQ under Microscaling Floating-Point (MXFP) . they find that MXFP8 consistently achieves near-lossless performance .
Outcome:	The proposed method achieves near-lossless performance while MXFP4 introduces substantial accuracy degradation and remains challenging.

Copied to clipboard

Liying Li, Yihan Bai, Minhao Cheng

Challenge:	Generative models have produced high-quality content, but they pose security risks . a new framework for deep learning systems enables the tracing of AI-generated content back to its source .
Approach:	They propose a digital forensics framework that embeds a secret watermark into the generated output and a "depth watermark" this watermark strengthens the link between content and generator, enabling accurate tracing while maintaining the quality of the generated content.
Outcome:	The proposed framework ensures accurate tracing while maintaining quality of generated content.

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks (2025.emnlp-main)

Copied to clipboard

Heng Zhou, Hejia Geng, Xiangyuan Xue, Li Kang, Yiran Qin, Zhiyong Wang, Zhenfei Yin, Lei Bai

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Challenge:	Multi-agent systems (MAS) are limited by poor flexibility and scalability, with underdeveloped optimization strategies.
Approach:	They propose a task graph generation and a reward-driven two-stage agent selection process to integrate multi-agent systems to improve their reasoning capabilities.
Outcome:	The proposed model outperforms existing methods on Math-MAS and SciBench-MAS SciBech, while other methods completely fail.

Copied to clipboard

Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration (2025.findings-acl)

Challenge:	Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach:	They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome:	Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.

Copied to clipboard

Yang Zhang, Shixin Yang, Chenjia Bai, Fei Wu, Xiu Li, Zhen Wang, Xuelong Li

Integrating Deep Event-Level and Script-Level Information for Script Event Prediction (2021.emnlp-main)

Challenge:	Existing methods for grounding large language models suffer from inefficient querying . Existing approaches that rely on physical verification or self-reflection suffer from excessive querying.
Approach:	They propose a framework that introduces Reinforced Advantage feedback for efficient self-refinement of plans.
Outcome:	The proposed framework surpasses baselines in success rate and significantly decreases interaction steps of agents and query rounds of LLMs.

Copied to clipboard

Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, Xueqi Cheng

Cross-lingual Supervision Improves Unsupervised Neural Machine Translation (2021.naacl-industry)

Challenge:	Existing studies only consider a single event sequence corresponding to one common protagonist.
Approach:	They propose a Transformer-based model which integrates deep event-level and script-level information for script event prediction.
Outcome:	The proposed model is superior to existing models on the New York Times corpus . it utilizes rich information in the text to obtain more comprehensive representations .

Copied to clipboard

Mingxuan Wang, Hongxiao Bai, Hai Zhao, Lei Li

Construction of Paired Knowledge Graph - Text Datasets Informed by Cyclic Evaluation (2024.lrec-main)

Challenge:	Existing models that use only monolingual data have not been fully duplicated in the vast majority of language pairs, especially for zero-source languages.
Approach:	They propose to leverage the corpus from En-Fr and En-De to collectively train the translation from one language into many languages under one model.
Outcome:	The proposed model significantly improves translation quality with a big margin in the benchmark unsupervised translation tasks and achieves comparable performance to supervised NMT.

Copied to clipboard

Ali Mousavi, Xin Zhan, He Bai, Peng Shi, Theodoros Rekatsinas, Benjamin Han, Yunyao Li, Jeffrey Pound, Joshua M. Susskind, Natalie Schluter, Ihab F. Ilyas, Navdeep Jaitly

Structured Data in NLP

Challenge:	Prior studies have shown that sequence-to-sequence models learn to hallucinate when the conditioning data has poor correlation with the sequence being produced.
Approach:	They construct a dataset that pairs Knowledge Graphs (KG) and text together and compare their results to a cyclic evaluation model.
Outcome:	The proposed model performs better on cyclic generation of KGs than on KG-T, but less well on synchronization of KTs.

Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)

Copied to clipboard

Tianyu Gao, Xu Han, Yuzhuo Bai, Keyue Qiu, Zhiyu Xie, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Pre-training Distillation for Large Language Models: A Design Space Exploration (2025.acl-long)

Challenge:	Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations .
Approach:	They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models .
Outcome:	The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset.

Copied to clipboard

Hao Peng, Xin Lv, Yushi Bai, Zijun Yao, Jiajie Zhang, Lei Hou, Juanzi Li

Large Language Model-Based Event Relation Extraction with Rationales (2025.coling-main)

Challenge:	Knowledge distillation (KD) aims to transfer knowledge from a large teacher model to a smaller student model for model compression.
Approach:	They extend knowledge distillation to the pre-training phase of large language models . they first conduct an experiment using a teacher LLM to distill a 1.9B student LLM .
Outcome:	The proposed model can be used to distill a 1.9B student model using a teacher LLM.

Copied to clipboard

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

m3P: Towards Multimodal Multilingual Translation with Multimodal Prompt (2024.lrec-main)

Challenge:	Existing methods for ERE rely on large language models, but they face limitations.
Approach:	They propose an LLM-based approach with rationales for the ERE task . LLMERE transforms ERE into a question-and-answer task that may have multiple answers .
Outcome:	Experimental results show that LLMERE improves over existing methods.

Copied to clipboard

Jian Yang, Hongcheng Guo, Yuwei Yin, Jiaqi Bai, Bing Wang, Jiaheng Liu, Xinnian Liang, LinZheng Chai, Liqun Yang, Zhoujun Li

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

Challenge:	Existing multimodal neural machine translation models focus on bilingual translation, but experimental results show that they outperform the text-only baselines and multilingual multimodal methods by a large margin.
Approach:	They propose a framework to leverage the multimodal prompt to guide the Multimodal Multilingual Neural Machine Translation (m3P) this framework aligns the representations of different languages with the same meaning and generates the conditional vision-language memory for translation.
Outcome:	The proposed framework outperforms previous text-only baselines and multilingual multimodal methods by a large margin.

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

FedSpaLLM: Federated Pruning of Large Language Models (2025.naacl-long)

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

Guangji Bai, Yijiang Li, Zilinghan Li, Liang Zhao, Kibaek Kim

Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking (2024.emnlp-main)

Challenge:	Existing pruning methods assume public access to calibration data, which is impractical for privacy-sensitive applications.
Approach:	They propose a federated learning framework for pruning LLMs that prunes models locally based on private data while accounting for system heterogeneity and communication efficiency.
Outcome:	The proposed framework reduces communication overhead and personalizes pruning process based on client resources in federated settings.

Copied to clipboard

Jun Bai, Zhuofan Chen, Zhenzi Li, Hanhua Hong, Jianfei Zhang, Chen Li, Chenghua Lin, Wenge Rong

EcomScriptBench: A Multi-task Benchmark for E-commerce Script Planning via Step-wise Intention-Driven Product Association (2025.acl-long)

Challenge:	Existing methods for text ranking are based on intuition, but their estimated transferability may not align well with the objectives of text ranking.
Approach:	They propose to compute expected rank as transferability, explicitly reflecting the model’s ranking capability.
Outcome:	The proposed method shows significant improvements over previous classification-oriented TE methods, human intuition, and ChatGPT with minor time consumption.

Copied to clipboard

Weiqi Wang, Limeng Cui, Xin Liu, Sreyashi Nag, Wenju Xu, Chen Luo, Sheikh Muhammad Sarwar, Yang Li, Hansu Gu, Hui Liu, Changlong Yu, Jiaxin Bai, Yifan Gao, Haiyang Zhang, Qi He, Shuiwang Ji, Yangqiu Song

Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting (2026.acl-long)

Challenge:	Goal-oriented script planning is used by humans to plan for typical activities . however, this capability remains underexplored due to several challenges .
Approach:	They propose a framework that enables product-enriched scripts by associating products with each step based on the semantic similarity between the actions and their purchase intentions.
Outcome:	The proposed framework can generate product-enriched scripts from 2.4 million scripts . human annotations are conducted to provide gold labels for a sampled subset .

Copied to clipboard

Jinhu Fu, Yan Bai, Longzhu He, Yihang Lou, Yanxiao Zhao, Li Sun, Sen Su

SQUIRE: A Sequence-to-sequence Framework for Multi-hop Knowledge Graph Reasoning (2022.emnlp-main)

Challenge:	Existing knowledge editing methods focus on structured fact triples, overlooking diverse unstructured forms of factual information.
Approach:	They propose a method that allows LLMs to edit knowledge via Chain of Thoughts reasoning.
Outcome:	The proposed method achieves strong generalization across six diverse knowledge editing scenarios with a single round of training on three open-source language models.

Copied to clipboard

Yushi Bai, Xin Lv, Juanzi Li, Lei Hou, Yincen Qu, Zelin Dai, Feiyu Xiong

MM-MATH: Advancing Multimodal Math Evaluation with Process Evaluation and Fine-grained Classification (2024.findings-emnlp)

Challenge:	Existing methods for multi-hop knowledge graph reasoning suffer from slow and poor convergence . a transformer model can be used to learn and predict in an end-to-end fashion, giving faster convergence compared to previous methods .
Approach:	They propose a Sequence-to-sequence based multi-hop reasoning framework . it uses an encoder-decoder transformer structure to translate the query to a path .
Outcome:	The proposed framework can learn and predict in an end-to-end fashion, which gives better and faster convergence.

Copied to clipboard

Kai Sun, Yushi Bai, Ji Qi, Lei Hou, Juanzi Li

Information Retrieval

Challenge:	Existing benchmarks for multimodal reasoning in large multimodal models are underperforming on multimodal tasks.
Approach:	They propose a benchmark for multimodal reasoning in large multimodal models, MM-MATH . MM's process evaluation employs LMM-as-a-judge to automatically analyze solution steps . diagram misinterpretation is the most common error, they find .
Outcome:	The proposed model achieves only 31% accuracy, compared to 82% for humans.

Syntax for Semantic Role Labeling, To Be, Or Not To Be (P18-1)

Copied to clipboard

Shexia He, Zuchao Li, Hai Zhao, Hongxiao Bai

MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding (2024.emnlp-main)

Challenge:	Existing neural SRL models lack syntactic backbone for performance, limiting its use in deep learning.
Approach:	They propose an enhanced argument labeling model with extended korder argument pruning algorithm for effectively exploiting syntactic information.
Outcome:	The proposed model achieves state-of-the-art on the CoNLL-2008 and 2009 benchmarks in English and Chinese.

Copied to clipboard

Baixuan Xu, Weiqi Wang, Haochen Shi, Wenxuan Ding, Huihao Jing, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Long Chen, Yangqiu Song

From Past To Path: Masked History Learning for Next-Item Prediction in Generative Recommendation (2026.acl-long)

Challenge:	Existing methods for acquiring large-scale intentions generate product-centric intentions without product images and incur high costs for scalability.
Approach:	They propose a multimodal framework that allows Large Vision-Language Models to infer purchase intentions from multimodal product metadata and prioritize human-centric ones.
Outcome:	The proposed framework shows that it is robust to different prompts and superior to previous methods.

Copied to clipboard

Kaiwen Wei, Kejun he, Xiaomian Kang, Jie Zhang, null Ymyang, Li Jin, Zhenyang Li, Jiang Zhong, Richard He Bai, Junnan Zhu

Knowledge Graph Embedding with Atrous Convolution and Residual Learning (2020.coling-main)

Challenge:	Generative recommendation models inherently bias towards local contexts, failing to capture deeper historical dependencies necessary for understanding complex user intents.
Approach:	They propose a training framework that shifts the objective from simple next-step prediction to deep comprehension of history by entropy-guided masking policy and a curriculum learning scheduler to enhance the framework.
Outcome:	The proposed framework outperforms state-of-the-art generative models on three public datasets and shows that it is more accurate than current models.

Copied to clipboard

Feiliang Ren, Juchen Li, Huihui Zhang, Shilei Liu, Bochao Li, Ruicheng Ming, Yujia Bai

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

Challenge:	Existing knowledge graph embedding methods are complex and require time for training and inference.
Approach:	They propose an atrous convolution based knowledge graph embedding method that increases feature interactions by using atrous . they evaluate method on six benchmark datasets with different evaluation metrics .
Outcome:	The proposed method achieves better results on six benchmark datasets than state-of-the-art methods on most evaluation metrics.

Copied to clipboard

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

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (2024.acl-long)

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

Copied to clipboard

Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

Socratic Human Feedback (SoHF): Expert Steering Strategies for LLM Code Generation (2024.findings-emnlp)

Challenge:	Large language models (LLMs) can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases.
Approach:	They propose a bilingual, multi-task benchmark for long context understanding that extends context windows and more sophisticated memory mechanisms to improve models' long context capabilities.
Outcome:	The proposed model outperforms open-source models but struggles on longer contexts.

Copied to clipboard

Subramanian Chidambaram, Li Li, Min Bai, Xiaopeng Li, Kaixiang Lin, Xiong Zhou, Alex Williams

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) are increasingly used for generating code solutions, but struggle with complex programming problems without human guidance.
Approach:	They use the “Socratic Feedback” paradigm to map observed feedback strategies to five stages of Socratic Questioning to identify failures in LLMs.
Outcome:	The proposed models solved 74% of the problems that the models initially failed to solve on their own.

Unveiling the Implicit Toxicity in Large Language Models (2023.emnlp-main)

Copied to clipboard

Jiaxin Wen, Pei Ke, Hao Sun, Zhexin Zhang, Chengfei Li, Jinfeng Bai, Minlie Huang

LongAlign: A Recipe for Long Context Alignment of Large Language Models (2024.findings-emnlp)

Challenge:	Recent studies focus on probing toxic outputs that can be easily detected with existing toxicity classifiers, but LLMs can generate diverse implicit toxic output that are difficult to detect via simply zero-shot prompting.
Approach:	They propose a reinforcement learning based attacking method to induce the implicit toxic outputs in large language models by fine-tuning toxicity classifiers.
Outcome:	The proposed method generates implicit toxic outputs that are difficult to detect via zero-shot prompting on five widely-adopted toxicity classifiers.

Copied to clipboard

Yushi Bai, Xin Lv, Jiajie Zhang, Yuze He, Ji Qi, Lei Hou, Jie Tang, Yuxiao Dong, Juanzi Li

Fusion Makes Perfection: An Efficient Multi-Grained Matching Approach for Zero-Shot Relation Extraction (2024.naacl-short)

Challenge:	Existing studies to build long context language models focus on context extension and continual training on long text.
Approach:	They propose a recipe for instruction fine-tuning on input sequences of similar length . they adopt packing and sorted batching strategies to speed up supervised fine-uning .
Outcome:	The proposed model outperforms existing recipes for LLMs in long context tasks by 30% while maintaining proficiency in handling short, generic tasks.

Copied to clipboard

Shilong Li, Ge Bai, Zhang Zhang, Ying Liu, Chenji Lu, Daichi Guo, Ruifang Liu, Sun Yong

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation (2023.acl-long)

Challenge:	Existing methods to extract unseen relations require laborious manual annotation . a new approach uses fine-grained matching to reduce manual annotation cost .
Approach:	They propose an efficient multi-grained matching approach that uses virtual entity matching to reduce manual annotation cost.
Outcome:	The proposed approach outperforms the state-of-the-art methods and achieves inference efficiency and accuracy in zero-shot relation extraction tasks.

Copied to clipboard

Yulong Chen, Huajian Zhang, Yijie Zhou, Xuefeng Bai, Yueguan Wang, Ming Zhong, Jianhao Yan, Yafu Li, Judy Li, Xianchao Zhu, Yue Zhang

Text Generation

Challenge:	Existing work on cross-lingual summarization (CLS) does not consider crosslingual sources for summarizing.
Approach:	They propose a cross-lingual conversation summarization benchmark that explicitly considers source context.
Outcome:	The proposed method surpasses baselines on ConvSumX and 3 widely-used manual annotations.

MMRA: A Benchmark for Evaluating Multi-Granularity and Multi-Image Relational Association Capabilities in Large Visual Language Models (2026.findings-eacl)

Copied to clipboard

Siwei Wu, King Zhu, Yu Bai, Yiming Liang, Yizhi Li, Haoning Wu, Jiaheng Liu, Ruibo Liu, Xingwei Qu, Xuxin Cheng, Ge Zhang, Wenhao Huang, Chenghua Lin

IntentionQA: A Benchmark for Evaluating Purchase Intention Comprehension Abilities of Language Models in E-commerce (2024.findings-emnlp)

Challenge:	Current multimodal benchmarks focus on facts within individual images, but neglect associative relations among multiple images.
Approach:	They propose a multi-image relational association task and a MMRA benchmark to evaluate LVLMs.
Outcome:	The proposed benchmarks show that entity-level multi-image perception tasks pose greater challenges than image-level tasks.

Copied to clipboard

Wenxuan Ding, Weiqi Wang, Sze Kwok, Minghao Liu, Tianqing Fang, Jiaxin Bai, Xin Liu, Changlong Yu, Zheng Li, Chen Luo, Qingyu Yin, Bing Yin, Junxian He, Yangqiu Song

Towards Real-world Scenario: Imbalanced New Intent Discovery (2024.acl-long)

Challenge:	Existing approaches that distill intentions from LMs fail to generate meaningful and human-centric intentions applicable in real-world E-commerce contexts.
Approach:	They propose a double-task multiple-choice question answering benchmark to evaluate LMs' comprehension of purchase intentions in E-commerce.
Outcome:	The proposed benchmark consists of 4,360 carefully curated problems across three difficulty levels, constructed using an automated pipeline to ensure scalability on large E-commerce platforms.

Copied to clipboard

Shun Zhang, Yan Chaoran, Jian Yang, Jiaheng Liu, Ying Mo, Jiaqi Bai, Tongliang Li, Zhoujun Li

Enhancing Multimodal Continual Instruction Tuning with BranchLoRA (2025.acl-long)

Challenge:	Existing studies focus on detecting known and previously undefined categories of user intent . skewed and long-tailed distributions often encountered in open-world scenarios .
Approach:	They propose to use imbalanced new intent discovery task to identify familiar and novel intent categories within long-tailed distributions.
Outcome:	The proposed model outperforms the existing benchmark on three datasets to simulate the real-world long-tail distributions.

Copied to clipboard

Duzhen Zhang, Yong Ren, Zhong-Zhi Li, Yahan Yu, Jiahua Dong, Chenxing Li, Zhilong Ji, Jinfeng Bai

Ruler: A Model-Agnostic Method to Control Generated Length for Large Language Models (2024.findings-emnlp)

Challenge:	Existing approaches to fine tune Multimodal Large Language Models (MLLMs) are prone to Catastrophic Forgetting (CF) existing approaches rely on the Mixture-of-Experts (MoE) LoRA framework to preserve previous instruction alignments.
Approach:	They propose an asymmetric tuning-freezing mechanism to mitigate parameter inefficiency . branch-specific routers are introduced to ensure optimal branch distribution over time .
Outcome:	The proposed framework outperforms existing frameworks on the latest MCIT benchmarks.

Copied to clipboard

Jiaming Li, Lei Zhang, Yunshui Li, Ziqiang Liu, Yuelin Bai, Run Luo, Longze Chen, Min Yang

ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Series (2025.findings-acl)

Challenge:	Large language models struggle to meet user’s needs when required to generate responses of a specific length due to their inherent difficulty in accurately perceiving numerical constraints.
Approach:	They propose a Target Length Generation Task and propose RULER, a model-agnostic approach that controls generated length for large language models.
Outcome:	The proposed model-agnostic approach improves instruction-following ability of large language models under length-constrained instructions and can generate appropriate MLT when length constraints are not explicitly provided.

Copied to clipboard

Shuai Niu, Jing Ma, Hongzhan Lin, Liang Bai, Zhihua Wang, V. W., Richard Yi Da Xu, Guo Li, Xian Yang

PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization (2022.coling-1)

Challenge:	Large language models excel at processing unstructured data, but integrating time series data with text remains a challenge.
Approach:	They propose a self-supervised multimodal framework that uses prompt-guided learning to unify heterogeneous data types.
Outcome:	The proposed framework outperforms state-of-the-art approaches on disease diagnosis tasks using real-world datasets.

Copied to clipboard

Xiaochen Liu, Yang Gao, Yu Bai, Jiawei Li, Yinan Hu, Heyan Huang, Boxing Chen

CANDLE: Iterative Conceptualization and Instantiation Distillation from Large Language Models for Commonsense Reasoning (2024.acl-long)

Challenge:	Experimental results show that our method outperforms full-model tuning in few-shot abstractive summarization tasks.
Approach:	They propose a soft prompts architecture with prompt pre-training and prompt fine-tuning paradigm to support few-shot abstractive summarization.
Outcome:	The proposed model outperforms Prompt Tuning and Profix-Tuning on CNN/DailyMail and XSum datasets and outperfies Profix Tuning by a large margin.

Copied to clipboard

Weiqi Wang, Tianqing Fang, Chunyang Li, Haochen Shi, Wenxuan Ding, Baixuan Xu, Zhaowei Wang, Jiaxin Bai, Xin Liu, Cheng Jiayang, Chunkit Chan, Yangqiu Song

Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimization (2025.emnlp-main)

Challenge:	Existing approaches to generalize commonsense reasoning lack instantiated knowledge and require pre-built concept taxonomies and annotations.
Approach:	They propose a framework that iteratively performs contextualized conceptualization and instantiation over commonsense knowledge bases by instructing large language models to generate both types of knowledge with critic filtering.
Outcome:	Empirical results show that distilling CANDLE on student models provides benefits across three downstream tasks.

Copied to clipboard

Shuo Xing, Peiran Li, Yuping Wang, Ruizheng Bai, Yueqi Wang, Chan-Wei Hu, Chengxuan Qian, Huaxiu Yao, Zhengzhong Tu

Discovering Language Model Behaviors with Model-Written Evaluations (2023.findings-acl)

Challenge:	emergence of large Vision Language Models (VLMs) has broadened the capabilities of single-modal Large Language Model (LLM) but VLMs are prone to significant hallucinations, especially in the form of cross-modal inconsistencies.
Approach:	They propose a new alignment framework that leverages image retrieval to integrate both textual and visual preference signals.
Outcome:	The proposed framework mitigates hallucinations more effectively than previous methods . it maintains robustness and scalability across a wide range of VLM sizes and architectures .

Copied to clipboard

Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kadavath, Andy Jones, Anna Chen, Benjamin Mann, Brian Israel, Bryan Seethor, Cameron McKinnon, Christopher Olah, Da Yan, Daniela Amodei, Dario Amodei, Dawn Drain, Dustin Li, Eli Tran-Johnson, Guro Khundadze, Jackson Kernion, James Landis, Jamie Kerr, Jared Mueller, Jeeyoon Hyun, Joshua Landau, Kamal Ndousse, Landon Goldberg, Liane Lovitt, Martin Lucas, Michael Sellitto, Miranda Zhang, Neerav Kingsland, Nelson Elhage, Nicholas Joseph, Noemi Mercado, Nova DasSarma, Oliver Rausch, Robin Larson, Sam McCandlish, Scott Johnston, Shauna Kravec, Sheer El Showk, Tamera Lanham, Timothy Telleen-Lawton, Tom Brown, Tom Henighan, Tristan Hume, Yuntao Bai, Zac Hatfield-Dodds, Jack Clark, Samuel R. Bowman, Amanda Askell, Roger Grosse, Danny Hernandez, Deep Ganguli, Evan Hubinger, Nicholas Schiefer, Jared Kaplan

MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property (2024.lrec-main)

Challenge:	Prior work creates evaluations with crowdwork or existing data sources, which are not always available.
Approach:	They generate evaluations automatically with language models (LMs) using crowdwork or existing data sources to find out how they behave .
Outcome:	The results show that large LMs repeat back a dialog user’s preferred answer and express greater desire to pursue concerning goals like resource acquisition and goal preservation.

Copied to clipboard

Shiwen Ni, Minghuan Tan, Yuelin Bai, Fuqiang Niu, Min Yang, Bowen Zhang, Ruifeng Xu, Xiaojun Chen, Chengming Li, Xiping Hu

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks.
Approach:	They propose a benchmark for the evaluation of large language models in the IP domain . they also propose supervised multilingual large language model called MoZi .
Outcome:	The proposed model outperforms four well-known LLMs on the MoZIP benchmark . the most powerful ChatGPT does not reach the passing level .

OssCSE: Overcoming Surface Structure Bias in Contrastive Learning for Unsupervised Sentence Embedding (2023.emnlp-main)

Copied to clipboard

Zhan Shi, Guoyin Wang, Ke Bai, Jiwei Li, Xiang Li, Qingjun Cui, Belinda Zeng, Trishul Chilimbi, Xiaodan Zhu

StyleDGPT: Stylized Response Generation with Pre-trained Language Models (2020.findings-emnlp)

Challenge:	Recent studies show that contrastive learning is effective in sentence representation learning . but, the surface structure bias is a problem in the current model .
Approach:	They propose to combine a sentence with a sub-semantic sentence to investigate the surface structure bias.
Outcome:	The proposed model achieves state-of-the-art on standard semantic textual similarity tasks using different pre-trained backbones.

Copied to clipboard

Ze Yang, Wei Wu, Can Xu, Xinnian Liang, Jiaqi Bai, Liran Wang, Wei Wang, Zhoujun Li

Text Generation

Challenge:	Existing methods for generating responses following a desired style are lacking of parallel data for training.
Approach:	They propose a KL loss and a style classifier to fine-tune response generation . they show that their model can significantly outperform state-of-the-art methods .
Outcome:	The proposed model outperforms state-of-the-art models in style consistency and contextual coherence with two public datasets.

MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings (2026.acl-long)

Copied to clipboard

Yiqun Zhang, Hao Li, Zihan Wang, Shi Feng, Xiaocui Yang, Daling Wang, Bo Zhang, Lei Bai, Shuyue Hu

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Challenge:	Multi-turn, long-horizon tasks require dozens of sequential model calls per episode.
Approach:	They propose a cost-aware multi-turn LLM routing tool which encodes interaction history and candidate models into joint history–model embeddings and learns an outcome estimator from logged trajectories to predict turn-level model utility.
Outcome:	The proposed model reduces cost and performance by 58.7% on ScienceWorld and on Humanity’s Last Exam (HLE) and even reduces costs for held-out tasks.

Copied to clipboard

Zelin Tan, Hejia Geng, Xiaohang Yu, Mulei Zhang, Guancheng Wan, Yifan Zhou, Qiang He, Xiangyuan Xue, Heng Zhou, Yutao Fan, Zhong-Zhi Li, Zaibin Zhang, Guibin Zhang, Chen Zhang, Zhenfei Yin, Philip Torr, Lei Bai

Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)

Challenge:	elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach:	They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome:	The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.

Copied to clipboard

Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, Yangqiu Song

OmniOData: Unleashing Small Language Models for OData Query Generation with Synthetic Data and Reinforcement Learning (2026.acl-industry)

Challenge:	Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions.
Approach:	They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions.
Outcome:	The proposed model outperforms state-of-the-art methods and shows its utility.

Copied to clipboard

Tao Bai, Zhaochen Li, Hongxin Shao, Daniel Dahlmeier

VLP: Vision-Language Preference Learning for Embodied Manipulation (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have been used for structured query generation but lack high-fidelity, execution-validated datasets.
Approach:	They propose a framework that generates SynOData, the first large-scale OData corpus featuring execution-grounded queries and reasoning traces.
Outcome:	The proposed model matches or surpasses proprietary systems on industrial benchmarks.

Copied to clipboard

Runze Liu, Chenjia Bai, Jiafei Lyu, Shengjie Sun, Yali Du, Xiu Li

Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model (2022.naacl-industry)

Challenge:	Existing approaches to reward engineering are time-consuming and expensive to collect human preference labels.
Approach:	They propose a vision-language preference learning framework which learns from human feedback . they define three types of language-conditioned preferences and construct a visual preference dataset .
Outcome:	The proposed framework outperforms baselines on embodied manipulation tasks and can be applied to other tasks.

Copied to clipboard

Gongzheng Li, Yadong Xi, Jingzhen Ding, Duan Wang, Ziyang Luo, Rongsheng Zhang, Bai Liu, Changjie Fan, Xiaoxi Mao, Zeng Zhao

GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models (2024.findings-emnlp)

Challenge:	Recent studies show that transformer-based models are effective over many tasks, but they are expensive to deploy in the industrial application.
Approach:	They propose a transformer-based inference solution that optimizes kernels for long inputs and large hidden sizes and a flexible CUDA memory manager to reduce the memory footprint when deploying a large model.
Outcome:	The proposed solution achieves an average speedup of 1.40-4.20x on the transformer decoder layer with an A100 GPU.

Copied to clipboard

Shilong Li, Yancheng He, Hangyu Guo, Xingyuan Bu, Ge Bai, Jie Liu, Jiaheng Liu, Xingwei Qu, Yangguang Li, Wanli Ouyang, Wenbo Su, Bo Zheng

FolkScope: Intention Knowledge Graph Construction for E-commerce Commonsense Discovery (2023.findings-acl)

Challenge:	Existing models for long contexts struggle to handle long inputs due to limited context window and memory usage.
Approach:	They propose a graph-based agent system that analyzes long texts into a graphical graph . GraphReader consistently outperforms GPT-4-128k across context lengths from 16k to 256k .
Outcome:	The proposed model outperforms existing models on four challenging benchmarks.

Copied to clipboard

Changlong Yu, Weiqi Wang, Xin Liu, Jiaxin Bai, Yangqiu Song, Zheng Li, Yifan Gao, Tianyu Cao, Bing Yin

Commonsense Reasoning

Challenge:	Existing intention-based studies on recommendation tasks are limited and use models to implicitly model the intention memberships.
Approach:	They propose a framework that leverages the generation power of large language models and human-in-the-loop annotation to semi-automatically construct the intention knowledge graph.
Outcome:	The proposed framework can model e-commerce knowledge and have many potential applications.

Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasks (2025.emnlp-main)

Copied to clipboard

Xubo Qin, Jun Bai, Jiaqi Li, Zixia Jia, Zilong Zheng

ReviewGrounder: Improving Review Substantiveness with Rubric-Guided, Tool-Integrated Agents (2026.acl-long)

Challenge:	Existing methods for retrieval of information excel at textual and semantic matching but struggle in reasoning-intensive retrieval tasks.
Approach:	They propose a family of small-scale language models for query reasoning and rewriting in reasoning-intensive retrieval.
Outcome:	The proposed model outperforms existing models on a BRIGHT benchmark with BM25 retrievers.

Copied to clipboard

Zhuofeng Li, Yi Lu, Dongfu Jiang, Haoxiang Zhang, Yuyang Bai, Chuan Li, Yu Wang, Shuiwang Ji, Jianwen Xie, Yu Zhang

MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL (2025.coling-main)

Challenge:	Rapid rise in AI conference submissions has driven increasing exploration of large language models (LLMs) for peer review support.
Approach:	They propose a peer review benchmarking tool based on paper-specific rubrics and a rubric-guided framework that decomposes reviewing into drafting and grounding stages.
Outcome:	The proposed framework outperforms baselines with stronger/larger backbones in both alignment with human judgments and rubric-based review quality across 8 dimensions.

Copied to clipboard

Bing Wang, Changyu Ren, Jian Yang, Xinnian Liang, Jiaqi Bai, LinZheng Chai, Zhao Yan, Qian-Wen Zhang, Di Yin, Xing Sun, Zhoujun Li

Programming Languages in NLP

Challenge:	Recent LLM-based Text-to-SQL methods suffer from performance degradation on “huge” databases and complex user questions that require multi-step reasoning.
Approach:	They propose a framework that integrates a decomposer agent and auxiliary agents to generate SQL queries from natural language text.
Outcome:	The proposed framework achieves comparable execution accuracy on SQL-Llama tasks compared to the baseline model.

Open World Classification with Adaptive Negative Samples (2022.emnlp-main)

Copied to clipboard

Ke Bai, Guoyin Wang, Jiwei Li, Sunghyun Park, Sungjin Lee, Puyang Xu, Ricardo Henao, Lawrence Carin

Information Retrieval

Challenge:	Existing models with no effective open category data during training are limited by the lack of effective open categories data during the training stage.
Approach:	They propose an approach to generate effective open category samples in the training stage and without requiring prior knowledge or external datasets.
Outcome:	The proposed approach generates effective synthetic open category samples in the training stage and without requiring any prior knowledge or external datasets.

Multilingual prediction of Alzheimer’s disease through domain adaptation and concept-based language modelling (N19-1)

Copied to clipboard

Kathleen C. Fraser, Nicklas Linz, Bai Li, Kristina Lundholm Fors, Frank Rudzicz, Alexandra König, Jan Alexandersson, Philippe Robert, Dimitrios Kokkinakis

DeepPrune: Parallel Scaling without Inter-trace Redundancy (2026.findings-acl)

Challenge:	Existing work on speech and language models has been limited by the size of available datasets.
Approach:	They propose to augment a small French dataset with a much larger English dataset to augment the language model to model the order in which information units are produced by dementia patients and controls.
Outcome:	The proposed model improves classification performance in English and French separately.

Copied to clipboard

Shangqing Tu, Yaxuan Li, Yushi Bai, Lei Hou, Juanzi Li

MRC Examples Answerable by BERT without a Question Are Less Effective in MRC Model Training (2020.aacl-srw)

Challenge:	Parallel scaling is a powerful paradigm to enhance reasoning capabilities in large language models.
Approach:	They propose a framework that enables efficient parallel scaling through dynamic pruning.
Outcome:	The proposed framework achieves token reductions of 65.73% to 88.50% compared to consensus sampling while maintaining competitive accuracy within 3.4 percentage points.

Copied to clipboard

Hongyu Li, Tengyang Chen, Shuting Bai, Takehito Utsuro, Yasuhide Kawada

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention (2026.acl-long)

Challenge:	Existing models for Machine Reading Comprehension (MRC) are unable to predict answers from a question and its related context.
Approach:	They propose a method that splits the training examples into those that are “easy to answer” or “hard to answer”.
Outcome:	The proposed model outperforms the previous models on a large-scale English MRC dataset.

Copied to clipboard

Shuochen Chang, Tong Bai, Xiaofeng Zhang, Qianli Ma, Qingyang Liu, Zhaohe Liao, Yibo Miao, Li Niu