Papers by Qi Zhu

Multi-turn Response Selection using Dialogue Dependency Relations (2020.emnlp-main)

Challenge:	Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent.
Approach:	They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt.
Outcome:	The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments.

Copied to clipboard

Qi Jia, Yizhu Liu, Siyu Ren, Kenny Zhu, Haifeng Tang

CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending (2024.acl-long)

Challenge:	Existing models for multi-turn response selection ignore the dependencies between the turns.
Approach:	They propose a dialogue extraction algorithm to transform a dialog history into threads based on their dependency relations.
Outcome:	The proposed model outperforms the state-of-the-art models on DSTC7 and DSTF8* with competitive results on UbuntuV2 .

Copied to clipboard

Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue, Qi Zhang, Yifan Wu, Jianguo Li

MuTIS: Enhancing Reasoning Efficiency through Multi Turn Intervention Sampling in Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing models that use self-attention and position embedding have anomalous behavior that hinder long context window extrapolation.
Approach:	They propose a collinear constraint between Q and K to integrate RoPE and self-attention.
Outcome:	The proposed model integrates self-attention and position embedding into LLMs without fine-tuning.

Copied to clipboard

Wenshuo Zhao, Haoxing Zhai, Xinyu Qiu, Zhenting Qi, Shuhe Li, Linchao Zhu

Opinion Summarization by Weak-Supervision from Mix-structured Data (2022.emnlp-main)

Challenge:	Existing methods for training large reasoning models with long chain-of-thought (CoT) are limited by the number of parameters and the complexity of the model.
Approach:	They propose a framework that leverages multi-turn interventions to produce concise reasoning chains and demonstrates strong scalability.
Outcome:	The proposed framework breaks the accuracy-efficiency trade-off by producing concise reasoning chains and demonstrating strong scalability on 7B models.

Copied to clipboard

Yizhu Liu, Qi Jia, Kenny Zhu

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

Challenge:	Existing methods for opinion summarization of multiple reviews lack reference summaries . OAs and ISs are often mismatched between review input and summary .
Approach:	They propose a method to generate mixed-structured synthetic training data for opinion summarization.
Outcome:	The proposed method outperforms existing methods on Yelp, Amazon and RottenTomatos datasets.

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

LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)

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

Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Enhancing Model Privacy in Federated Learning with Random Masking and Quantization (2025.findings-emnlp)

Challenge:	Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM.
Approach:	They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks.
Outcome:	The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting.

Copied to clipboard

Zhibo Xu, Zhu JianHao, Jingwen Xu, Changze Lv, Zhenghua Wang, Zisu Huang, Xiaohua Wang, Muling Wu, Qi Qian, Xiaoqing Zheng, Xuanjing Huang

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection (2025.acl-long)

Challenge:	federated learning approaches are limited by the complexity of large language models and the need for specialized expertise to protect intellectual property.
Approach:	They propose a federated learning approach that leverages random masking to obscure a subnetwork of model parameters and applies quantization to the remaining parameters.
Outcome:	The proposed approach maintains strong model performance in federated learning settings and achieves enhanced protection of model parameters compared to baseline methods.

Copied to clipboard

Yixian Shen, Qi Bi, Jia-hong Huang, Hongyi Zhu, Andy D. Pimentel, Anuj Pathania

Challenge:	MaCP is a new adaptation method for large foundation models that requires minimal parameters and memory for fine-tuning.
Approach:	They propose a method that exploits the superior energy compaction and decorrelation properties of cosine projection to improve model efficiency and accuracy.
Outcome:	The proposed method improves model efficiency and accuracy across a wide range of single-modality tasks including natural language understanding, natural language generation, text summarization, and multi-modalities such as image classification and video understanding.

Facet-Aware Evaluation for Extractive Summarization (2020.acl-main)

Copied to clipboard

Yuning Mao, Liyuan Liu, Qi Zhu, Xiang Ren, Jiawei Han

One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework (2026.acl-long)

Challenge:	lexical overlap is a common evaluation metric for extractive summarization, but recent studies reveal its limitations.
Approach:	They propose a facet-aware evaluation setup for better assessment of information coverage in extractive summaries.
Outcome:	The proposed evaluation setup improves human correlation with extractive summarization datasets and improves comparative analysis.

Copied to clipboard

Qi Jia, Ye Shen, Xiujie Song, Kaiwei Zhang, Shibo Wang, Dun Pei, Xiangyang Zhu, Guangtao Zhai

Pass off Fish Eyes for Pearls: Attacking Model Selection of Pre-trained Models (2022.acl-long)

Challenge:	Existing benchmarks for instruction-following in multi-topic dialogues are limited to a fixed number of turns, susceptible to saturation and failing to account for users’ interactive experience.
Approach:	They propose a framework featuring a three-layer tracking mechanism and a query synthesis agent to mimic sequential user behaviors.
Outcome:	The proposed framework outperforms existing benchmarks in the evaluation of instruction following in multi-topic dialogues and demonstrates deficiencies in failure recovery and fine-grained instruction following.

Copied to clipboard

Biru Zhu, Yujia Qin, Fanchao Qi, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu

Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)

Challenge:	Existing feature-based model selection methods are vulnerable to fine-tuning and are not reliable indicators for the PTM’s transferability.
Approach:	They propose feature-based model selection methods which assess PTMs’ transferability to a specific task in a fast way without fine-tuning.
Outcome:	The proposed methods can make FMS mistakenly judge transferability of models and can be combined with the backdoor attack to misguide the FMS to select poisoned models.

Copied to clipboard

Ziqi Wang, Chen Zhu, Zhi Zheng, Xinhang Li, Tong Xu, Yongyi He, Qi Liu, Ying Yu, Enhong Chen

SOTOPIA-π: Interactive Learning of Socially Intelligent Language Agents (2024.acl-long)

Challenge:	Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors.
Approach:	They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively.
Outcome:	The proposed framework achieves state-of-the-art on the fine-grained content extraction task.

Copied to clipboard

Ruiyi Wang, Haofei Yu, Wenxin Zhang, Zhengyang Qi, Maarten Sap, Yonatan Bisk, Graham Neubig, Hao Zhu

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)

Challenge:	Existing studies on building language agents have not addressed this social learning gap.
Approach:	They propose an interactive learning method that improves the social intelligence of language agents by using behavior cloning and self-reinforcement based training on filtered social interaction data.
Outcome:	The proposed method allows a 7B LLM to reach the social goal completion ability of an expert model (GPT-4-based agent) without the loss of more generic abilities, such as the ability to answer knowledge-based questions.

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

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

Challenge:	Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases.
Approach:	They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases.
Outcome:	The proposed framework synthesizes more generalized training data to address these model weaknesses.

Copied to clipboard

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

Information Extraction & Text Mining

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.

BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language? (2024.findings-emnlp)

Copied to clipboard

Zongmeng Zhang, Jinhua Zhu, Wengang Zhou, Xiang Qi, Peng Zhang, Houqiang Li

AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026.findings-acl)

Challenge:	Dense retrieval systems focus on optimizing text embedding space while overlooking Boolean logic in language.
Approach:	They propose a task to investigate whether retrieval systems can comprehend Boolean logic in language.
Outcome:	The proposed method is based on a benchmark dataset covering complex queries containing basic Boolean logic and corresponding annotated passages.

Copied to clipboard

Jiazheng Zhang, Ziche Fu, Zhiheng Xi, Wenqing Jing, Mingxu Chai, Wei He, Guoqiang Zhang, Chenghao Fan, Chenxin An, Wenxiang Chen, Zhicheng Liu, Haojie Pan, Dingwei Zhu, Tao Gui, Qi Zhang, Xuanjing Huang

QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)

Challenge:	Existing approaches to improve LLM reasoning are limited in complex domains and lack external grounding makes verifiers unreliable on computation-intensive tasks.
Approach:	They propose a framework that transforms reward modeling into a multi-turn, tool-augmented deliberative process.
Outcome:	The proposed framework surpasses state-of-the-art ORMs by 25.2% under parallel and sequential TTS.

Copied to clipboard

Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen

TaKG: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs (2022.findings-aacl)

Challenge:	Existing approaches to program repair are based on correctness alone.
Approach:	They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits.
Outcome:	The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing.

Copied to clipboard

Qianqian Qi, Zhenyun Deng, Yonghua Zhu, Lia Jisoo Lee, Michael Witbrock, Jiamou Liu

Structured Data in NLP

Challenge:	Existing table-to-text generation benchmarks have some limitations, such as E2E and ToTTo focusing on singlesentence generation tasks.
Approach:	They propose a new table-to-text generation dataset called TaKG that uses a set of knowledge graphs to enhance table input.
Outcome:	The proposed model outperforms existing models for short-text generation tasks and shows reliable performance on long-text generated across a variety of metrics.

TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents (2025.emnlp-demos)

Copied to clipboard

Haofei Yu, Keyang Xuan, Fenghai Li, Kunlun Zhu, Zijie Lei, Jiaxun Zhang, Ziheng Qi, Kyle Richardson, Jiaxuan You

SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation (2025.naacl-long)

Challenge:	Existing research systems often design and use agentic workflows to perform research tasks such as ideation, scientific coding, review writing, and tree-based search.
Approach:	They propose an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer.
Outcome:	The proposed framework adapts easily to new tools and supports iterative growth.

Copied to clipboard

Yixian Shen, Qi Bi, Jia-hong Huang, Hongyi Zhu, Andy D. Pimentel, Anuj Pathania

Perception, Understanding and Reasoning: A Multimodal Benchmark for Video Fake News Detection (2026.acl-long)

Challenge:	Low-rank adaptation (LoRA) has been demonstrated effective in reducing the trainable parameter number when fine-tuning a large foundation model (LLM).
Approach:	They propose a low-rank adaptation approach that reduces the number of trainable parameters while enhancing model performance.
Outcome:	The proposed approach outperforms existing parameter-efficient fine-tuning methods while achieving substantial reductions in computational cost and memory requirements.

Copied to clipboard

Cui Yakun, Peng Qi, Fushuo Huo, Hang Du, Weijie Shi, Juntao Dai, Zhenghao Zhu, Sirui Han

Factual Dialogue Summarization via Learning from Large Language Models (2025.coling-main)

Challenge:	Existing video fake news detection benchmarks focus on the detection accuracy, while failing to provide fine-grained assessments for the entire detection process.
Approach:	They propose a process-oriented video fake news detection benchmark that evaluates MLLMs' perception, understanding, and reasoning capabilities in VFND.
Outcome:	The proposed model achieves sota performance on video fake news detection tasks.

Copied to clipboard

Rongxin Zhu, Jey Han Lau, Jianzhong Qi

Spatiotemporal Sycophancy: Negation-Based Gaslighting in Video Large Language Models (2026.findings-acl)

Challenge:	Existing models generate fluent and coherent summaries, but inconsistencies can be found in generated summary.
Approach:	They propose to use symbolic knowledge distillation to improve the factual consistency of smaller pretrained models for dialogue summarization.
Outcome:	The proposed model outperforms baseline models in BART, PEGASUS, and Flan-T5 in factual consistency and accuracy.

Copied to clipboard

Ziyao Tang, Pengkun Jiao, Bin Zhu, Huiyan Qi, Jingjing Chen, Yu-Gang Jiang

PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning (2024.naacl-long)

Challenge:	Existing Vid-LLMs lack robust mechanisms for maintaining grounded spatiotemporal beliefs under conversational feedback.
Approach:	They propose a negation-based gaslighting evaluation framework and introduce a benchmark to investigate spatiotemporal sycophancy.
Outcome:	The proposed framework evaluates state-of-the-art Vid-LLMs across video understanding tasks.

Copied to clipboard

Xuekai Zhu, Biqing Qi, Kaiyan Zhang, Xinwei Long, Zhouhan Lin, Bowen Zhou

AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning (2025.acl-industry)

Challenge:	Large language models excel in various tasks, but their huge size and inaccessibility of parameters present challenges for practical deployment.
Approach:	They propose to use CoT data to distill task-specific ability from large language models to smaller models . they use reasoning programs to suppress errors in distilled data and improve distillation quality .
Outcome:	The proposed model outperforms LLMs on arithmetic reasoning, symbolic reasoning, and general ability.

Copied to clipboard

Jiayu Li, Jennifer Zhu, Fang Liu, Yanjun Qi

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study (2026.acl-long)

Challenge:	Existing methods for fine-tuning large language models for specific tasks require extensive seed datasets or struggle to balance task relevance and data diversity.
Approach:	They propose a data synthesis framework that uses a multi-hop process to expand very few seed data points while ensuring data diversity and task relevance.
Outcome:	The proposed framework outperforms state-of-the-art methods in task-specific fine-tuning by over 30%.

Copied to clipboard

Zhexin Zhang, Xian Qi Loye, Victor Shea-Jay Huang, Junxiao Yang, Qi Zhu, Shiyao Cui, Fei Mi, Lifeng Shang, Yingkang Wang, Hongning Wang, Minlie Huang

BoundRL: Efficient Token-level Structured Text Segmentation through Reinforced Boundary Generation (2026.findings-acl)

Challenge:	Large Reasoning Models have achieved remarkable success on reasoning-intensive tasks, but their enhanced reasoning capabilities do not translate to improved safety performance.
Approach:	They propose to use supervised fine tuning to enhance the safety of Large Reasoning Models.
Outcome:	The proposed method improves the safety of large reasoning models on reasoning-intensive tasks.

Copied to clipboard

Haoyuan Li, Zhengyuan Shen, Sullam Jeoung, Yueyan Chen, Jiayu Li, Qi Zhu, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow (2026.findings-acl)

Challenge:	Structured texts often contain elements beyond plain language, such as code snippets, which conventional sentence-level segmentation methods cannot handle effectively.
Approach:	They propose a token-level approach that performs efficient token-based text segmentation and label prediction for long structured texts.
Outcome:	The proposed approach outperforms existing models on short-shot prompts and SFT and standard RLVR models on complex LLM prompts.

Copied to clipboard

Yangyang Zhong, Yanmei Gu, Zhengqing Zang, Xiaomeng Li, Yuqi Ding, Xibei Jia, Yuting Shen, Zhenzhong Lan, Liwang Zhu, Weiping Liu, Junlin Zhou, Haisheng Liu, Zhong Xin Yu, Pengxin Luo, Donglian Qi, Yunfeng Yan, Junbo Zhao

Improving Robustness of Language Models from a Geometry-aware Perspective (2022.findings-acl)

Challenge:	Autoregressive (AR) language models dominate modern natural language processing due to strong likelihood-based training objectives and reliable left-to-right decoding.
Approach:	They characterize MDLM behavior along two dimensions: parallelism strength and generation order . authors propose a Generate-then-Edit paradigm that mitigates dependency loss .
Outcome:	The proposed model improves on tasks that require "backward information" the Generate-then-Edit paradigm improves parallel decoding efficiency while reducing dependency loss.

Copied to clipboard

Bin Zhu, Zhaoquan Gu, Le Wang, Jinyin Chen, Qi Xuan

Diagnosing Vision-and-Language Navigation: What Really Matters (2022.naacl-main)

Challenge:	Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness.
Approach:	They propose friendly adversarial data augmentation and geometry-aware adversarial training to achieve stronger robustness using fewer search steps.
Outcome:	The proposed method can obtain stronger robustness using fewer steps than existing methods.

Copied to clipboard

Wanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone, Sugato Basu, Xin Wang, Qi Wu, Miguel Eckstein, William Yang Wang

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

Challenge:	Existing models claim to be able to align object tokens with specific visual targets, but there are non-negligible gaps between the two.
Approach:	They conduct diagnostic experiments to examine how the agents perceive multimodal input by ablation diagnostics input data.
Outcome:	The results show that indoor and outdoor navigation agents refer to object and direction tokens when making decisions.

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

Building Multi-domain Dialog State Trackers from Single-domain Dialogs (2023.emnlp-main)

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.

Copied to clipboard

Qi Zhu, Zheng Zhang, Xiaoyan Zhu, Minlie Huang

Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Grounding (2025.findings-emnlp)

Challenge:	Existing multi-domain dialog state tracking models require significant manual effort to define domain relations and collect data.
Approach:	They propose a divide-and-conquer (DAC) DST paradigm and a multi-domain dialog synthesis framework to build multi- domain DST models from single-domain dialogues.
Outcome:	The proposed paradigm makes building multi-domain DST models easier on unseen domain combinations.

Copied to clipboard

Hangdi Xing, Feiyu Gao, Qi Zheng, Zhaoqing Zhu, Zirui Shao, Ming Yan

Hierarchical Document Refinement for Long-context Retrieval-augmented Generation (2025.acl-long)

Challenge:	Existing methods fragment document parsing into pipeline of separated subtasks, resulting in incomplete semantics and error propagation.
Approach:	They propose an end-to-end document parsing framework that leverages vision-language priors of MLLMs.
Outcome:	The proposed method surpasses existing methods significantly in document parsing . it leverages the vision-language priors of MLLMs to decouple parse and layout grounding based on visual information.

Copied to clipboard

Jiajie Jin, Xiaoxi Li, Guanting Dong, Yuyao Zhang, Yutao Zhu, Yongkang Wu, Zhonghua Li, Ye Qi, Zhicheng Dou

SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph (2022.aacl-main)

Challenge:	Real-world RAG applications often encounter long-context input scenarios where redundant information and noise results in higher inference costs and reduced performance.
Approach:	They propose an efficient plug-and-play refiner that leverages the structural characteristics of long documents.
Outcome:	Experiments on seven QA datasets show that LongRefiner achieves competitive performance in various scenarios while using 10x fewer computational costs and latency compared to baseline.

Copied to clipboard

Siya Qi, Lei Li, Yiyang Li, Jin Jiang, Dingxin Hu, Yuze Li, Yingqi Zhu, Yanquan Zhou, Marina Litvak, Natalia Vanetik

Information Extraction & Text Mining

Challenge:	Abstractive and extractive methods are used to condense long text into concise summaries while retaining essential information.
Approach:	They propose to use paper structure to extract paper summaries from long text . they provide a large-scale dataset of COVID-19-related papers .
Outcome:	The proposed framework generates more comprehensive and valuable summaries compared to previous work on COVID-19-related papers.

Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Copied to clipboard

Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo

BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering (2025.emnlp-main)

Challenge:	Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach:	They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome:	The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.

Copied to clipboard

Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis, Zhen Han, Qi Zhu, Ian Robinson, Bryan Thompson, Huzefa Rangwala, George Karypis

Structured Data in NLP

Challenge:	Existing approaches to knowledge graph question answering (KGQA) rely on Large Language Model (LLM) agents for graph traversal and retrieval.
Approach:	They propose a framework that synergizes Large Language Models with specialized graph retrieval tools to enhance KGQA.
Outcome:	The proposed framework outperforms the second-best graph retrieval method by 4.5% points while showing better generalization to custom KGs.

ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs (2025.findings-emnlp)

Copied to clipboard

Zige Wang, Qi Zhu, Fei Mi, Minghui Xu, Ruochun Jin, Wenjing Yang

Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Gradient-based data influence approximation is not feasible in practice.
Approach:	They propose a gradient-based data selection framework with clustering and a modified Upper Confidence Bound algorithm to solve this problem.
Outcome:	The proposed framework can achieve comparable results to the original gradient-based data selection methods while reducing computational consumption.

Copied to clipboard

Junde Wu, Jiayuan Zhu, Yunli Qi, Jingkun Chen, Min Xu, Filippo Menolascina, Yueming Jin, Vicente Grau

Reading Order Matters: Information Extraction from Visually-rich Documents by Token Path Prediction (2023.emnlp-main)

Challenge:	GraphRAG framework is designed to enhance LLMs in generating evidence-based medical responses.
Approach:	They propose a graph-based Retrieval-augmented generation framework to enhance LLMs in generating evidence-based medical responses.
Outcome:	The proposed framework outperforms state-of-the-art models on 9 medical Q&A benchmarks, 2 health fact-checking datasets, and a long-form generation test set.

Copied to clipboard

Chong Zhang, Ya Guo, Yi Tu, Huan Chen, Jinyang Tang, Huijia Zhu, Qi Zhang, Tao Gui

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Challenge:	Recent advances in multimodal pre-trained models have significantly improved information extraction from visually-rich documents (VrDs).
Approach:	They propose a method to predict token sequences within visually-rich documents by a simple prediction head.
Outcome:	The proposed method can be used to predict token mentions as token sequences within documents.

Copied to clipboard

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che

Dynamic Curriculum Learning for Low-Resource Neural Machine Translation (2020.coling-main)

Challenge:	Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach:	They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome:	The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.

Copied to clipboard

Chen Xu, Bojie Hu, Yufan Jiang, Kai Feng, Zeyang Wang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Challenge:	Recent work on neural machine translation (NMT) has demonstrated impressive performance improvements and became the de-facto standard.
Approach:	They propose a dynamic curriculum learning method to reorder training samples in training using a Transformer-based system.
Outcome:	The proposed method outperforms baselines on three low-resource machine translation benchmarks and different sized data of WMT’16 En-De.

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Post-Training Dialogue Summarization using Pseudo-Paraphrasing (2022.findings-naacl)

Copied to clipboard

Qi Jia, Yizhu Liu, Haifeng Tang, Kenny Zhu

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	Existing approaches to dialogue summarization use dialogue-specific features that require additional knowledge to recognize or make the models harder to tune.
Approach:	They propose to post-train pretrained language models to rephrase from dialogue to narratives and fine-tune them as usual.
Outcome:	The proposed approach outperforms existing models by summary quality and implementation costs.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

RePair: Automated Program Repair with Process-based Feedback (2024.findings-acl)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Yuze Zhao, Zhenya Huang, Yixiao Ma, Rui Li, Kai Zhang, Hao Jiang, Qi Liu, Linbo Zhu, Yu Su

TaeBench: Improving Quality of Toxic Adversarial Examples (2025.naacl-industry)

Challenge:	Commercial-scale language models (LMs) have taken APR to unprecedented levels, but they are limited by parameters and humans interact with them through explicit prompts.
Approach:	They propose a method that utilizes process supervision to improve program repair by allowing users to input feedback from compilers and test cases.
Outcome:	The proposed method outperforms large outcome-based generation methods and is inspired by strategies used in programming competitions.

Copied to clipboard

Jennifer Zhu, Dmitriy Bespalov, Liwen You, Ninad Kulkarni, Yanjun Qi

CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset (2020.tacl-1)

Challenge:	Existing adversarial examples generate invalid or ambiguous examples that fool the systems into wrong detection.
Approach:	They propose an annotation pipeline for quality control of generated toxic adversarial examples (TAE) they use model-based automated annotation and human-based quality verification to assess quality requirements of a TAE dataset.
Outcome:	The proposed pipeline can transfer-attack SOTA toxicity content moderation models and services with adversarial training.

Copied to clipboard

Qi Zhu, Kaili Huang, Zheng Zhang, Xiaoyan Zhu, Minlie Huang

Cross-lingual Lexical Sememe Prediction (D18-1)

Challenge:	Despite the significant contributions to the community, there is still a gap between existing dialogue corpora and real-life human dialogue data.
Approach:	They propose to develop Chinese cross-domain wizard-of-oz task-oriented dataset CrossWOZ with rich annotations of dialogue states and dialogue acts on both user and system sides.
Outcome:	The proposed dataset contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi.

Copied to clipboard

Fanchao Qi, Yankai Lin, Maosong Sun, Hao Zhu, Ruobing Xie, Zhiyuan Liu

Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining (2021.emnlp-main)

Challenge:	Sememes are defined as the minimum semantic units of human languages . but most languages do not have sememe-based linguistic knowledge bases . a new framework is proposed to predict sememes for words in other languages based on semems .
Approach:	They propose a framework to model correlations between sememes and multi-lingual words in low-dimensional semantic space for sememe prediction.
Outcome:	The proposed model improves on baseline methods on real-world datasets.

Copied to clipboard

Yicheng Zou, Bolin Zhu, Xingwu Hu, Tao Gui, Qi Zhang

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders (2021.acl-long)

Challenge:	Existing methods for low-resource dialogue summarization neglect the difference between dialogues and conventional articles.
Approach:	They propose a multi-source pretraining paradigm to leverage external summary data . they exploit large-scale in-domain non-summary data to separate dialogue encoder and summary decoder .
Outcome:	The proposed model can be used to better leverage external summary data.

Copied to clipboard

Chen Xu, Bojie Hu, Yanyang Li, Yuhao Zhang, Shen Huang, Qi Ju, Tong Xiao, Jingbo Zhu

ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format (2023.emnlp-demo)

Challenge:	End-to-end Speech Translation (E2E ST) encoders lack global context representation, whereas MT encoder lacks it.
Approach:	They propose a Stacked Acoustic-and-Textual Encoding method for speech translation . they propose an adaptor module to alleviate representation inconsistency .
Outcome:	The proposed method achieves state-of-the-art BLEU scores of 18.3 and 25.2 on two ST tasks.

Copied to clipboard

Qi Zhu, Christian Geishauser, Hsien-chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Shutong Feng, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gasic, Minlie Huang

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

Challenge:	Existing tools for building TOD systems often lack a user-friendly interface . a toolkit with advanced, easily integrable modules is needed to bridge this gap .
Approach:	They propose a multifaceted dialogue system toolkit that integrates diverse datasets and models with a streamlined training process and in-depth evaluation tools.
Outcome:	The proposed toolkit combines RL and transfer learning to support the rapid development and evaluation of robust dialogue policies.

Copied to clipboard

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

GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

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

Copied to clipboard

Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou

Black-Box Membership Inference Attacks for Video Training Data in Multimodal Large Language Models (2026.acl-long)

Challenge:	Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach:	They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome:	The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.

Copied to clipboard

Jinrui Wang, Zhenfeng Gao, Wendan Wang, Huili Wang, Zichen Qin, Linjie Zhu, Hongke Fu, Shangguang Wang, Tao Qi

RLSeek: Evidence-Grounded Reasoning for RAG Hallucination Detection (2026.acl-long)

Challenge:	Existing methods assess model memorization of key semantic concepts within a video but do not provide reliable evidence that a specific video was used during training.
Approach:	They propose a black-box MIA framework that can provide reliable evidence of specific video data usage for training multimodal large language models.
Outcome:	The proposed framework can provide reliable evidence of specific video data usage for training multimodal large language models.

Copied to clipboard

Zhaoheng Huang, Dacheng Wen, Yutao Zhu, Xiaoying Lian, Yushi Liang, Kai Hao, Nan Li, Liangjie Zhang, Qi Zhang, Ji-Rong Wen, Zhicheng Dou, Fangzhao Wu

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

Challenge:	Recent work addresses this problem by training span-level hallucination detectors using reinforcement learning and chain-of-thought reasoning.
Approach:	They propose a framework that explicitly enforces active evidence seeking during CoT reasoning by requiring quotation of relevant source segments at each verification step.
Outcome:	The proposed framework improves hallucination span detection performance with limited reasoning overhead and improved robustness in out-of-domain settings.

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

Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding (2024.emnlp-main)

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 .

Copied to clipboard

Chong Zhang, Yi Tu, Yixi Zhao, Chenshu Yuan, Huan Chen, Yue Zhang, Mingxu Chai, Ya Guo, Huijia Zhu, Qi Zhang, Tao Gui

Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs (2025.acl-short)

Challenge:	Existing models of layout reading order do not convey the complete reading order information in the layout.
Approach:	They propose to model layout reading order as ordering relations over layout elements . they propose a reading-order-relation-enhancing pipeline to improve model performance .
Outcome:	The proposed model outperforms existing models on a visual-rich document dataset and on eight cross-domain VrD-IE/QA tasks without targeted optimization.

Copied to clipboard

Payal Mohapatra, Akash Pandey, Xiaoyuan Zhang, Qi Zhu

Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model (2023.emnlp-main)

Challenge:	Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech.
Approach:	They propose an EMG adaptor module that maps EMG features to an LLM's input space and achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task.
Outcome:	The proposed module achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task.

Copied to clipboard

Qi Jia, Siyu Ren, Yizhu Liu, Kenny Zhu

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors (2026.acl-long)

Challenge:	Existing work evaluates faithfulness using models trained on related tasks or in-domain synthetic data.
Approach:	They propose to do zero-shot faithfulness evaluation with a foundation language model.
Outcome:	The proposed model outperforms ChatGPT on faithfulness and inconsistency detection with 24x fewer parameters and is competitive with existing models.

Copied to clipboard

Yuqing Yang, Qi Zhu, Zhen Han, Boran Han, Zhengyuan Shen, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

UniRAG: Unified Query Understanding Method for Retrieval Augmented Generation (2025.acl-long)

Challenge:	Large language models (LLMs) perform well on table tasks, but they still make data referencing errors (DREs) prior studies have only offered limited, small-scale analyses.
Approach:	They propose inference-time strategies and lightweight critics to mitigate data referencing errors.
Outcome:	The proposed model achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-difference DREs and assists inference for larger models.

Copied to clipboard

Rui Li, Liyang He, Qi Liu, Zheng Zhang, Heng Yu, Yuyang Ye, Linbo Zhu, Yu Su

Efficient Sequential Decision Making with Large Language Models (2024.emnlp-main)

Challenge:	Existing query augmentation methods face knowledge update lag and hallucinations in large language models (LLMs) Existing methods face two key challenges: (1) separation of query augmented and encoding tasks, which hinders information sharing and introduces cumulative errors; (2) difficulty of selecting optimal augmentation strategy for different scenarios.
Approach:	They propose a unified framework for query understanding in RAG that integrates internal and external knowledge to enhance query augmentation and encoding tasks.
Outcome:	The proposed framework outperforms traditional query augmentation methods in five knowledge-intensive benchmark tasks in both closed and open domain question answering.

Copied to clipboard

Dingyang Chen, Qi Zhang, Yinglun Zhu

SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL (2026.acl-long)

Challenge:	Existing approaches to retrain or finetune large language models (LLMs) for decision making suffer from computational burden of gradient updates.
Approach:	They propose a model selection algorithm that leverages online model selection algorithms to efficiently incorporate LLMs agents into sequential decision making.
Outcome:	The proposed approach outperforms both traditional decision making algorithms and vanilla LLM agents on a large-scale Amazon dataset.

Copied to clipboard

Harper Hua, Zhen Han, Zhengyuan Shen, Meng-Chieh Lee, Sheng Guan, Qi Zhu, Sullam Jeoung, Yueyan Chen, Yunfei Bai, Shuai Wang, Vassilis N. Ioannidis, Huzefa Rangwala

Programming Languages in NLP

Challenge:	Recent large language models (LLMs) have significantly improved Text-to-SQL generation, but a gap remains between AI systems and human experts on challenging benchmarks such as BIRD-Sql.
Approach:	They propose a multi-turn reinforcement learning agentic framework for Text-to-SQL that uses execution feedback to iteratively refine its predictions.
Outcome:	The proposed framework outperforms proprietary systems on 7B and 14B models by **5% on average, underscoring the effectiveness of interactive, agentic workflows for robust Text-to-SQL generation.

CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture (2025.findings-emnlp)

Copied to clipboard

Zaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu, Yinhan He, Liangjie Hong, Qi Guo, Jundong Li

ESF: Efficient Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models (2025.findings-acl)

Challenge:	Existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base, which often miss relevant information located further away from a global view.
Approach:	Hybrid-RAG combines textual documents and graph-structured relational information for RAG . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .
Outcome:	Hybrid-RAG combines textual documents and graph-structured relational information . existing methods only retrieve related documents from local neighbors or subgraphs in the knowledge base .

Copied to clipboard

Xiaofan Bai, Pingyi Hu, Xiaojing Ma, Linchen Yu, Dongmei Zhang, Qi Zhang, Bin Benjamin Zhu

Prompt-based Conservation Learning for Multi-hop Question Answering (2022.coling-1)

Challenge:	Large language models (LLMs) are increasingly utilized in diverse applications, including code generation, legal document analysis, medical diagnosis, and decision-making.
Approach:	They propose a fingerprinting method tailored for black-box tamper detection of large language models.
Outcome:	The proposed method detects tampering with a 99.2% detection rate using 5 fingerprint samples across state-of-the-art LLMs.

Copied to clipboard

Zhenyun Deng, Yonghua Zhu, Yang Chen, Qianqian Qi, Michael Witbrock, Patricia Riddle

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering (2025.emnlp-main)

Challenge:	Existing multi-hop QA methods fail to answer a large fraction of sub-questions even if their parent questions are answered correctly.
Approach:	They propose a Prompt-based Conservation Learning framework that acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop tasks.
Outcome:	The proposed framework acquires new knowledge from multi-hop QA tasks while conserving old knowledge learned on single-hop tasks, mitigating forgetting.

Copied to clipboard

Jingxuan Wei, Nan Xu, Junnan Zhu, null Haoyanni, Gaowei Wu, Qi Chen, Bihui Yu, Lei Wang

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

Challenge:	Chart question answering (CQA) is a multimodal task for evaluating the reasoning capabilities of vision-language models.
Approach:	They propose a chart question answering benchmark that incorporates multilingual contexts and supports open-domain textual outputs.
Outcome:	The proposed framework outperforms the previous three common CQA paradigms: instruction-following, OCR-enhanced, and chain-of-thought.

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

In-sample Curriculum Learning by Sequence Completion for Natural Language Generation (2023.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

Qi Jia, Yizhu Liu, Haifeng Tang, Kenny Zhu

Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding (2025.emnlp-main)

Challenge:	Existing work on curriculum learning rely on task-specific expertise and cannot generalize to different tasks.
Approach:	They propose to do in-sample curriculum learning for natural language generation tasks using human-crafted rules and a numeric score for each sample based on domain expertise to rank the model.
Outcome:	The proposed learning strategy generalizes well to different tasks and achieves significant improvements over baselines.

Copied to clipboard

Zirui Shao, Feiyu Gao, Zhaoqing Zhu, Chuwei Luo, Hangdi Xing, Zhi Yu, Qi Zheng, Ming Yan, Jiajun Bu

Exploring Hybrid Question Answering via Program-based Prompting (2024.acl-long)

Challenge:	Multimodal large language models (MLLMs) have shown impressive capabilities in document understanding due to different types of annotation noise in training.
Approach:	They propose a method to reduce C&P knowledge conflicts across all tested MLLMs . they propose to use annotation noise to train models to understand document content .
Outcome:	The proposed method reduces C&P knowledge conflicts across all tested MLLMs and enhances their performance in both cognitive and perceptual tasks.

Copied to clipboard

Qi Shi, Han Cui, Haofeng Wang, Qingfu Zhu, Wanxiang Che, Ting Liu

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems (2020.acl-demos)

Challenge:	Existing approaches to question answering over heterogeneous data are limited due to large scale of information and organic coupling of heterogenous data.
Approach:	They propose a program-based prompting framework for hybrid question answering tasks . it integrates various functions to perform hybrid information-seeking over data .
Outcome:	The proposed framework surpasses baseline systems and achieves the best performance under the fewshot settings.

Copied to clipboard

Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang

Continual Prompt Tuning for Dialog State Tracking (2022.acl-long)

Challenge:	ConvLab-2 inherits Convlab's framework but integrates more powerful dialogue models and supports more datasets.
Approach:	They present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models and perform an end-to-end evaluation.
Outcome:	The new tool inherits ConvLab's framework and extends it by integrating many recently proposed state-of-the-art dialogue models.

Copied to clipboard

Qi Zhu, Bing Li, Fei Mi, Xiaoyan Zhu, Minlie Huang

CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model (2023.emnlp-main)

Challenge:	Existing methods to train a model on a sequence of tasks are not efficient enough to mitigate catastrophic forgetting.
Approach:	They propose a parameter-efficient framework that prevents forgetting and enables knowledge transfer between tasks by learning and freezing a pre-trained model.
Outcome:	The proposed framework avoids forgetting and enables knowledge transfer between tasks.

Copied to clipboard

Kaiyan Zhang, Ning Ding, Biqing Qi, Xuekai Zhu, Xinwei Long, Bowen Zhou

UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning (2026.acl-long)

Challenge:	Instruction tuning is an effective way of aligning large language models with private instruction data.
Approach:	They propose a training-free strategy to derive improved emulators from LLMs by using Offsite-Tuning (OFT) they propose CRaSh, which transfers transformer blocks between centralized LLM and downstream emulators .
Outcome:	The proposed technique boosts performance of large language models with billions of parameters.

Copied to clipboard

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

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)

Challenge:	Extensive experiments on 18 widely used LLMs uncover critical insights: (1) models exhibit severe geographic biases and resolution gaps; (2) failures in complex multi-hop tasks stem from brittle foundational spatial skills rather than high-level logic deficits.
Approach:	They propose a dual-module framework that disentangles factual recall and spatial logic from the model's real capabilities in urban environments.
Outcome:	Extensive tests on 18 widely used LLMs reveal that models exhibit severe geographic biases and resolution gaps, and failures in complex multi-hop tasks often stem from brittle foundational spatial skills rather than high-level logic deficits.

Copied to clipboard

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang

HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases (2025.acl-long)

Challenge:	Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision.
Approach:	They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck.
Outcome:	The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards.

Copied to clipboard

Meng-Chieh Lee, Qi Zhu, Costas Mavromatis, Zhen Han, Soji Adeshina, Vassilis N. Ioannidis, Huzefa Rangwala, Christos Faloutsos

Knowledge Representation

Challenge:	Existing methods for retrieving information from a semi-structured knowledge base are struggling with hybrid questions.
Approach:	They propose a retrieval method that leverages both textual and relational information from a semi-structured knowledge base to answer user questions.
Outcome:	The proposed method surpasses all baselines on the STaRK benchmark and achieves significant performance gains.

UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models (2025.acl-long)

Copied to clipboard

Boyang Xue, Fei Mi, Qi Zhu, Hongru Wang, Rui Wang, Sheng Wang, Erxin Yu, Xuming Hu, Kam-Fai Wong

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios (2024.findings-acl)

Challenge:	Large Language Models (LLMs) often struggle to accurately express factual knowledge, especially in cases where the knowledge boundaries are ambiguous.
Approach:	They propose a framework that leverages Uncertainty estimations to represent knowledge boundaries and incorporates these representations into prompts for LLMs to Align with factual knowledge.
Outcome:	The proposed framework significantly improves the LLMs’ capacities to confidently answer known questions and refuse unknown questions on both in-domain and out-of-domain tasks.

Copied to clipboard

Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, Qun Liu

Reducing Sensitivity on Speaker Names for Text Generation from Dialogues (2023.findings-acl)

Challenge:	Existing benchmarks focus on simple synthesized queries that do not reflect real-world complexity, thereby offering limited perspectives in evaluating tool utilization.
Approach:	They propose a benchmark to evaluate LLMs’ ability in tool utilization within real-world scenarios.
Outcome:	The proposed benchmark improves LLMs’ ability in tool utilization within real-world scenarios and eliminates the restriction of pre-defined toolset.

Copied to clipboard

Qi Jia, Haifeng Tang, Kenny Zhu

Annotating and Detecting Fine-grained Factual Errors for Dialogue Summarization (2023.acl-long)

Challenge:	Pre-trained language models are sensitive to nuances, resulting in unfairness in real-world applications.
Approach:	They propose to quantitatively measure a model's sensitivity on speaker names and comprehensively evaluate a number of known methods for reducing speaker name sensitivity.
Outcome:	The proposed approach reduces speaker name sensitivity and improves quality of generation.

Copied to clipboard

Rongxin Zhu, Jianzhong Qi, Jey Han Lau

Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization (2025.findings-naacl)

Challenge:	Existing work on factual inconsistency in abstractive summarization addresses this problem.
Approach:	They propose a dataset with fine-grained factual error annotations named DIASUMFACT and an unsupervised model named ENDERANKER.
Outcome:	The proposed model performs on par with the state-of-the-art models while requiring fewer resources.

Copied to clipboard

Yen-Ju Lu, Ting-Yao Hu, Hema Swetha Koppula, Hadi Pouransari, Jen-Hao Rick Chang, Yin Xia, Xiang Kong, Qi Zhu, Xiaoming Simon Wang, Oncel Tuzel, Raviteja Vemulapalli

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning (2026.acl-long)

Challenge:	Empirical results demonstrate that our method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings.
Approach:	They propose Mutual Reinforcing Data Synthesis (MRDS) within large language models to enhance few-shot dialogue summarization task.
Outcome:	Empirical results show that the proposed method improves dialogue summarization, achieving a 1.5% increase in ROUGE scores and a 0.3% improvement in BERT scores in few-shot settings.

Copied to clipboard

Bowen Ding, Yuhan Chen, Jiayang Lyu, Jiyao Yuan, Qi Zhu, Shuangshuang Tian, Dantong Zhu, Futing Wang, Heyuan Deng, Fei Mi, Lifeng Shang, Tao Lin

Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution (2026.acl-long)

Challenge:	evolving generic Large Language Models into specialized Large Reasoning Models requires effective post-training.
Approach:	They propose a plasticity-ceiling framework to harness expert trajectories . they establish the Sequential SFT-then-RL pipeline as the superior standard .
Outcome:	The proposed framework overcomes stability and premature convergence deficits in synchronized approaches.

Copied to clipboard

Beidan Liu, Zhengqiu Zhu, Chen Gao, Tianle Pu, Yong Zhao, Wei Qi, Quanjun Yin

Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models (2024.findings-naacl)

Challenge:	Large Language Model (LLM)-based optimization has shown promise for autonomous problem solving, but most approaches cast LLMs as passive constraint checkers rather than proactive strategy designers.
Approach:	They propose an end-to-end Automated Constraint Optimization method that tightly couples operations-research principles of constraint relaxation with LLM reasoning.
Outcome:	Extensive experiments on three challenging COP benchmarks validate AutoCO’s consistent effectiveness and superior performance, especially in hard regimes where current methods degrade.

Copied to clipboard

Rui Wang, Fei Mi, Yi Chen, Boyang Xue, Hongru Wang, Qi Zhu, Kam-Fai Wong, Ruifeng Xu

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

Challenge:	Large Language Models (LLMs) suffer catastrophic forgetting when tailored to specific domains . authors present a novel approach to manage multi-domain LLM adaptation .
Approach:	They propose a strategy to manage multi-domain LLM adaptation using self-distillation and role integration.
Outcome:	The proposed model alleviates catastrophic forgetting and inter-domain confusion while maintaining robust general capabilities.

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

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users (2025.findings-emnlp)

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

Mengxuan Hu, Hongyi Wu, Ronghang Zhu, Zihan Guan, Dongliang Guo, Daiqing Qi, Sheng Li

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Challenge:	Retrieval-augmented generation is widely adopted for its effectiveness and cost-efficiency in mitigating hallucinations.
Approach:	They propose a practical three-level threat model from the perspective of user fairness awareness.
Outcome:	The proposed model shows that RAG can undermine fairness alignment without fine-tuning or retraining.

Copied to clipboard

Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen

Knowledge-Enhanced Named Entity Disambiguation for Short Text (2020.aacl-main)

Challenge:	Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach:	They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome:	The proposed model achieves 49.04% accuracy across five model families.

Copied to clipboard

Zhifan Feng, Qi Wang, Wenbin Jiang, Yajuan Lyu, Yong Zhu

Knowledge Representation

Challenge:	Existing methods for named entity disambiguation are weak for short text . performance of existing methods drops dramatically for short texts .
Approach:	They propose a knowledge-enhanced method for named entity disambiguation . they use factual knowledge graph and conceptual knowledge graph to provide additional knowledge .
Outcome:	The proposed method achieves significant improvement on a large manually annotated short-text dataset and the state-of-the-art on three standard datasets.

A Unified Dialogue User Simulator for Few-shot Data Augmentation (2022.findings-emnlp)

Copied to clipboard

Dazhen Wan, Zheng Zhang, Qi Zhu, Lizi Liao, Minlie Huang

Low-Resource NLP

Challenge:	Existing methods to augment large-scale task-oriented dialogues rely on annotated data.
Approach:	They propose to build a unified dialogue user simulation model by pre-training on publicly available datasets.
Outcome:	The proposed model can be tuned on a target domain with few-shot data.

Context Compression for Auto-regressive Transformers with Sentinel Tokens (2023.emnlp-main)

Copied to clipboard

Siyu Ren, Qi Jia, Kenny Zhu

Length Control in Abstractive Summarization by Pretraining Information Selection (2022.acl-long)

Challenge:	Existing Transformer-based LLMs have limited performance due to complexity of attention module . key-value cache is the major memory footprint and inference latency problem .
Approach:	They propose a plug-and-play approach that incrementally compresses token activation into compact ones . they also profile the benefit of context compression on improving the system throughout .
Outcome:	The proposed approach reduces memory footprint and inference latency by compressing tokens into compact ones.

Copied to clipboard

Yizhu Liu, Qi Jia, Kenny Zhu

Summarization

Challenge:	Existing length-controllable summarization models generate summaries as long as training data . current methods only control lengths at decoding stage, but adapt to desired lengths .
Approach:	They propose a length-aware attention mechanism to adapt the encoding of the source based on the desired length.
Outcome:	The proposed method produces high-quality summaries with desired lengths and even those short lengths never seen in the training data.

SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discovery (2025.emnlp-main)

Copied to clipboard

Kunlun Zhu, Jiaxun Zhang, Ziheng Qi, Nuoxing Shang, Zijia Liu, Peixuan Han, Yue Su, Haofei Yu, Jiaxuan You

Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)

Challenge:	Recent advances in large language model (LLM) agents have significantly accelerated scientific discovery automation, yet raised critical ethical and safety concerns.
Approach:	They propose a framework to enhance safety and ethical responsibility in AI-driven scientific exploration.
Outcome:	The proposed framework significantly improves safety performance by 35% compared to traditional frameworks.

Copied to clipboard

Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang

Challenge:	Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals .
Approach:	They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation.
Outcome:	The proposed method mitigates behavior collapse and improves performance across benchmarks.

ConvLab: Multi-Domain End-to-End Dialog System Platform (P19-3)

Copied to clipboard

Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Zheng Zhang, Yaoqin Zhang, Xiang Li, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao

TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing (2021.acl-demo)

Challenge:	ConvLab is an open-source multi-domain end-to-end dialog system platform . it allows researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments.
Approach:	They propose to use an open-source multi-domain end-to-end dialog system platform to train and evaluate dialog bots in common environments.
Outcome:	The proposed system enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches in common environments.

Copied to clipboard

Xiao Wang, Qin Liu, Tao Gui, Qi Zhang, Yicheng Zou, Xin Zhou, Jiacheng Ye, Yongxin Zhang, Rui Zheng, Zexiong Pang, Qinzhuo Wu, Zhengyan Li, Chong Zhang, Ruotian Ma, Zichu Fei, Ruijian Cai, Jun Zhao, Xingwu Hu, Zhiheng Yan, Yiding Tan, Yuan Hu, Qiyuan Bian, Zhihua Liu, Shan Qin, Bolin Zhu, Xiaoyu Xing, Jinlan Fu, Yue Zhang, Minlong Peng, Xiaoqing Zheng, Yaqian Zhou, Zhongyu Wei, Xipeng Qiu, Xuanjing Huang