Papers by Jie Zhu

Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Challenge:	Recent advances in large language models have revolutionized natural language processing (NLP) there is an urgent need for new benchmarks to keep pace with the development of LLMs.
Approach:	They propose a benchmark to assess the capability of large language models (LLMs) they use a dataset to provide both knowledge assessment and application assessment .
Outcome:	The proposed benchmark provides datasets tailored for knowledge assessment and application assessment.

Copied to clipboard

Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu

Modeling Graph Structure in Transformer for Better AMR-to-Text Generation (D19-1)

Challenge:	Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach:	They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome:	The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.

Copied to clipboard

Jie Zhu, Junhui Li, Muhua Zhu, Longhua Qian, Min Zhang, Guodong Zhou

Semantic Text Processing

Challenge:	Recent studies on AMR-to-text generation formalize the task as a sequence-tosequence learning problem . previous approaches only consider the relations between directly connected concepts while ignoring the rich structure in AMR graphs.
Approach:	They propose a structure-aware self-attention approach to model the relations between indirectly connected concepts in the seq2seq model.
Outcome:	The proposed approach outperforms the state-of-the-art on English AMR benchmarks . it significantly outperformed the state of the art on the benchmarks, with 29.66 and 31.82 BLEU scores .

LaMP-Val: Large Language Models Empower Personalized Valuation in Auction (2025.findings-emnlp)

Copied to clipboard

Jie Sun, Tianyu Zhang, Houcheng Jiang, Kexin Huang, Xiang Shu, Zhibo Zhu, Lintao Ma, Xingyu Lu, Jun Zhou, Junkang Wu, Chi Luo, An Zhang, Jiancan Wu, Xiang Wang

Semantic Text Processing

Challenge:	Currently, most research focuses on the bidding algorithms used within auction mechanisms.
Approach:	They propose a personalized valuation framework that integrates Large Language Models to incorporate personalized semantic preference into users valuation process.
Outcome:	The proposed framework incorporates Large Language Models to incorporate personalized semantic preference into users valuation process.

Adaptive and Representative Multi-Interest Modeling for Recommendation with Large Language Model (2026.findings-acl)

Copied to clipboard

Ziyan Wang, Yingpeng Du, Tianjun Wei, Haoyan Chua, Jieyi Bi, Jie Zhang, Zhu Sun

LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

Challenge:	Existing methods for multi-interest analysis of users rely on heuristic assumptions . however, the granularity of raw generation of LLMs is agnostic, leading to overly fine or coarse interest grouping.
Approach:	They propose an LLM-driven adaptive and representative multi-interest modeling framework that exploits the agnostic granularity of LLMs for multi-interest analysis.
Outcome:	The proposed model outperforms baselines on real-world datasets.

Copied to clipboard

Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun

Challenge:	Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach:	They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome:	The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

Data Efficient RLVR via Off-Policy Influence Guidance (2026.acl-long)

Copied to clipboard

Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang

Green & Sustainable NLP

Challenge:	Existing data selection methods for RLVR are heuristic-based, lacking theoretical guarantees and generalizability.
Approach:	They propose an off-policy influence estimation method that approximates data influence using offline trajectories.
Outcome:	The proposed method reduces the computational cost of policy rollouts and improves storage and computation efficiency.

A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition (2023.findings-acl)

Copied to clipboard

Limao Xiong, Jie Zhou, Qunxi Zhu, Xiao Wang, Yuanbin Wu, Qi Zhang, Tao Gui, Xuanjing Huang, Jin Ma, Ying Shan

Robust Preference Optimization via Dynamic Target Margins (2025.findings-acl)

Challenge:	Existing models for named entity recognition (NER) are based on large-scale labeled datasets, which always obtain using crowdsourcing.
Approach:	They propose a CONfidence-based partial Label Learning method to integrate prior and posterior confidences for crowd-annotated named entity recognition models.
Outcome:	The proposed model improves on real-world and synthetic datasets compared with baselines.

Copied to clipboard

Jie Sun, Junkang Wu, Jiancan Wu, Zhibo Zhu, Xingyu Lu, Jun Zhou, Lintao Ma, Xiang Wang

Responsible & Trustworthy NLP

Challenge:	Direct Preference Optimization (DPO) is an efficient method for ensuring safety and reliability in practical applications.
Approach:	They propose a dynamic target margin preference optimization algorithm that adjusts reward margins at the pairwise level.
Outcome:	The proposed method achieves an average 4.4% improvement over baselines, setting new benchmarks for state-of-the-art performance.

Lifting Optimized Binaries to Canonical Compiler IR via Structure-Aware Retrieval and Iterative Verification (2026.acl-long)

Copied to clipboard

Xiaoao Zhu, Jie Ren, Zhiqiang Li, Jie Zheng, Zhanyong Tang, Zheng Wang

Information Retrieval

Challenge:	Existing methods for decompiling binary code are brittle due to compiler optimizations that distort control-flow and data-flow structure.
Approach:	They propose a system that lifts optimized binaries to canonical compiler intermediate representation (IR) BRIDGE uses control-flow-aware retrieval-augmented generation with feedback-driven verification .
Outcome:	The proposed system outperforms seven baselines on humanEval-Decompile and MBPP, lifting x86-64 and ARM64 binaries to LLVM IR.

Beyond Atomic Characters: Glyph-Aware Sub-character Alignment for Low-Resource Multilingual OCR (2026.acl-long)

Copied to clipboard

Mengxiao Zhu, Haixu Chen, Jiu Sha, Jie Liu, Ge Shi

Visual Data in NLP

Challenge:	Low-resource multilingual OCR models struggle with complex script structures and data scarcity.
Approach:	They propose a framework for multilingual character recognition that integrates visual and linguistic backbones with a novel glyph-aware interface.
Outcome:	The proposed framework improves on high-resolution visual and language backbones with glyph-aware interface.

Let’s Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models (2024.lrec-main)

Copied to clipboard

Shunyu Liu, Jie Zhou, Qunxi Zhu, Qin Chen, Qingchun Bai, Jun Xiao, Liang He

Sentiment Analysis

Challenge:	Empirical evaluations conducted on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.
Approach:	They propose a diffusion model which extracts aspects step by step and learns a denoising process that progressively restores them in a reverse manner.
Outcome:	Empirical evaluations on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.

CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation (2022.acl-long)

Copied to clipboard

Pei Ke, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Xiaoyan Zhu, Minlie Huang

Low-Resource NLP

Challenge:	Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
Approach:	They propose an unsupervised reference-free metric which evaluates controlled text generation from different aspects by formulating each aspect into multiple text infilling tasks.
Outcome:	The proposed metric has higher correlations with human judgments while obtaining better generalization of evaluating generated texts from different models and with different qualities.

Revisiting Interpolation Augmentation for Speech-to-Text Generation (2024.findings-acl)

Copied to clipboard

Chen Xu, Jie Wang, Xiaoqian Liu, Qian Dong, Chunliang Zhang, Tong Xiao, JingBo Zhu, Dapeng Man, Wu Yang

Text Generation

Challenge:	Existing approaches to speech-to-text generation tasks are limited by the lack of extensive labeled datasets.
Approach:	They propose to use interpolation augmentation to construct virtual training samples by transforming inputs and labels to enhance generalization in other domains.
Outcome:	The proposed approach significantly improves performance across diverse tasks, architectures, and data scales, offering a promising avenue for more robust S2T systems in resource-constrained settings.

An Operation Network for Abstractive Sentence Compression (C18-1)

Copied to clipboard

Naitong Yu, Jie Zhang, Minlie Huang, Xiaoyan Zhu

Challenge:	Sentence compression is a natural language generation task that condenses a sentence . Delete-based models remove unimportant words from the source sentence and generate a shorter sentence if the source is not a word deletion problem.
Approach:	They propose a neural network approach for abstractive sentence compression . they model the sentence compression process as an editing procedure .
Outcome:	The proposed approach outperforms state-of-the-art models in the abstractive sentence compression field.

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)

Copied to clipboard

Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu

Reasoning

Challenge:	Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints.
Approach:	They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs.
Outcome:	The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications.

DEER: Descriptive Knowledge Graph for Explaining Entity Relationships (2022.emnlp-main)

Copied to clipboard

Jie Huang, Kerui Zhu, Kevin Chen-Chuan Chang, Jinjun Xiong, Wen-mei Hwu

MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization (2021.naacl-main)

Challenge:	Existing knowledge graphs lack two desired features for modeling entity relationships: openness and informativeness.
Approach:	They propose a self-supervised learning method to extract relation descriptions with the analysis of dependency patterns and generate relation descriptions using a transformer-based relation description synthesizing model.
Outcome:	The proposed system extracts and generates high-quality relation descriptions without human labeling.

Copied to clipboard

Chenguang Zhu, Yang Liu, Jie Mei, Michael Zeng

Dialogue Systems & Conversational Agents

Challenge:	Existing datasets for dialogue summarization are limited to their small sizes and are built from a narrow domain.
Approach:	They propose a large-scale media interview dataset consisting of 463.6K transcripts with abstractive summaries.
Outcome:	The proposed dataset is larger and contains multi-party conversations from multiple domains.

Benchmarking Diverse-Modal Entity Linking with Generative Models (2023.findings-acl)

Copied to clipboard

Sijia Wang, Alexander Hanbo Li, Henghui Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, Jie Ma, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng

Dynamic Model-Bank Test-Time Adaptation for Automatic Speech Recognition (2025.emnlp-main)

Challenge:	Existing models for diverse-mode entity linking (EL) work well on per modality configurations, but it is more challenging to design a unified model for diverse modality.
Approach:	They propose a generative diverse-modal model that integrates text, image and table . they propose combining a multimodal encoder-decoder paradigm with a fine-tuning GDMM .
Outcome:	The proposed model outperforms state-of-the-art models by 8.51 F1 on average for diverse-modal EL.

Copied to clipboard

Yanshuo Wang, Yanghao Zhou, Yukang Lin, Haoxing Chen, Jin Zhang, Wentao Zhu, Jie Hong, Xuesong Li

FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (D19-1)

Challenge:	Existing ASR TTA methods struggle with instability under continual and long-term distribution shifts.
Approach:	They propose a continuous adaptive model-bank framework that adapts to domain shifts in ASR test-time scenarios.
Outcome:	Experiments on diverse, continuously shifting ASR benchmarks show that DMSUTA outperforms existing continual TTA baselines.

Copied to clipboard

Tianyu Gao, Xu Han, Hao Zhu, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

YuLan-Mini: Pushing the Limits of Open Data-efficient Language Model (2025.acl-long)

Challenge:	Few-shot domain adaptation and NOTA detection are two real-world challenges for few-shot relation classification models.
Approach:	They propose a task to investigate two aspects of few-shot relation classification models . they build upon the FewRel dataset by adding a new test set in a different domain .
Outcome:	The proposed task can evaluate few-shot domain adaptation and few- shot none-of-the-above detection on a new domain and NOTA relation choice.

Copied to clipboard

Hu Yiwen, Huatong Song, Jie Chen, Jia Deng, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Zican Dong, Yang Lu, Xu Miao, Xin Zhao, Ji-Rong Wen

MFinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Dataset (2025.findings-acl)

Challenge:	prevailing pre-training approaches for large language models involve several complexities.
Approach:	They propose a low-cost training recipe and a robust optimization approach to mitigate training instability . they also propose synthesis, curriculum, and data selection pipelines to integrate data .
Outcome:	The proposed model achieves top-tier performance among models with similar parameter scale . it is comparable to industry-leading models that require significantly more data .

Copied to clipboard

Jie Zhu, Junhui Li, Yalong Wen, Xiandong Li, Lifan Guo, Feng Chen

Selecting Stickers in Open-Domain Dialogue through Multitask Learning (2022.findings-acl)

Challenge:	Existing financial benchmarks rely on news articles, earnings reports, or announcements, making it challenging to capture the real-world dynamics of financial meetings.
Approach:	They propose a multilingual, multi-sector, and multi-task dataset called MFinMeeting that supports English, Chinese, and Japanese .
Outcome:	The proposed benchmark supports English, Chinese, and Japanese, enhancing comprehension of financial discussions in diverse linguistic contexts.

Copied to clipboard

Zhexin Zhang, Yeshuang Zhu, Zhengcong Fei, Jinchao Zhang, Jie Zhou

Dialogue Systems & Conversational Agents

Challenge:	Existing methods to select appropriate stickers in open-domain dialogues have not been explored.
Approach:	They propose a multitask learning method consisting of three auxiliary tasks to combine multimodal information to enhance the understanding of dialogue history, emotion and semantic meaning of stickers.
Outcome:	The proposed model can combine multimodal information and achieve significantly higher accuracy over strong baselines.

Huatuo-26M, a Large-scale Chinese Medical QA Dataset (2025.findings-naacl)

Copied to clipboard

Xidong Wang, Jianquan Li, Shunian Chen, Yuxuan Zhu, Xiangbo Wu, Zhiyi Zhang, Xiaolong Xu, Junying Chen, Jie Fu, Xiang Wan, Anningzhe Gao, Benyou Wang

Question Answering

Challenge:	Large Language Models are a powerful tool for medical research, but the data is a bottleneck.
Approach:	They propose to use the largest ever medical Question Answering dataset with 26 Million QA pairs as a fine-tuning data for training large language models.
Outcome:	The proposed dataset demonstrates that it can be used to train large language models and improves zero-shot performance on other datasets.

DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept Relationships (2023.acl-long)

Copied to clipboard

Chenzhengyi Liu, Jie Huang, Kerui Zhu, Kevin Chen-Chuan Chang

Reasoning

Challenge:	Existing models that describe concepts in everyday situations are difficult to summarize in a single sentence.
Approach:	They propose DimonGen, which generates sentences describing concept relationships in everyday scenarios.
Outcome:	The proposed model outperforms baseline models in terms of quality and diversity of generated sentences.

Dialogue is Better Than Monologue: Instructing Meidcal LLMs via Strategic Conversations (2026.findings-eacl)

Copied to clipboard

Zijie Liu, Xinyu Zhao, Jie Peng, Jinhao Duan, Zhuangdi Zhu, Qingyu Chen, Kaidi Xu, Xia Hu, Tianlong Chen

Natural Language Interfaces

Challenge:	Existing tuning methods for medical AI models are monologue-based . existing benchmarks are based on licensing exams or research articles .
Approach:	They propose a benchmark to expose limitations of monologue-based tuning for medical AI models . they use a large dialogue dataset to capture stepwise diagnostic reasoning .
Outcome:	The proposed model outperforms monologue-tuned models on a medical question answering task and improves accuracy on standard medical QA benchmarks.

EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction (2022.naacl-main)

Copied to clipboard

Benfeng Xu, Quan Wang, Yajuan Lyu, Yabing Shi, Yong Zhu, Jie Gao, Zhendong Mao

Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Challenge:	Existing studies only explore entity representations, but propose a novel triple perspective for relation extraction.
Approach:	They propose to explicitly introduce relation representation and jointly represent it with entities to identify valid triples.
Outcome:	The proposed method is based on ablations and document-level relation extraction and joint entity and relation extraction.

Copied to clipboard

Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang

Responsible & Trustworthy NLP

Challenge:	Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach:	They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome:	Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.

MIO: A Foundation Model on Multimodal Tokens (2025.emnlp-main)

Copied to clipboard

Zekun Moore Wang, King Zhu, Chunpu Xu, Wangchunshu Zhou, Jiaheng Liu, Yibo Zhang, Jessie Wang, Ning Shi, Siyu Li, Yizhi Li, Haoran Que, Zhaoxiang Zhang, Yuanxing Zhang, Ge Zhang, Ke Xu, Jie Fu, Wenhao Huang

Graph Neural Networks with Generated Parameters for Relation Extraction (P19-1)

Challenge:	Existing models lack multimodal understanding capabilities, resulting in closed-source model that does not support multimodal interleaved sequences.
Approach:	They propose a foundation model built on multimodal tokens capable of understanding and generating speech, text, images, and videos in an end-to-end, autoregressive manner.
Outcome:	The proposed model is able to understand speech, text, images, and videos in an end-to-end, autoregressive manner.

Copied to clipboard

Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-Seng Chua, Maosong Sun

Answer Quality Aware Aggregation for Extractive QA Crowdsourcing (2022.findings-emnlp)

Challenge:	Existing graph neural networks can only process multi-hop relational reasoning on pre-defined graphs and cannot be directly applied in natural language relational reasoning.
Approach:	They propose a graph neural network with generated parameters using natural language sentences as inputs.
Outcome:	The proposed model can process relational reasoning on graphs and in natural language processing tasks.

Copied to clipboard

Peide Zhu, Zhen Wang, Claudia Hauff, Jie Yang, Avishek Anand

Natural Language Interfaces

Challenge:	Existing methods for creating extractive question answering datasets are crowdsourcing, but results are often inconsistent.
Approach:	They propose a method for aggregating answers from different crowd workers that takes into account the relations between the answer, question, and context passage.
Outcome:	The proposed method outperforms baselines by 16% on precision and effectively conduct answer aggregation for extractive question answering task.

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

Abstract then Play: A Skill-centric Reinforcement Learning Framework for Text-based Games (2023.findings-acl)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Anjie Zhu, Peng-Fei Zhang, Yi Zhang, Zi Huang, Jie Shao

Challenge:	Existing reinforcement learning frameworks fail to decompose the task and abstract the action autonomously.
Approach:	They propose a skill-centric reinforcement learning framework capable of abstracting the action in an end-to-end manner.
Outcome:	Empirical experiments on the Jericho environment validate the proposed framework against state-of-the-art baselines.

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Information Retrieval

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

SCAIR: Schema-Conditioned Agentic Iterative Reasoning for Enterprise Knowledge Graphs (2026.acl-industry)

Copied to clipboard

Prateek Chaturvedi, Yuqicheng Zhu, Hongkuan Zhou, Dongzhuoran Zhou, Yunjie He, Steffen Staab, Fei Du, Jie Tang, Evgeny Kharlamov

Structured Data in NLP

Challenge:	Existing agentic approaches for Knowledge Graph-based Retrieval-Augmented Generation fail to generalize to real-world enterprise Knowledge graphs (KGs) dense, schema-driven, and operationally constrained, requiring a training-free framework.
Approach:	They propose a training-free framework that integrates structured planning with controlled iterative reasoning by injecting schema-conditioned structural priors and enforcing schemas during multi-hop reasoning.
Outcome:	The proposed framework significantly improves on a real-world enterprise-oriented benchmark constructed from a Configuration Management DataBase (CMDB).

SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval (2024.findings-acl)

Copied to clipboard

Siwei Wu, Yizhi Li, Kang Zhu, Ge Zhang, Yiming Liang, Kaijing Ma, Chenghao Xiao, Haoran Zhang, Bohao Yang, Wenhu Chen, Wenhao Huang, Noura Al Moubayed, Jie Fu, Chenghua Lin

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

Challenge:	Multi-modal information retrieval (MMIR) is a rapidly evolving field . current benchmarks for image-text pairings overlook the scientific domain .
Approach:	They develop a scientific domain-specific MMIR benchmark to evaluate image-text pairings using open-access research paper corpora.
Outcome:	The proposed benchmarks are based on 530K image-text pairs extracted from scientific documents with detailed captions.

Copied to clipboard

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

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models (2025.acl-long)

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

Siming Huang, Tianhao Cheng, Jason Klein Liu, Weidi Xu, Jiaran Hao, Liuyihan Song, Yang Xu, Jian Yang, Jiaheng Liu, Chenchen Zhang, Linzheng Chai, Ruifeng Yuan, Xianzhen Luo, Qiufeng Wang, YuanTao Fan, Qingfu Zhu, Zhaoxiang Zhang, Yang Gao, Jie Fu, Qian Liu, Houyi Li, Ge Zhang, Yuan Qi, Xu Yinghui, Wei Chu, Zili Wang

GenProve: Learning to Generate Text with Fine-Grained Provenance (2026.acl-long)

Challenge:	Code LLMs lack reproducible data pipelines and training protocols for reproducible advancements in code intelligence.
Approach:	They propose a top-tier code LLM that releases model weights and inference code . reproducible data pipelines, rigorous experimental ablation results and training protocols are included .
Outcome:	The proposed model achieves comparable performance to leading models and serves as an "open cookbook" reproducible training data, rigorous experimental ablation results, and detailed training protocols are also included in the model.

Copied to clipboard

Jingxuan Wei, Xingyue Wang, Yanghaoyu Liao, Jie Dong, Yuchen Liu, Caijun Jia, Bihui Yu, Junnan Zhu

Reasoning

Challenge:	Existing methods for large language models (LLMs) are coarse-grained and fail to distinguish between direct quotes and complex reasoning.
Approach:	They propose a framework that combines supervised fine-tuning and group relative policy optimization to generate fluent answers while simultaneously producing sentence-level provenance triples.
Outcome:	The proposed framework outperforms 14 strong large language models in joint evaluation.

ControversialQA: Exploring Controversy in Question Answering (2024.lrec-main)

Copied to clipboard

Zhen Wang, Peide Zhu, Jie Yang

Question Answering

Challenge:	Existing studies on controversy define it based on vague assumptions of its relation to sentiment . experimental results show controversy detection is essential and challenging .
Approach:	They propose a question-answering dataset that defines content controversy by user perception . they show controversy detection is essential and challenging .
Outcome:	The proposed dataset defines controversy by user perception, i.e., votes from plenty of users.

Toward Fully Exploiting Heterogeneous Corpus:A Decoupled Named Entity Recognition Model with Two-stage Training (2021.findings-acl)

Copied to clipboard

Yun Hu, Yeshuang Zhu, Jinchao Zhang, Changwen Zheng, Jie Zhou

STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (2026.acl-long)

Challenge:	Named Entity Recognition (NER) is a fundamental and widely used task in natural language processing.
Approach:	They propose a decoupled NER model with two-stage training to take advantage of heterogeneous corpus, including dictionaries, distantly supervised instances, and human-annotated instances.
Outcome:	Empirical results show that the proposed model improves against baselines and can be scaled to a large extent.

Copied to clipboard

Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu

An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language Models (2024.findings-acl)

Challenge:	Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence.
Approach:	They propose a hierarchical group-based RL framework that leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a mechanism of trajectory-aware reward and trajectory-independent penalty.
Outcome:	Experiments on ALFWorld, WebShop, and Search-Augmented QA show that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect.

Copied to clipboard

Xiongtao Zhou, Jie He, Yuhua Ke, Guangyao Zhu, Victor Gutierrez Basulto, Jeff Pan