Papers by Yang Ji

CART: A Generative Cross-Modal Retrieval Framework With Coarse-To-Fine Semantic Modeling (2025.acl-long)

Challenge:	Existing multilingual TTS datasets are limited in speech generation fields due to lack of quality data.
Approach:	They propose to use 30,000 hours of high-quality speech data across 3 languages . they filter out low-quality text-text pairs and concatenate short transcripts .
Outcome:	The proposed dataset comprises 30,000 hours of high-quality speech data, across 3 languages with multiple speakers and styles, suitable for various speech tasks such as TTS and ASR.

Copied to clipboard

Minghui Fang, Shengpeng Ji, Jialong Zuo, Hai Huang, Yan Xia, Jieming Zhu, Xize Cheng, Xiaoda Yang, Wenrui Liu, Gang Wang, Zhenhua Dong, Zhou Zhao

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

Challenge:	Cross-modal retrieval tasks are used to retrieve data from one modality or another based on a query from another modality.
Approach:	They propose a generative cross-modal retrieval framework based on coarse-to-fine semantic modeling . they propose combining K-Means and RQ-VAE to discretize multimodal data into token sequences that support autoregressive generation.
Outcome:	The proposed framework achieves excellent performance and efficiency in multimodal retrieval tasks.

Copied to clipboard

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

OCP: Outlier-Centric Probing for Dynamic Structured Pruning of LLMs (2026.acl-long)

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

Copied to clipboard

Yang Ji, Ying Sun

Gaussian Process based Deep Dyna-Q approach for Dialogue Policy Learning (2021.findings-acl)

Challenge:	Existing structured pruning methods fail to identify outlier-triggering tokens and uniform layer-wise sparsity misaligns with heterogeneous outlier distributions.
Approach:	They propose a framework that prioritizes capturing outlier-triggering tokens rather than reconstructing full hidden distributions.
Outcome:	Experiments on LLaMA2, LLama3 and OPT show that the proposed framework outperforms state-of-the-art methods and achieves 25% perplexity reduction at 1.6 speedup.

Copied to clipboard

Guanlin Wu, Wenqi Fang, Ji Wang, Jiang Cao, Weidong Bao, Yang Ping, Xiaomin Zhu, Zheng Wang

Dialogue Systems & Conversational Agents

Challenge:	Reinforcement learning (RL) is the main dialogue policy learning method in recent years.
Approach:	They propose a Gaussian Process based Deep Dyna-Q approach to dialogue policy learning . they propose evaluating the quality of experiences generated by the world model using a discriminator .
Outcome:	The proposed approach improves the effectiveness and efficiency of dialogue policy learning by 20% with fewer human-machine interactions.

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query (2025.emnlp-main)

Copied to clipboard

Yixuan Wang, Shiyu Ji, Yijun Liu, Yuzhuang Xu, Yang Xu, Qingfu Zhu, Wanxiang Che

Challenge:	Existing KV cache eviction methods prune tokens using prefilling-stage attention scores, causing inconsistency with actual inference queries.
Approach:	They propose a lookahead q-cache framework that generates low-cost pseudo lookaheaded queries to better approximate the true decoding-stage queries.
Outcome:	The proposed framework outperforms existing methods on LongBench and Needle-in-a-Haystack benchmarks and can be flexibly combined to yield further improvements.

RAVEN: Robust Advertisement Video Violation Temporal Grounding via Reinforcement Reasoning (2025.acl-industry)

Copied to clipboard

Deyi Ji, Yuekui Yang, Haiyang Wu, Shaoping Ma, Tianrun Chen, Lanyun Zhu

Robustness in NLP

Challenge:	Existing methods for detecting ads video violations lack precise temporal grounding, noisy annotations, and limited generalization.
Approach:	They propose a framework that integrates curriculum reinforcement learning with large language models to enhance reasoning and cognitive capabilities for violation detection.
Outcome:	The proposed framework achieves superior performance in violation category accuracy and temporal interval localization.

Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes (2022.coling-1)

Copied to clipboard

Bin Ji, Shasha Li, Shaoduo Gan, Jie Yu, Jun Ma, Huijun Liu, Jing Yang

AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Challenge:	Existing prototypical networks for named entity recognition suffer from label dependency and tightly distributed prototypes, thus causing misclassifications.
Approach:	They propose an Entity-level Prototypical Network enhanced by dispersedly distributed prototypes to build entity-level prototypes and distribute them dispersionally.
Outcome:	The proposed system outperforms the previous models on two evaluation tasks and the Few-NERD settings in terms of overall performance.

Copied to clipboard

Zhiheng Xi, Dingwen Yang, Jiaqi Liu, Jixuan Huang, Honglin Guo, Baodai Huang, Tinggang Chen, Qi Zhang, Zhonghang Lu, Chenyu Liu, Jiajun Sun, Jiazheng Zhang, Dingwei Zhu, Xin Guo, Junzhe Wang, Zhihao Zhang, Yuming Yang, Junjie Ye, Minghe Gao, Dongrui Liu, Jiaming Ji, Guohao Li, Tao Gui, Qi Zhang, Xuanjing Huang

Towards a Unified Multi-Dimensional Evaluator for Text Generation (2022.emnlp-main)

Challenge:	Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach:	They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome:	Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .

Copied to clipboard

Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, Jiawei Han

Text Generation

Challenge:	Existing evaluation frameworks for natural language generation are dominated by similarity-based metrics.
Approach:	They propose a multi-dimensional evaluator for natural language generation that integrates multiple dimensions into one evaluer.
Outcome:	The proposed evaluator improves on three typical NLG tasks and improves with external knowledge.

Zero-shot Neural Passage Retrieval via Domain-targeted Synthetic Question Generation (2021.eacl-main)

Copied to clipboard

Ji Ma, Ivan Korotkov, Yinfei Yang, Keith Hall, Ryan McDonald

Low-Resource NLP

Challenge:	Recent advances in neural retrieval have led to advancements on document, passage and knowledge-base benchmarks.
Approach:	They propose an approach to zero-shot learning for passage retrieval that uses synthetic question generation to close this gap.
Outcome:	The proposed approach can exceed term-based techniques on document retrieval benchmarks by using domain-targeted synthetic question generation.

Budget-Constrained Tool Learning with Planning (2024.findings-acl)

Copied to clipboard

Yuanhang Zheng, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Few-Shot Multimodal Named Entity Recognition Based on Mutlimodal Causal Intervention Graph (2024.lrec-main)

Challenge:	Existing methods for budget-constrained tool learning have been overlooked . et al., 2023b) compared tool learning with other methods to improve performance .
Approach:	They propose a method for budget-constrained tool learning by creating a preferable plan under the budget constraint before utilizing the tools.
Outcome:	The proposed method reduces the cost of tool learning and reaches competitive Pass Rate.

Copied to clipboard

Feihong Lu, Xiaocui Yang, Qian Li, Qingyun Sun, Ke Jiang, Cheng Ji, Jianxin Li

Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering (2026.acl-long)

Challenge:	Existing methods for multimodal named entity recognition are limited due to limited resources.
Approach:	They propose a Few-shot Multimodal Named Entity Recognition task to address these relation types by constructing a multimodal graph and a new multimodal causal intervention strategy.
Outcome:	The proposed model improves on two multimodal named entity recognition datasets.

Copied to clipboard

Li Zheng, Xin Zhang, Shuyi He, Fei Li, Chong Teng, Jiang-Ming Yang, Donghong Ji, Zhuang Li

ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services (2026.acl-long)

Challenge:	Existing studies on neurons focus on emotion and rhetoric, neglecting their intrinsic connections.
Approach:	They propose a framework for fine-grained steering of emotion and rhetoric in large language models . they propose 'neuro-based' masking method that integrates multi-dimensional screening .
Outcome:	The proposed method achieves directed induction of non-target sentences and enhancement of emotion tasks via rhetoric neurons.

Copied to clipboard

Fengxian Ji, Jingpu Yang, Zirui Song, Lang Gao, Junhong Liang, Zhenhao Chen, Jinghui Zhang, Xiuying Chen

Persona-DB: Efficient Large Language Model Personalization for Response Prediction with Collaborative Data Refinement (2025.coling-main)

Challenge:	Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks.
Approach:	They propose a benchmark that correlates image outputs with economic value in commercial design projects.
Outcome:	ServImage benchmarks show image generation models perform well on academic benchmarks but are uncertain on commercial projects.

Copied to clipboard

Chenkai Sun, Ke Yang, Revanth Gangi Reddy, Yi Fung, Hou Pong Chan, Kevin Small, ChengXiang Zhai, Heng Ji

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training (2026.acl-long)

Challenge:	Existing research has focused on enhancing the retrieval stage and optimizing the representation of the database.
Approach:	They propose a framework to improve generalization across task contexts and collaborative refinement to bridge knowledge gaps among users.
Outcome:	The proposed framework improves generalization across task contexts and collaborative refinement to bridge knowledge gaps among users.

Copied to clipboard

Kailai Yang, Xiao Liu, Lei Ji, Hao Li, Xiao Liang, Zhiwei Liu, Yeyun Gong, Peng Cheng, Mao Yang

Bayesian Example Selection Improves In-Context Learning for Speech, Text and Visual Modalities (2024.emnlp-main)

Challenge:	Existing methods for reweighting data mixtures rely on manual designation with certain heuristics based on intuition or empirical results.
Approach:	They propose a model-based framework that learns to re-weight domains by reinforcement learning on large quantities of data mixing trajectories with corresponding feedback from an evaluation environment.
Outcome:	The proposed framework outperforms baselines in achieving balanced performance across source and target fields and domain spaces without retraining.

Copied to clipboard

Siyin Wang, Chao-Han Yang, Ji Wu, Chao Zhang

Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion (2025.findings-emnlp)

Challenge:	Large language models (LLMs) can adapt to new tasks easily and efficiently in a training-free manner.
Approach:	They propose to use eBayesian in-context example selection method to extend the inference probability conditioned on in-constitut examples based on Bayes’ theorem to select in-strategy examples . Experimental results show the efficacy and robustness of their method on various models, tasks and modalities.
Outcome:	The proposed method is based on the eBayesian in-context example selection approach.

Copied to clipboard

Yujian Liu, Jiabao Ji, Tong Yu, Ryan A. Rossi, Sungchul Kim, Handong Zhao, Ritwik Sinha, Yang Zhang, Shiyu Chang

Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)

Challenge:	Existing methods to integrate external information into a given table neglect the structured nature of the table.
Approach:	They propose a simple yet effective method to integrate external information into a given table by first building an augmenting table and then generating a SQL query over the two tables to answer the question.
Outcome:	The proposed method outperforms strong baselines on three table QA benchmarks.

Copied to clipboard

Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

AudioVSR: Enhancing Video Speech Recognition with Audio Data (2024.emnlp-main)

Challenge:	Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone.
Approach:	They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs.
Outcome:	The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively.

Copied to clipboard

Xiaoda Yang, Xize Cheng, Jiaqi Duan, Hongshun Qiu, Minjie Hong, Minghui Fang, Shengpeng Ji, Jialong Zuo, Zhiqing Hong, Zhimeng Zhang, Tao Jin

Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision (2021.emnlp-main)

Challenge:	Recent work has shown poor performance with non-Indo-European languages . previous work primarily utilizes video information to build VSR models .
Approach:	They propose a generative model for data inflation that integrates synthetic data with authentic visual data to enhance the VSR model.
Outcome:	The proposed model improves on the audio-visual alignment problem in audio-video tasks.

Copied to clipboard

Mieradilijiang Maimaiti, Yang Liu, Yuanhang Zheng, Gang Chen, Kaiyu Huang, Ji Zhang, Huanbo Luan, Maosong Sun

DeepMed: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference (2026.findings-acl)

Challenge:	Recent state-of-the-art (SOTA) effective neural network methods have been used in Chinese word segmentation (CWS) However, the robustness of the previous neural methods is limited by the large-scale annotated corpus.
Approach:	They propose a self-supervised Chinese word segmentation approach with a straightforward and effective architecture.
Outcome:	The proposed approach outperforms previous methods on 9 different CWS datasets with single criterion training and multiple criteria training and achieves better robustness.

Copied to clipboard

Zihan Wang, Hao Wang, Shi Feng, Xiaocui Yang, Daling Wang, Yiqun Zhang, Jinghao Lin, Xiaozhong Ji, Haihua Yang

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (2023.emnlp-main)

Challenge:	Medical reasoning models are constrained by parametric knowledge and can induce hallucinations and spurious attributions.
Approach:	They propose a model that uses a multi-hop med-search QA synthesis method to apply the DR paradigm in medical contexts.
Outcome:	The proposed model outperforms larger medical reasoning models on medical benchmarks.

Copied to clipboard

Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging (2025.acl-long)

Challenge:	Recent advances in large language models (LLMs) have produced models that exhibit remarkable performance across a variety of NLP tasks.
Approach:	They analyze a large-scale collection of user-GPT conversations to identify a significant gap between academic research in NLP and the needs of real-world NLP applications.
Outcome:	The proposed model outperforms existing models in a large-scale collection of user-GPT conversations and identifies a significant gap between the tasks that users frequently request from LLMs and the tasks commonly studied in academic research.

Copied to clipboard

Zichen Tang, Haihong E, Ziyan Ma, Haoyang He, Jiacheng Liu, Zhongjun Yang, Zihua Rong, Rongjin Li, Kun Ji, Qing Huang, Xinyang Hu, Yang Liu, Qianhe Zheng

Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference (2025.naacl-long)

Challenge:	Compared to existing benchmarks, FinanceReasoning provides three key advancements: (1) credibility; (2) comprehensiveness; (3) numerical precision; (4) complexity; (5) complexity; and (6) complexity.
Approach:	They propose a benchmark to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems.
Outcome:	The proposed benchmark exceeds existing benchmarks in 67.8% of financial concepts and formulas and is credible, comprehensive, and challenging.

Copied to clipboard

Zeping Li, Xinlong Yang, Ziheng Gao, Ji Liu, Guanchen Li, Zhuang Liu, Dong Li, Jinzhang Peng, Lu Tian, Emad Barsoum

Machine Translation

Challenge:	Existing methods such as Medusa lack adequate information interaction between different drafting heads.
Approach:	They propose an enhanced speculative decoding framework that builds upon Medusa and integrates a drafting block capable of parallel inference.
Outcome:	The proposed framework outperforms Medusa in terms of head accuracy and latency.

SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning (2026.acl-long)

Copied to clipboard

Lichao Wang, ZhaoXing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai

Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models (2022.findings-acl)

Challenge:	Large Language Model (LLM) agents are expanding their action spaces to operate in complex environments.
Approach:	They propose a server-side defense plugin that constrains tool acquisition via predictive reasoning regarding future safety risks.
Outcome:	Experiments on PowerSeeking Bench, ToolEmu, and AgentHarm show that SafeMCP achieves a safe equilibrium, effectively mitigating risks while preserving agent utility.

Copied to clipboard

Jianmo Ni, Gustavo Hernandez Abrego, Noah Constant, Ji Ma, Keith Hall, Daniel Cer, Yinfei Yang

Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models (2024.emnlp-main)

Challenge:	Sentence embeddings are useful for language processing tasks, but it is unclear how to produce them from encoder-decoder models.
Approach:	They investigate the effects of scaling up sentence encoders to 11B parameters on sentence embeddings from text-to-text transformers (T5) .
Outcome:	The proposed models outperform the previous best models on both SentEval and SentGLUE transfer tasks.

Copied to clipboard

Ji Liu, Jiaxiang Ren, Ruoming Jin, Zijie Zhang, Yang Zhou, Patrick Valduriez, Dejing Dou

LOHRec: Leveraging Order and Hierarchy in Generative Sequential Recommendation (2025.findings-emnlp)

Challenge:	Existing frameworks for learning Large Language Models (LLMs) require adaptive data processing and low-rank adjustment to improve accuracy and fine-tuning speed.
Approach:	They propose a fisher information-based adaptive federated curriculum learning framework with two novel methods to improve FL fine-tuning process.
Outcome:	The proposed framework improves performance and fine-tuning speed compared with baseline approaches.

Copied to clipboard

Jiawen Xie, Haiyang Wu, Deyi Ji, Yuekui Yang, Shaoping Ma

Challenge:	generative recommenders focus on maximizing the prediction probability of the next item in the temporal sequence, ignoring diverse potential items.
Approach:	They propose a learning framework that leverages order and hierarchy in generative recommendation using quantized identifiers to further explore performance ceiling of lightweight generative recommenders.
Outcome:	The proposed learning framework outperforms strong prior baselines across multiple datasets.

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

Copied to clipboard

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

Can Language Models Follow Multiple Turns of Entangled Instructions? (2025.findings-emnlp)

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

Copied to clipboard

Chi Han, Xin Liu, Haodong Wang, Shiyang Li, Jingfeng Yang, Haoming Jiang, Zhengyang Wang, Qingyu Yin, Liang Qiu, Changlong Yu, Yifan Gao, Zheng Li, Bing Yin, Jingbo Shang, Heng Ji

Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce (P18-2)

Challenge:	Despite of significant achievements in improving instruction-following capabilities of large language models, the ability to process multiple potentially entangled or conflicting instructions remains a considerable challenge.
Approach:	They construct multi-turn instruction with 1.1K high-quality multi-turned conversations using the human-in-the-loop approach and examine their capabilities.
Outcome:	The proposed model shows that it is difficult to integrate multiple turns and balance competing objectives when instructions intersect or conflict.

Copied to clipboard

Minghui Qiu, Liu Yang, Feng Ji, Wei Zhou, Jun Huang, Haiqing Chen, Bruce Croft, Wei Lin

Natural Language Interfaces

Challenge:	Recent researches focus on deep learning and reinforcement learning for multi-turn information seeking conversation systems.
Approach:	They propose an efficient and effective multi-turn conversation model based on convolutional neural networks and extend it to adapt the knowledge learned from a resource-rich domain to enhance the performance.
Outcome:	The proposed model performs better than the existing model on an industrial chatbot called AliMe Assist.

RAVEN++: Pinpointing Fine-Grained Violations in Advertisement Videos with Active Reinforcement Reasoning (2025.emnlp-industry)

Copied to clipboard

Deyi Ji, Yuekui Yang, Liqun Liu, Peng Shu, Haiyang Wu, Shaogang Tang, Xudong Chen, Shaoping Ma, Tianrun Chen, Lanyun Zhu

AnyTrans: Translate AnyText in the Image with Large Scale Models (2024.findings-emnlp)

Challenge:	Recent advances in large language models have improved the detection of non-compliant content, but critical gaps persist in fine-grained understanding, explainability, and generalization.
Approach:	They propose a framework that combines active reinforcement learning, fine-grained violation understanding and progressive multi-stage training.
Outcome:	The proposed framework outperforms general-purpose LLMs and specialized models in fine-grained violation understanding, explainability, and generalization.

Copied to clipboard

Zhipeng Qian, Pei Zhang, Baosong Yang, Kai Fan, Yiwei Ma, Derek Wong, Xiaoshuai Sun, Rongrong Ji

Multilinguality

Challenge:	Recent advances in natural language processing and computer vision have made it possible to translate images with text in one language into equivalent images displaying that text translated into another language.
Approach:	They propose an all-encompassing framework for the task–In-Image Machine Translation (IIMT) that incorporates contextual cues from both textual and visual elements during translation.
Outcome:	The proposed framework can be constructed using open-source models and requires no training, making it highly accessible and expandable.

Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization (2024.findings-emnlp)

Copied to clipboard

Yixin Ji, Yang Xiang, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Kehai Chen, Min Zhang

When Is Thinking Enough? Early Exit via Sufficiency Assessment for Efficient Reasoning (2026.acl-long)

Challenge:	Large language models require a balance between efficiency and performance.
Approach:	They propose a low-rank compression technique that reduces non-essential parameters by decomposing weight matrices into products of two low-ranked matrici.
Outcome:	The proposed method outperforms existing pruning and low-rank compression techniques in maintaining model performance at the same compression ratio.

Copied to clipboard

Yang Xiang, Yixin Ji, Ruotao Xu, Dan Qiao, Zheming Yang, Juntao Li, Min Zhang

Skeletons Matter: Dynamic Data Augmentation for Text-to-Query (2025.emnlp-main)

Challenge:	Existing approaches to early exit reasoning often rely on handcrafted or empirical indicators that are unreliable and impractical.
Approach:	They propose a framework that allows LRMs to assess the sufficiency of its chain-of-thought and determine the optimal point for early exit.
Outcome:	The proposed framework reduces reasoning length by 28.9%–34.9% with minimal performance loss, effectively mitigating overthinking.

Copied to clipboard

Yuchen Ji, Bo Xu, Jie Shi, Jiaqing Liang, Deqing Yang, Yu Mao, Hai Chen, Yanghua Xiao

Semantic Parsing

Challenge:	Existing studies focus on a single query language, resulting in limited generalizability . a new task paradigm is proposed to unify semantic parsing tasks across different query languages .
Approach:	They propose a task paradigm that unifies parsing tasks across query languages . they identify query skeletons as a shared optimization target of Text-to-Query tasks .
Outcome:	The proposed method achieves state-of-the-art performance using only a small amount of synthesized data.

SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation (2026.findings-acl)

Copied to clipboard

Chengyi Yang, Pengzhen Li, Jiayin Qi, Aimin Zhou, Ji Wu, Ji Liu

Dual-Reasoner: Bridging Interleaved Atomicity and Streaming Latency via Thinking-while-Talking (2026.findings-acl)

Challenge:	Text-to-Video (T2V) generation is a challenge under complex scenarios.
Approach:	They propose a scenario-aware and self-correcting multi-agent prompt refinement framework for T2V prompting.
Outcome:	The proposed framework improves text-to-video alignment and overall generation quality under complex scenarios.

Copied to clipboard

Yangzhuo Li, Shengpeng Ji, Yifu Chen, Tianle Liang, Haoyu Yang, null Junboli, Jun Fang, Lin Li, Qingyang Hong

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

Challenge:	Existing methods to integrate Chain-of-Thought into spoken dialogue models incur prohibitive latency.
Approach:	They propose a Streaming Masking Mechanism to ensure uninterrupted audio streaming . they use a quadruple-constraint system to reconstruct logical atomicity .
Outcome:	Experimental results show that Dual-Reasoner improves speech generation performance with low latency.

Copied to clipboard

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

MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering (2021.findings-emnlp)

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

Copied to clipboard

Junjie Wang, Yatai Ji, Jiaqi Sun, Yujiu Yang, Tetsuya Sakai

SafeMT: Multi-turn Safety for Multimodal Language Models (2026.acl-long)

Challenge:	Existing bilinear methods focus on inter-modality information between images and questions . existing models focus on the interaction between images, questions, and images .
Approach:	They propose a trilinear interaction framework that incorporates attention mechanisms for capturing inter-modality and intra-modal relationships.
Outcome:	The proposed model outperforms bilinear models on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperformed baselines on the VQA, TDIUC and GQA datasets.

Copied to clipboard

Han Zhu, Juntao Dai, Jiaming Ji, Haoran Li, Chengkun Cai, Pengcheng Wen, Chi-Min Chan, Boyuan Chen, Yaodong Yang, Sirui Han, Yike Guo

Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA (2025.findings-acl)

Challenge:	Multi-turn dialogues pose a greater risk than single prompts, but existing safety benchmarks do not account for this situation.
Approach:	They propose a benchmark that features dialogues of varying lengths generated from harmful queries accompanied by images.
Outcome:	The proposed model reduces multi-turn Attack Success Rate (ASR) compared to existing guard models.

Copied to clipboard

Chi-Min Chan, Chunpu Xu, Junqi Zhu, Jiaming Ji, Donghai Hong, Pengcheng Wen, Chunyang Jiang, Zhen Ye, Yaodong Yang, Wei Xue, Sirui Han, Yike Guo

Question Answering

Challenge:	Experimental results show that our approach can effectively improve the performance of both the policy model and the reward model.
Approach:	They propose to use Monte Carlo Tree Search for both policy model improvement and reward model improvement to bridge it to more subtle open-domain question answering.
Outcome:	The proposed approach surpasses existing methods for annotation and training data with fewer data points and achieves better performance in test-time scaling strategies.

LaMemo: Language Modeling with Look-Ahead Memory (2022.naacl-main)

Copied to clipboard

Haozhe Ji, Rongsheng Zhang, Zhenyu Yang, Zhipeng Hu, Minlie Huang

Non-Autoregressive Sentence Ordering (2023.findings-emnlp)

Challenge:	Existing approaches to model long-term dependencies are limited to long texts with thousands of words.
Approach:	They propose a look-ahead memory that augments the recurrence memory by attending to the right-side tokens and interpolating with the old memory states to maintain long-term information in the history.
Outcome:	Experiments on widely used language modeling benchmarks show that LaMemo outperforms baseline models with recurrence memory.

Copied to clipboard

Yi Bin, Wenhao Shi, Bin Ji, Jipeng Zhang, Yujuan Ding, Yang Yang

RAV: Retrieval-Augmented Voting for Tactile Descriptions Without Training (2025.emnlp-main)

Challenge:	Existing sentence ordering approaches only leverage unilateral dependencies during decoding and cannot fully explore the semantic dependency between sentences.
Approach:	They propose a non-autoregressive ordering network that explores bilateral dependencies between sentences and predicts sentences for each position in parallel.
Outcome:	The proposed model outperforms existing autoregressive sentence ordering approaches and yields competitive performance compared with the state-of-the-arts.

Copied to clipboard

Jinlin Wang, Yulong Ji, Hongyu Yang

Enhancing LLM-Based Persuasion Simulations with Cultural and Speaker-Specific Information (2025.findings-emnlp)

Challenge:	Conventional approaches relying on extensive parameter learning for multimodal perception are rigid and computationally inefficient.
Approach:	They propose a parameter-free method that constructs visual-tactile cross-modal knowledge directly by retrieving similar visual-touch data for given visual and tactile inputs and generating tactile descriptions through a voting mechanism.
Outcome:	The proposed method achieves comparable performance to large-scale cross-modal models without training across a wide range of datasets.

Copied to clipboard

Weicheng Ma, Hefan Zhang, Shiyu Ji, Farnoosh Hashemi, Qichao Wang, Ivory Yang, Joice Chen, Juanwen Pan, Michael Macy, Saeed Hassanpour, Soroush Vosoughi

Dialogue Systems & Conversational Agents

Challenge:	Existing approaches to persuasive dialogue generation suffer from stance oscillation and low informativeness.
Approach:	They propose reinforced instructional prompting, a method that ensures speaker characteristics consistently guide all stages of dialogue generation.
Outcome:	The proposed method ensures speaker characteristics guide all stages of dialogue generation and aligns language use with speakers’ native languages to better capture cultural nuances.

PUPPET: Neural-Symbolic Standardized Patients for Mental Health (2026.acl-long)

Copied to clipboard

Chen Xu, Yu ji, Zhenyu Lv, Yang Yi, Yizhe Yang, Luyao Ji, Chaoyi Chen, Xianyang Wang, Tian Lan, Zhihua Wang, Juan Wang, Xunde Dong, Fuze Tian, Qunxi Dong, Bin Hu

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing (2024.naacl-short)

Challenge:	Existing LLM-based training approaches lack faithful responses to clinical errors and explainable feedback.
Approach:	They propose a neural-symbolic virtual standardized patient governed by an OBSERVE-THINK-BEHAVE architecture that embeds LLM reasoning into a symbolic system where experts implant causal associations between intervention logic and patient mental states.
Outcome:	The proposed model outperforms baselines in faithfulness and pedagogical value.

Copied to clipboard

Jiabao Ji, Bairu Hou, Zhen Zhang, Guanhua Zhang, Wenqi Fan, Qing Li, Yang Zhang, Gaowen Liu, Sijia Liu, Shiyu Chang

Robustness in NLP

Challenge:	Existing adversarial attacks can cause LLMs to make wrong predictions on downstream tasks or generate harmful content misaligned with human values.
Approach:	They propose to use randomized smoothing to add noise to the input and then make predictions based on these denoised versions.
Outcome:	The proposed method surpasses existing methods in both empirical and certified robustness in defending against adversarial perturbations for both downstream tasks and human alignments (i.e., jailbreak attacks).

A Game-Theoretica Negotiation Framework for Cross-Cultural Consensus (2026.acl-long)

Copied to clipboard

Guoxi Zhang, Jiawei Chen, Tianzhuo Yang, Jiaming Ji, Yaodong Yang, Juntao Dai

Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching (2025.acl-long)

Challenge:	Large language models exhibit pronounced WEIRD cultural bias, marginalizing diverse viewpoints and posing challenges for reconciling diverse populations with varying cultural backgrounds and value systems.
Approach:	They propose a framework for cross-cultural fairness using a Nash Equilibrium . they propose equilibriums that iteratively propose and refine natural-language guidelines .
Outcome:	The proposed framework generates higher-quality and more balanced consensus . it finetunes diverse LLM architectures with negotiation data, reducing cultural distances by 95.53%.

Copied to clipboard

Jialong Zuo, Shengpeng Ji, Minghui Fang, Mingze Li, Ziyue Jiang, Xize Cheng, Xiaoda Yang, Chen Feiyang, Xinyu Duan, Zhou Zhao

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation (2026.acl-long)

Challenge:	Existing methods focus on disentangling speakers and content, while others focus on preserving the source's prosody.
Approach:	They propose a rhythm-controllable and efficient zero-shot voice conversion model that transforms the source speaker’s timbre into an unseen one while retaining speech content.
Outcome:	The proposed model adapts the linguistic content duration to the desired speaking style, facilitating the transfer of the target speaker’s rhythm.

Copied to clipboard

Huawei Zheng, Xinqi Jiang, Sen Yang, Shouling Ji, Yingcai Wu, Dazhen Deng

GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them? (2025.emnlp-main)

Challenge:	Domain-specific datasets of harmful prompts are scarce and often rely on manual construction. Existing efforts to improve domain knowledge and reduce harmful prompt generation are lacking.
Approach:	They propose a framework that transforms domain knowledge into actionable constraints and increases the implicitness of generated harmful prompts.
Outcome:	The proposed framework yields high-quality datasets combining strong domain relevance with implicitness, enabling more realistic red-teaming and advancing LLM safety research.

Copied to clipboard

Yiyang Zhou, Linjie Li, Shi Qiu, Zhengyuan Yang, Yuyang Zhao, Siwei Han, Yangfan He, Kangqi Li, Haonian Ji, Zihao Zhao, Haibo Tong, Lijuan Wang, Huaxiu Yao

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

Challenge:	Existing video benchmarks often resemble image-based questions with scans of only a few key frames, without deep temporal reasoning.
Approach:	They propose a video benchmark to assess whether large vision-language models can genuinely think with videos rather than perform superficial frame-level analysis.
Outcome:	The proposed benchmark consists of 3,269 videos and over 4,342 highly visual-centric questions across 11 categories, including Trajectory Analysis, Temporal Reasoning, and Forensics Detection.

Copied to clipboard

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

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

Error Analysis of Uyghur Name Tagging: Language-specific Techniques and Remaining Challenges (L18-1)

Copied to clipboard

Halidanmu Abudukelimu, Abudoukelimu Abulizi, Boliang Zhang, Xiaoman Pan, Di Lu, Heng Ji, Yang Liu

Syntactic Text Processing

Challenge:	despite efforts at name tagging, there is limited understanding on the performance ceiling . despite the high-resource language, there are very few natural language processing tools available .
Approach:	They propose to use a machine learning model to identify Uyghur name tagger errors . they conclude that such a model is unlikely to be effective for Uygur, or low-resource languages .
Outcome:	The proposed model is unlikely to be effective for Uyghur, or low-resource languages in general, the authors argue . they show that the proposed model can be used for high-res languages with superficial features .

UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents (2026.acl-long)

Copied to clipboard

Yifan Ji, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Qian Zhang, Zhibo Yang, Junyang Lin, Yu Gu, Ge Yu, Maosong Sun

Information Extraction & Text Mining

Challenge:	Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images.
Approach:	They propose a benchmark to evaluate the performance of Large Multimodal Models (LMMs) using a constrained-category KIE track and an open-categorical KIE Track.
Outcome:	Experiments on 15 state-of-the-art LMMs show performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios.

Towards Interpretable Mental Health Analysis with Large Language Models (2023.emnlp-main)

Copied to clipboard

Kailai Yang, Shaoxiong Ji, Tianlin Zhang, Qianqian Xie, Ziyan Kuang, Sophia Ananiadou

MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding (2026.acl-long)

Challenge:	Existing studies on large language models lack adequate evaluations and prompting strategies for explainability.
Approach:	They evaluate the mental health analysis and emotional reasoning ability of large language models (LLMs) using 11 datasets across 5 tasks.
Outcome:	The proposed model shows strong in-context learning ability but still has a significant gap with advanced task-specific methods.

Copied to clipboard

Fuwen Luo, Shengfeng Lou, Chi Chen, Ziyue Wang, Chenliang Li, Weizhou Shen, Jiyue Guo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu

Visual Data in NLP

Challenge:	Existing methods for MLLMs struggle with fine-grained temporal reasoning . despite advances in video understanding, current methods struggle with time-sensitive tasks .
Approach:	They propose a time-stamp-aware multi-segment grounding method that enhances temporal understanding by introducing timestamps.
Outcome:	The proposed method outperforms existing methods on time-sensitive tasks and generalizes well across diverse temporal understanding scenarios.

FineState-Bench: Benchmarking State-Conditioned Grounding for Fine-grained GUI State Setting (2026.findings-acl)

Copied to clipboard

Fengxian Ji, Jingpu Yang, Zirui Song, Yuanxi Wang, Zhexuan Cui, Yuke Li, Qian Jiang, Xiuying Chen

Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization (2023.emnlp-main)

Challenge:	FineState-Bench evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Approach:	They propose a benchmark that evaluates whether an agent can correctly ground an instruction to the intended UI control and reach the exact target state.
Outcome:	The proposed benchmark evaluates whether an agent can ground an instruction to the intended UI control and reach the exact target state.

Copied to clipboard

Tianshi Che, Ji Liu, Yang Zhou, Jiaxiang Ren, Jiwen Zhou, Victor Sheng, Huaiyu Dai, Dejing Dou

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

Challenge:	Prompt tuning of Large Language Models (LLMs) can incur performance degradation or low training efficiency.
Approach:	They propose a prompt tuning approach with Adaptive Optimization to enable efficient FL of LLMs.
Outcome:	The proposed approach improves performance and efficiency simultaneously and addresses client drift problems on both the device and server sides.

Copied to clipboard

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

Unsupervised Sounding Pixel Learning (2023.emnlp-main)

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

Copied to clipboard

Yining Zhang, Yanli Ji, Yang Yang

Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification (D19-1)

Challenge:	Sounding source localization is a challenging task due to the difficulty of cross-modal alignment.
Approach:	They propose an unsupervised method which enables pixel-level sounding source localization in unsupervised paradigm.
Outcome:	The proposed method achieves pixel-level sounding source localization without annotations.

Copied to clipboard

Hu Linmei, Tianchi Yang, Chuan Shi, Houye Ji, Xiaoli Li

Information Extraction & Text Mining

Challenge:	Existing studies on short text classification focus on long texts and achieve unsatisfactory performance due to the sparsity and limited labeled data.
Approach:	They propose a heterogeneous graph neural network based method for semi-supervised short text classification that leverages the full advantage of few labeled data and large unlabeled data through information propagation along the graph.
Outcome:	The proposed method outperforms state-of-the-art methods across six benchmark datasets significantly.

Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations (2021.findings-emnlp)

Copied to clipboard

Yunhe Xie, Kailai Yang, Chengjie Sun, Bingquan Liu, Zhenzhou Ji

Sentiment Analysis

Challenge:	Emotion Recognition in Conversation models neglect direct utterance-knowledge interaction and use emotion-indirect auxiliary tasks to augment semantic information.
Approach:	They propose a Knowledge-Interactive Network with sentiment polarity intensity-aware multi-task learning which leverages both commonsense knowledge and sentiment lexicon to augment semantic information.
Outcome:	The proposed model shows 1.04% performance improvement over the state-of-the-art model on the IEMOCAP dataset.

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

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

Submodular-based In-context Example Selection for LLMs-based Machine Translation (2024.lrec-main)

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

Baijun Ji, Xiangyu Duan, Zhenyu Qiu, Tong Zhang, Junhui Li, Hao Yang, Min Zhang

Machine Translation

Challenge:	Prior studies have focused on the role of well-chosen examples in in-context learning .
Approach:	They propose to use multiple translational factors for in-context example selection by using monotone submodular function maximization.
Outcome:	The proposed approach outperforms random selection and robust single-factor baselines across various NLP tasks.

Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences (2022.naacl-main)

Copied to clipboard

Yifan Chen, Qi Zeng, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang

OpenMSD: Towards Multilingual Scientific Documents Similarity Measurement (2024.lrec-main)

Challenge:	Existing models for long sequences are not efficient due to the quadratic space and time complexity of the self-attention modules.
Approach:	They propose to reduce the quadratic complexity to linear (modulo logarithmic factors) by low-dimensional projection and row selection.
Outcome:	The proposed methods outperform transformer-based models with smaller time/space footprint on the Long Range Arena benchmark.

Copied to clipboard

Yang Gao, Ji Ma, Ivan Korotkov, Keith Hall, Dana Alon, Donald Metzler

Multilinguality

Challenge:	Existing methods for finding related papers in different languages are not effective for multilingual SDSM.
Approach:	They propose to use Open-access Multilingual Scientific Documents to develop multilingual SDSM models that adjust and extend state-of-the-art methods for English SDSM tasks.
Outcome:	The proposed model outperforms baseline methods on multilingual SDSM tasks while preserving the performance of the existing methods.

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

Copied to clipboard

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

Low-Resource NLP

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

Applying Contrastive Learning to Code Vulnerability Type Classification (2024.emnlp-main)

Copied to clipboard

Chen Ji, Su Yang, Hongyu Sun, Yuqing Zhang

PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)

Challenge:	Recent approaches to classification of vulnerabilities ignore their relationships and treat each class in isolation, resulting in non-scalable code vector representations.
Approach:	They propose a hierarchical contrastive learning framework to bring vector representations of related CWEs closer together and use max-pooling to enable the model to handle longer vulnerability code inputs.
Outcome:	The proposed framework outperforms state-of-the-art methods by 2.97%-17.90% on accuracy and 0.98%-22.27% on weighted-F1 with even better performance on higher-quality datasets.

Copied to clipboard

Jiaming Ji, Donghai Hong, Borong Zhang, Boyuan Chen, Josef Dai, Boren Zheng, Tianyi Alex Qiu, Jiayi Zhou, Kaile Wang, Boxun Li, Sirui Han, Yike Guo, Yaodong Yang

Challenge:	Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours.
Approach:	They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs .
Outcome:	The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models.

Incorporating Argument-Level Interactions for Persuasion Comments Evaluation using Co-attention Model (C18-1)

Copied to clipboard

Lu Ji, Zhongyu Wei, Xiangkun Hu, Yang Liu, Qi Zhang, Xuanjing Huang

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs (2026.findings-acl)

Challenge:	Existing research explores different text features of reply comments on word level and ignores interactions between participants.
Approach:	They propose a co-attention mechanism based neural network to capture interactions between participants on argument level to better model dialogical argumentation.
Outcome:	The proposed model outperforms state-of-the-art methods on a publicly available dataset showing that it extracts interactive argument pairs from the original post and the reply.

Copied to clipboard

Yang Luo, Liu Xinran, TianTian Ji, Zhiyi Yin, Lingyun Peng, Shuyu Li

Robustness in NLP

Challenge:	Prior work focused on typographic and pixel-level perturbations, leaving the study of SCO unexplored.
Approach:	They propose a framework that exploits MLLMs' diagrammatic reasoning capabilities to bypass safety guardrails.
Outcome:	The proposed framework exploits the model's reasoning capabilities to bypass safety guardrails.

Simple and Effective Text Matching with Richer Alignment Features (P19-1)

Copied to clipboard

Runqi Yang, Jianhai Zhang, Xing Gao, Feng Ji, Haiqing Chen

Challenge:	Existing models only use a single inter-sequence alignment layer to make full use of this process.
Approach:	They propose to keep three key features available for inter-sequence alignment . they conduct experiments on four well-studied benchmark datasets .
Outcome:	The proposed model is able to perform on four well-studied datasets with fewer parameters and the inference speed is at least 6 times faster than similar models.

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)

Copied to clipboard

Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu

SafeLawBench: Towards Safe Alignment of Large Language Models (2025.findings-acl)

Challenge:	Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering.
Approach:	They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow.
Outcome:	The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow.

Copied to clipboard

Chuxue Cao, Han Zhu, Jiaming Ji, Qichao Sun, Zhenghao Zhu, Wu Yinyu, Josef Dai, Yaodong Yang, Sirui Han, Yike Guo

When Slower Isn’t Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning (2026.findings-acl)

Challenge:	Recent studies indicate that large language models (LLMs) may exhibit risks, including threats to the protection of private data and the generation of hallucinations.
Approach:	They propose to evaluate LLMs from a legal perspective using the SafeLawBench benchmark.
Outcome:	The proposed framework categorizes safety risks into three levels based on legal standards and includes 24,860 multi-choice questions and 1,106 open-domain question-answering tasks.

Copied to clipboard

Sitong Fang, Wenjing Cao, Jiahao Li, Xuyao Wang, Chi-Min Chan, Sirui Han, Juntao Dai, Yike Guo, Yaodong Yang, Jiaming Ji

Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning (2026.acl-long)

Challenge:	a study of slow reasoning models for multimodal reasoning finds that they are more prone to fabricating plausible yet false details when confronted with incomplete or misleading visual inputs.
Approach:	They conduct the first systematic study of the inverse scaling law in slow-thinking paradigms for multimodal reasoning.
Outcome:	The findings suggest that slower reasoning models are more prone to fabricating false details . the study analyzed 5,000-sample hierarchical prompt dataset by 50 participants .

Copied to clipboard

Junpeng Ding, Zichen Tang, Haihong E, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun, Yang Xu, Yichen Liu, Haocheng Gao, Zijie Xi, Ruomeng Jiang, Peizhi Zhao, Rongjin Li, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Jintong Chen, Siying Lin

InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training (2025.acl-long)

Challenge:	Xu and Peng, 2025) . . SPUR is a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images.
Approach:	They propose to use 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images to evaluate the visual perception of multimodal large language models (MLLMs) . they also propose to utilize cross-panel relation understanding to evaluate MLLM’s ability to decipher intricate cross-panel relations.
Outcome:	The proposed model is based on 4,264 question-answering pairs derived from 1,084 expert-curated images.

Copied to clipboard

Dingdong Wang, Jin Xu, Ruihang Chu, Zhifang Guo, Xiong Wang, Jincenzi Wu, Dongchao Yang, Shengpeng Ji, Junyang Lin

Language Models Resist Alignment: Evidence From Data Compression (2025.acl-long)

Challenge:	Recent advances in speech large language models exhibit suboptimal performance in adhering to speech instructions.
Approach:	They propose a method to pre-train large-scale unsupervised speech-text sequences . they use text-to-speech conversion to generate textual continuations corresponding to provided speech segments .
Outcome:	The proposed model achieves superior or competitive results across diverse speech processing tasks.

Copied to clipboard

Jiaming Ji, Kaile Wang, Tianyi Alex Qiu, Boyuan Chen, Jiayi Zhou, Changye Li, Hantao Lou, Josef Dai, Yunhuai Liu, Yaodong Yang

Communication Makes Perfect: Persuasion Dataset Construction via Multi-LLM Communication (2025.naacl-long)

Challenge:	Large language models (LLMs) may exhibit undesirable behaviors due to the inevitable biases and harmful content present in training.
Approach:	They propose to investigate the elasticity of large language models by examining their performance.
Outcome:	The proposed model performance declines rapidly before reverting to the pre-training distribution, the authors show . the proposed model weight and code are available at pku-lm-res ist-alignment.github.io.

Copied to clipboard

Weicheng Ma, Hefan Zhang, Ivory Yang, Shiyu Ji, Joice Chen, Farnoosh Hashemi, Shubham Mohole, Ethan Gearey, Michael Macy, Saeed Hassanpour, Soroush Vosoughi

Challenge:	Large Language Models (LLMs) have shown proficiency in generating persuasive dialogue, yet concerns about the fluency and sophistication of their outputs persist.
Approach:	They propose a multi-LLM communication framework that facilitates the efficient production of high-quality, diverse linguistic content with minimal human oversight.
Outcome:	The proposed framework excels in naturalness, linguistic diversity, and the strategic use of persuasion, even in complex scenarios involving social taboos.

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

Copied to clipboard

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

Improving Span Representation by Efficient Span-Level Attention (2023.findings-emnlp)

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

Copied to clipboard

Pengyu Ji, Songlin Yang, Kewei Tu

Benchmarking Multi-National Value Alignment for Large Language Models (2025.findings-acl)

Challenge:	Existing methods for generating high-quality span representations are limited by subset of tokens . span-span interactions should play an important role in span encoding, authors argue .
Approach:	They propose to introduce span-span interactions and more comprehensive span-token interactions to improve span representations.
Outcome:	The proposed model outperforms baseline models on span-related tasks and shows superior performance.

Copied to clipboard

Chengyi Ju, Weijie Shi, Chengzhong Liu, Jiaming Ji, Jipeng Zhang, Ruiyuan Zhang, Jiajie Xu, Yaodong Yang, Sirui Han, Yike Guo

Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoning (2025.findings-acl)

Challenge:	Existing studies on large language models focus on ethical reviews, failing to capture the diversity of national values.
Approach:	They propose a national value extraction pipeline to efficiently construct value assessment datasets and a model-based model with instruction tagging to process raw data sources.
Outcome:	The proposed benchmark evaluates the alignment of LLMs with the values of five major nations: China, the United States, the UK, France, and Germany.

Copied to clipboard

Haoyu Han, Yaochen Xie, Hui Liu, Xianfeng Tang, Sreyashi Nag, William Headden, Yang Li, Chen Luo, Shuiwang Ji, Qi He, Jiliang Tang

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

Challenge:	Large language models (LLMs) have demonstrated remarkable success across a wide range of tasks, however, they still face challenges in reasoning tasks that require understanding and inferring relationships between distinct pieces of information within text sequences.
Approach:	They propose to construct explicit graphs from context and leverage them to enhance LLM reasoning performance on reasoning tasks.
Outcome:	Extensive experiments show that the proposed method improves both logical reasoning and multi-hop question answering tasks.

Copied to clipboard

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

Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbations (2025.findings-emnlp)

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

Copied to clipboard

Shuo Li, Jiajun Sun, Guodong Zheng, Xiaoran Fan, Yujiong Shen, Yi Lu, Zhiheng Xi, Yuming Yang, Wenming Tan, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs (2022.naacl-main)

Challenge:	Multimodal large language models have demonstrated remarkable performance in visual-language tasks, but their authenticity is often compromised by object hallucinations.
Approach:	They propose a multi-frequency perturbation method that leverages both low-frequency and high-frequency features of images to perturb visual feature representations and explicitly suppress redundant frequency-domain features during inference.
Outcome:	The proposed method significantly mitigates object hallucinations across various model architectures.

Copied to clipboard

Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur

Structured Data in NLP

Challenge:	Existing conversation models treat knowledge selection as a sentence ranking problem where each sentence is handled individually, ignoring the internal semantic connection between sentences.
Approach:	They propose to automatically convert background knowledge documents into document semantic graphs and perform knowledge selection over such graphs.
Outcome:	The proposed model improves on the knowledge selection task and the response generation task on HollE and generalizes on unseen topics in WoW.

TOI-CNN: a Solution of Information Extraction on Chinese Insurance Policy (N19-2)

Copied to clipboard

Lin Sun, Kai Zhang, Fule Ji, Zhenhua Yang

Information Extraction & Text Mining

Challenge:	Existing methods for Element Tagging on insurance policies can be used to streamline manual review of hundreds of contracts.
Approach:	They propose a text-of-interest convolutional neural network (TOI-CNN) to replace traditional pooling layer for processing nested phrasal or clausal elements in insurance policies.
Outcome:	The proposed method can automatically convert a massive amount of insurance policies into structural archives for management and comparison.

Voice Query Auto Completion (2021.emnlp-main)

Copied to clipboard

Raphael Tang, Karun Kumar, Kendra Chalkley, Ji Xin, Liming Zhang, Wenyan Li, Gefei Yang, Yajie Mao, Junho Shin, Geoffrey Craig Murray, Jimmy Lin

FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation (2025.acl-long)

Challenge:	Existing methods fail to complete voice queries from incomplete prefixes because they use orthographic prefix and substrings instead of the true phonetic prefix.
Approach:	They propose to condition QAC approaches on intermediate transcriptions to complete voice queries.
Outcome:	The proposed method obtains an 18% relative improvement over previous methods on a speech-enabled smart television with real-life voice search traffic.

Copied to clipboard

Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo

Toward Annotator Group Bias in Crowdsourcing (2022.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years, but there is a notable lack of effective and specialized multimodal evaluation datasets in the financial domain.
Approach:	They introduce FinMME, a multimodal large language model with 11,000 financial research samples and 20 annotators.
Outcome:	The proposed model performs better than state-of-the-art models, highlighting its challenging nature.

Copied to clipboard

Haochen Liu, Joseph Thekinen, Sinem Mollaoglu, Da Tang, Ji Yang, Youlong Cheng, Hui Liu, Jiliang Tang