Papers by Ning Li

Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings (2025.acl-long)

Challenge:	Document-level event argument extraction (EAE) is a critical task in natural language processing.
Approach:	They propose an LLM-driven HiErarchical Rule Optimization framework that iteratively generates and selects optimal hierarchical rules.
Outcome:	The proposed framework outperforms few-shot supervised methods and outperformed state-of-the-art prompting baselines.

Copied to clipboard

Tengyu Pan, Zhichao Duan, Zhenyu Li, Bowen Dong, Ning Liu, Xiuxing Li, Jianyong Wang

Representation Learning

Challenge:	Text embedding models are used for various natural language processing tasks such as sentiment analysis, text clustering, and content-based information retrieval.
Approach:	They propose a synthesis framework that leverages large language models to generate diverse negative samples with varying levels of similarity with the query.
Outcome:	The proposed framework achieves state-of-the-art performance surpassing existing synthesis strategies with synthetic data and when combined with public retrieval datasets.

Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization (2026.findings-acl)

Copied to clipboard

Yueyang Cang, Xiaoteng Zhang, Erlu Zhao, Zehua Ji, Yuhang Liu, Yuchen He, Zhiyuan Ning, Chen Yijun, Wenge Que, Li Shi

Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification (2022.acl-long)

Challenge:	Recent approaches to optimize communication topology rely on single-sample policy gradients with absolute rewards.
Approach:	They propose a topology optimization framework that integrates Group Relative Policy Optimization.
Outcome:	The proposed topology optimization framework outperforms state-of-the-art methods on reasoning and code generation benchmarks.

Copied to clipboard

Shengding Hu, Ning Ding, Huadong Wang, Zhiyuan Liu, Jingang Wang, Juanzi Li, Wei Wu, Maosong Sun

An LLM-Embedding Semantic Adaptation Network for Post-level Semantic Drift Evaluation (2026.findings-acl)

Challenge:	Recent studies suggest that pre-trained language models have gained rich knowledge during pre-training.
Approach:	They propose to tune pre-trained language models with task-specific prompts to improve and stabilize prompttuning.
Outcome:	Extensive experiments on zero and few-shot text classification tasks show that prompt-tuning improves and stabilizes prompttun-ing.

Copied to clipboard

Ning Chen, Mingyu Kang, Jie Li, Linyuan Lü

Representation Learning

Challenge:	Evaluating semantic drift is essential for understanding discourse evolution and opinion formation in online discussions.
Approach:	They propose an LLM-embedding Semantic Adaptation Network to evaluate semantic drift . they use an LRU module, an LEM-Embedding graph convolutional network module and an adaptive fusion module to integrate features from event related posts.
Outcome:	The proposed model achieves state-of-the-art performance on the semantic drift evaluation task compared to baseline models.

CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding (2021.acl-long)

Copied to clipboard

Dong Wang, Ning Ding, Piji Li, Haitao Zheng

Generating Fluent Adversarial Examples for Natural Languages (P19-1)

Challenge:	Pre-trained language models are vulnerable to simple perturbations, causing poor robustness . recent studies show that adversarial training is useless or harmful for the model to detect these semantic changes.
Approach:	They propose to use adversarial training to improve the robustness of pre-trained models . they propose to construct negative examples with similar and opposite semantics .
Outcome:	Empirical results show that the proposed approach improves on sentiment analysis, reasoning, and reading comprehension tasks.

Copied to clipboard

Huangzhao Zhang, Hao Zhou, Ning Miao, Lei Li

Robustness in NLP

Challenge:	Current methods for building adversarial attackers for NLP are inefficient as the gradient is discarded.
Approach:	They propose an adversarial attacker which performs Metropolis-Hastings sampling with the guidance of gradients to solve these problems.
Outcome:	The proposed algorithm outperforms the baseline model on attacking capability on IMDB and SNLI.

ClusterAttn: KV Cache Compression under Intrinsic Attention Clustering (2025.acl-long)

Copied to clipboard

Minwei Zhang, Haifeng Sun, Jingyu Wang, Shaolong Li, Wanyi Ning, Qi Qi, Zirui Zhuang, Jianxin Liao

Factorized Learning Assisted with Large Language Model for Gloss-free Sign Language Translation (2024.lrec-main)

Challenge:	Existing methods for sparse attention apply the same pattern across different attention heads and inputs, but fail to capture the intrinsic attention clustering in large language models.
Approach:	They propose a training-free sparse attention method that provides an efficient prompt cache compression scheme under intrinsic attention clustering for efficient LLM inference.
Outcome:	The proposed method reduces memory usage by 10%–65% and increases throughput by 2.6–4.8 times with no accuracy loss.

Copied to clipboard

Zhigang Chen, Benjia Zhou, Jun Li, Jun Wan, Zhen Lei, Ning Jiang, Quan Lu, Guoqing Zhao

Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation (2020.acl-main)

Challenge:	Previous Sign Language Translation methods have relied on gloss annotations to improve performance, but labeling high-quality glosses is labor-intensive and inefficient.
Approach:	They propose to integrate Large Language Model (LLM) into SLT by factorizing learning into two stages to improve the learning curve.
Outcome:	The proposed approach improves on three SLT datasets conducted under the gloss-free setting.

Copied to clipboard

Arya D. McCarthy, Xian Li, Jiatao Gu, Ning Dong

Machine Translation

Challenge:	Existing variational inference models ignore their latent variables, a phenomenon called posterior collapse.
Approach:	They propose a new loss function for conditional variational autoencoders that counteracts posterior collapse by using a modified evidence lower bound objective and a factorized decoder.
Outcome:	The proposed model yields improved translation quality compared to existing models on WMT RoEn and DeEn.

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension (2022.acl-long)

Copied to clipboard

Huibin Zhang, Zhengkun Zhang, Yao Zhang, Jun Wang, Yufan Li, Ning Jiang, Xin Wei, Zhenglu Yang

LongTutor: Benchmarking Large Language Models for Long-term Personalized Tutoring (2026.acl-long)

Challenge:	Procedural Multimodal Documents organize textual instructions and corresponding images step by step.
Approach:	They propose a novel temporal-modal entity Graph for comprehending PMDs . they propose encoding and reasoning modules to capture textual and visual entities .
Outcome:	The proposed model can capture textual and visual entities and trace their temporal-modal evolution.

Copied to clipboard

Ning Li, Zheng Zhang, Zhenya Huang, Rui Li, Yi Zhan, Yinbo Luo, Qi Liu, Enhong Chen

Counterfactual Adversarial Learning with Representation Interpolation (2021.findings-emnlp)

Challenge:	Existing evaluations focus on isolated, short-term interactions, overlooking the inherently long-term nature of learning.
Approach:	They propose a benchmark for long-term personalized tutoring based on an annotated learning log . they propose an automated generator–verifier pipeline to enable benchmark expansion .
Outcome:	The proposed benchmarks evaluate LLMs across three progressive tasks: evidence acquisition, knowledge state diagnosis, and adaptive teaching action.

Copied to clipboard

Wei Wang, Boxin Wang, Ning Shi, Jinfeng Li, Bingyu Zhu, Xiangyu Liu, Rong Zhang

Robustness in NLP

Challenge:	Existing models with statistical bias are prone to memorized correlations . large pre-trained models such as BERT have revolutionized the model development paradigm in natural language processing .
Approach:	They propose a framework to tackle the problem from a causal perspective using a latent space interpolation approach.
Outcome:	Extensive experiments show that CAT achieves substantial performance improvement over SOTA across different downstream tasks, including sentence classification, natural language inference and question answering.

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning (2025.emnlp-main)

Copied to clipboard

Lang Cao, Yingtian Zou, Chao Peng, Renhong Chen, Wu Ning, Yitong Li

MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models (2026.findings-acl)

Challenge:	Existing approaches to improve mathematical reasoning require extensive datasets for training or depend on few-shot methods that compromise computational accuracy.
Approach:	They propose a training-free adaptation framework that efficiently equips general-purpose pre-trained language models with enhanced mathematical reasoning capabilities.
Outcome:	The proposed framework outperforms Qwen2.5-72B-Math-Instruct on MMLU-STEM with a score of 90.9%, compared to 87.3%.

Copied to clipboard

Kailin Jiang, Ning Jiang, Yuntao Du, Yuchen Ren, Yuchen Li, Yifan Gao, Jinhe Bi, Yunpu Ma, Bin Li, Lei Liu, Qing Li

When Efficiency Becomes a Vulnerability: Computational Cost Attacks on WebAgents (2026.acl-long)

Challenge:	Existing benchmarks for Large Multimodal Models (LMMs) are constrained by static representations, inadequately evaluating their ability to understand time-sensitive knowledge.
Approach:	They propose a benchmark containing 2,104 time-sensitive knowledge samples spanning six knowledge types to evaluate temporal awareness along 6 key dimensions and 11 challenging tasks.
Outcome:	The proposed benchmark measures temporal awareness along 6 key dimensions and 11 tasks, while most open-source LMMs still lack time understanding ability.

Copied to clipboard

Liang-Bo Ning, Yuchen Zhu, Heqing Huang, Xin Wang, Yi Chang, Li Qing, Wenqi Fan

Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models (2025.findings-acl)

Challenge:	Existing WebAgents suffer from computational cost attacks due to long reasoning processes and excessive computational cost.
Approach:	They propose a framework that generates adversarial prompts and a reinforcement learning-enhanced selector to identify the most effective perturbations.
Outcome:	The proposed framework exploits large language models to generate diverse adversarial prompts and a reinforcement learning–enhanced selector to identify the most effective perturbations.

Copied to clipboard

Huangyw Huangyw, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao

CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations (2025.findings-acl)

Challenge:	Existing methods, such as a n-terminal coding, do not provide accurate data for large language models.
Approach:	They propose a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding.
Outcome:	Experiments on open-book QA datasets show that DAGCD improves faithfulness and robustness while preserving computational efficiency.

Copied to clipboard

Xiaohu Li, Yunfeng Ning, Zepeng Bao, Mayi Xu, Jianhao Chen, Tieyun Qian

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data (2026.acl-long)

Challenge:	Existing studies have isolated LLM jailbreak attacks and defenses . a new framework combines attack and defense to protect against malicious queries .
Approach:	They propose a framework that combines attack and defense to protect the Large Language Model (LLM) by embedding harmful problems into the safe area.
Outcome:	The proposed framework achieves an average jailbreak success rate of 88.85% across three popular LLMs while the defense success rate reaches an average of 84.17%.

Copied to clipboard

Shiping Yang, Jie Wu, Wenbiao Ding, Ning Wu, Shining Liang, Ming Gong, Hongzhi Li, Hengyuan Zhang, Angel X. Chang, Dongmei Zhang

Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring (2026.acl-long)

Challenge:	Existing studies on robustness to explicit noise (e.g., document semantics) but overlook implicit noise (spurious features).
Approach:	They propose a framework to quantify the robustness of RAGs against spurious features by integrating a data synthesis pipeline and a taxonomy.
Outcome:	The proposed framework quantifies the robustness of RALMs against spurious features.

Copied to clipboard

Peichun Hua, Hao Li, Shanghao Shi, Zhiyuan Yu, Ning Zhang

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection (2024.emnlp-main)

Challenge:	Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating a generalizable defense that is efficient for practical deployment.
Approach:	They propose a framework that uses a lightweight projection to separate benign and malicious inputs in safety-critical layers.
Outcome:	The proposed framework enables a simple yet powerful contrastive score that differentiates true malicious intent from mere distribution shift.

Copied to clipboard

Bin Lin, Yang Ye, Bin Zhu, Jiaxi Cui, Munan Ning, Peng Jin, Li Yuan

Event-Centric Natural Language Processing (2021.acl-tutorials)

Challenge:	Existing approaches to visual-language understanding lack unified tokenization for images and videos . lack of unified visual representations makes it difficult to learn multi-modal interactions from poor projection layers.
Approach:	They propose to unify visual representation into the language feature space to advance the foundational LLM towards a unified LVLM.
Outcome:	The proposed model outperforms Video-ChatGPT on image benchmarks and on 9 image benchmark benchmarks.

Copied to clipboard

Muhao Chen, Hongming Zhang, Qiang Ning, Manling Li, Heng Ji, Kathleen McKeown, Dan Roth

Challenge:	This tutorial will provide an introduction to various methods for automating the extraction, conceptualization and prediction of events and their relations.
Approach:	This tutorial will provide an introduction to various methods for automating events and their relations, and a wide range of NLU and commonsense understanding tasks.
Outcome:	This tutorial will provide an introduction to various methods for automating extraction, conceptualization and prediction of events and their relations, and a wide range of NLU and commonsense understanding tasks.

LongLeader: A Comprehensive Leaderboard for Large Language Models in Long-context Scenarios (2025.naacl-long)

Copied to clipboard

Pei Chen, Hongye Jin, Cheng-Che Lee, Rulin Shao, Jingfeng Yang, Mingyu Zhao, Zhaoyu Zhang, Qin Lu, Kaiwen Men, Ning Xie, Huasheng Li, Bing Yin, Han Li, Lingyun Wang

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

Challenge:	LongLeader aims to assess different LLMs' long-context comprehension abilities . long-constext comprehension is a key bottleneck for many use cases .
Approach:	They propose a leaderboard to assess different LLMs' long-context comprehension abilities . they offer open-source access to the benchmarks and maintain a dedicated website .
Outcome:	The proposed model assesses different LLMs on selected benchmarks and provides open-source access to the benchmarks.

Copied to clipboard

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

Multi-Stage LLM Fine-Tuning with a Continual Learning Setting (2025.findings-naacl)

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

Copied to clipboard

Changhao Guan, Chao Huang, Hongliang Li, You Li, Ning Cheng, Zihe Liu, Yufeng Chen, Jinan Xu, Jian Liu

ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning (2026.acl-long)

Challenge:	Large language models (LLMs) have made significant progress in knowledge-intensive applications, but they may face a multi-stage continuous learning scenario.
Approach:	They propose a multi-stage continuous learning paradigm that includes a preference-based learning bias to identify potential knowledge conflicts and a self-distillation-based data augmentation strategy to expand and enrich the training corpus.
Outcome:	The proposed learning paradigm achieves a significant improvement in accuracy after 7 stages of fine-tuning compared to previous methods while preserving general knowledge.

Copied to clipboard

Jiani Huang, Shijie Wang, Liang-Bo Ning, Wenqi Fan, Li Qing

Decoder Tuning: Efficient Language Understanding as Decoding (2023.acl-long)

Challenge:	Existing reasoning-augmented systems that handle complex queries are lacking . we present a framework that enhances LLM-based recommendation assistants .
Approach:	They propose a reinforcement fine-tuning framework that enhances LLM-based recommendation . they use a dual-graph Enhanced Reward Shaping framework to integrate recommendation metrics .
Outcome:	The proposed framework outperforms state-of-the-art recommendations and preserves core abilities.

Copied to clipboard

Ganqu Cui, Wentao Li, Ning Ding, Longtao Huang, Zhiyuan Liu, Maosong Sun

Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasks (2025.findings-acl)

Challenge:	Existing approaches to adapt pre-trained models with parameters frozen are based on input-side adaptation, which requires thousands of API queries.
Approach:	They propose to train a model-as-a-service (MaaS) setting to provide only the inference APIs for users . they argue that input-side adaptation could be arduous due to the lack of gradient signals .
Outcome:	The proposed model outperforms state-of-the-art algorithms with a 200x speed-up.

Copied to clipboard

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lyu, Daxiang Dong

Programming Languages in NLP

Challenge:	Effectively and efficiently handling complex realworld problems has become a key focus across industry and academia.
Approach:	They propose a tree-of-code framework that generates nodes through self-supervision and combines prompt and model exploration in a GT-free setting.
Outcome:	Experiments on two datasets with ten popular zero-shot LLMs show that Tree-of-Code boosts accuracy by nearly 20% over CodeAct with fewer than 1/4 turns.

Extracting Financial Events from Raw Texts via Matrix Chunking (2024.lrec-main)

Copied to clipboard

Yusheng Huang, Ning Hu, Kunping Li, Nan Wang, Zhouhan Lin

Chunking

Challenge:	Event Extraction (EE) is widely used in the Chinese financial field to provide valuable structured information.
Approach:	They propose a task which extracts financial events from raw texts and an efficient method called MACK.
Outcome:	The proposed method is fault-tolerant and can visualize interactions among text components.

Don’t Trust ChatGPT when your Question is not in English: A Study of Multilingual Abilities and Types of LLMs (2023.emnlp-main)

Copied to clipboard

Xiang Zhang, Senyu Li, Bradley Hauer, Ning Shi, Grzegorz Kondrak

Multilinguality

Challenge:	Existing studies have shown that large language models can perform a wide variety of language tasks when presented in English.
Approach:	They propose a method to evaluate the multilingual capabilities of large language models using a prompt back-translation method to find out how LLMs acquire their multilingual abilities.
Outcome:	The proposed method shows that large language models can transfer learned knowledge across different languages, but struggle to provide accurate results in translation-variant tasks.

Do you have the right scissors? Tailoring Pre-trained Language Models via Monte-Carlo Methods (2020.acl-main)

Copied to clipboard

Ning Miao, Yuxuan Song, Hao Zhou, Lei Li

Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning (2026.findings-acl)

Challenge:	Pre-trained language models can be fine-tuned on task-specific datasets, but fine-timing can lead to over- and/or under-estimation problems.
Approach:	They propose a method to transfer probability mass from over-estimated regions to under-estimates by truncating and transferring probability mass between over- and under-estimating regions.
Outcome:	The proposed method outperforms the fine-tuning approach on a variety of datasets.

Copied to clipboard

Jie Deng, Hanshuang Tong, Jun Li, Shining Liang, Ning Wu, Hongzhi Li, Yutao Xie

From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning (2024.naacl-long)

Challenge:	Large language models (LLMs) fine-tuned using rejection sampling retain only correct reasoning trajectories . however, this paradigm treats supervision as a binary filter that systematically excludes teacher-generated errors, leaving a gap in how reasoning failures are modeled during training.
Approach:	They propose a fine-tuning strategy that reframes rejection sampling as a structured supervision construction process.
Outcome:	The proposed approach outperforms RFT on multiple math benchmarks while retaining only correct reasoning trajectories.

Copied to clipboard

Ming Li, Yong Zhang, Zhitao Li, Jiuhai Chen, Lichang Chen, Ning Cheng, Jianzong Wang, Tianyi Zhou, Jing Xiao

GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extraction (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) have revolutionized the landscape of artificial intelligence.
Approach:	They propose a self-guided method to identify and select cherry samples from open-source datasets, minimizing manual curation and potential cost for instruction tuning an LLM.
Outcome:	The proposed method enables LLMs to identify discrepancies between expected responses and intrinsic generation capability, and a marked uptick in model training efficiency.

Copied to clipboard

Jie Zhao, Wanting Ning, Yuxiao Fei, Yubo Feng, Lishuang Li

GraphDx: A Cost-Aware Knowledge-Enhanced Multi-Agent Framework for Sequential Diagnosis (2026.findings-acl)

Challenge:	Existing approaches to analyzing large language models are limited by their pre-trained knowledge of Small Language Models(SLMs).
Approach:	They propose a global distance-aware modeling approach based on Large Language Models (LLMs) they first present a distance-based graph structure utilizing Graph Attention Network(GAT)
Outcome:	The proposed approach significantly improves minority relation class learning ability on two publicly available datasets, TB-Dense and MATRES.

Copied to clipboard

Shaoting Tan, Ning Liu, Yuntao Du, Shuyue Wei, Wu Shuai, Qian Li, Yanyu Xu, Wei Zhang, Lizhen Cui, Haitao Yuan

On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference (2026.acl-long)

Challenge:	Existing Large Language Models struggle to reason systematically under cost constraints . Existing approaches lack the knowledge-reasoning capability to reason under cost .
Approach:	They propose a knowledge-enhanced framework that leverages large language models to construct MDKGs . they propose three collaborative agents that handle language understanding and generation .
Outcome:	GraphDx improves diagnostic success rates from 50–68% to 79–93% while reducing test costs by 20–54%.

Copied to clipboard

Zhengyi Li, Yakai Wang, Jingwen Leng, Kang Yang, Yu Yu, Jiaping Gui, Yu Feng, Ning Liu, Minyi Guo

MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction (2022.emnlp-main)

Challenge:	Existing work reveals only randomly permuted activations to the client, allowing adversaries to extract model weights.
Approach:	They propose an attack that aligns differently shuffled activations to a common permutation and exploits them to extract model weights.
Outcome:	The proposed attack can align shuffled activations to a common permutation and exploit them to extract model weights with a query cost of approximately $1.

Copied to clipboard

Xiaozhi Wang, Yulin Chen, Ning Ding, Hao Peng, Zimu Wang, Yankai Lin, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie Zhou

Information Extraction & Text Mining

Challenge:	Existing datasets only cover limited relation types at once, which prevents models from taking full advantage of relation interactions.
Approach:	They construct a large-scale human-annotated ERE dataset with improved annotation schemes to address these drawbacks.
Outcome:	The proposed dataset is larger than existing datasets of all the ERE tasks by at least an order of magnitude.

PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter (2023.emnlp-main)

Copied to clipboard

Haoyan Yang, Zhitao Li, Yong Zhang, Jianzong Wang, Ning Cheng, Ming Li, Jing Xiao

Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)

Challenge:	Large Language Models (LLMs) are too large to be fine-tuned with budget constraints and some are only accessible via APIs.
Approach:	They propose a pluggable Reward-Driven Contextual Adapter that integrates large language models as generators and trains them to refine the retrieved information.
Outcome:	The proposed method improves ReQA performance on three datasets by up to 20% compared to existing methods.

Copied to clipboard

Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao

CODIS: Benchmarking Context-dependent Visual Comprehension for Multimodal Large Language Models (2024.acl-long)

Challenge:	Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs .
Approach:	They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained .
Outcome:	The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency.

Copied to clipboard

Fuwen Luo, Chi Chen, Zihao Wan, Zhaolu Kang, Qidong Yan, Yingjie Li, Xiaolong Wang, Siyu Wang, Ziyue Wang, Xiaoyue Mi, Peng Li, Ning Ma, Maosong Sun, Yang Liu

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

Challenge:	Multimodal large language models have demonstrated promising results in a variety of tasks that combine vision and language.
Approach:	They propose a benchmark to assess the ability of models to use contextual information in free-form text to enhance visual comprehension.
Outcome:	The proposed model fails to extract and utilize contextual information to improve understanding of images.

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

Chinese Relation Extraction with Multi-Grained Information and External Linguistic Knowledge (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

Ziran Li, Ning Ding, Zhiyuan Liu, Haitao Zheng, Ying Shen

Knowledge Representation

Challenge:	Existing methods for Chinese relation extraction suffer from segmentation errors and ambiguity of polysemy.
Approach:	They propose a multi-grained lattice framework for Chinese relation extraction . they incorporate word-level information into character sequence inputs to avoid segmentation errors .
Outcome:	The proposed model outperforms existing models on three real-world datasets in distinct domains.

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning (2024.acl-long)

Copied to clipboard

Ming Li, Yong Zhang, Shwai He, Zhitao Li, Hongyu Zhao, Jianzong Wang, Ning Cheng, Tianyi Zhou

HqeKV: Towards Hybrid Quantization and Eviction for KV Cache in Long-Context LLM Inference (2026.findings-acl)

Challenge:	Earlier studies of instruction tuning on Large Language Models focus on creating large, varied, and high-quality datasets with responses curated by human experts.
Approach:	They propose to use a smaller and weaker model to fine tune a larger and stronger model . they find it can largely speed up the data filtering and improve performance .
Outcome:	The proposed model can filter instruction data faster and better on benchmarks.

Copied to clipboard

He Wang, Yu Gu, Fangfang Li, Zhigang Wang, Zhenghao Liu, Ning Wang, Xiaohua Li, Ge Yu

Challenge:	autoregressive inference requires repeated computation across transformer layers.
Approach:	They propose a hybrid compression framework built on both quantization and eviction . they propose varying importance metric and flexible conversion policies to reduce memory overhead .
Outcome:	The proposed framework outperforms state-of-the-art methods under memory constraints.

UltraIF: Advancing Instruction Following from the Wild (2025.emnlp-main)

Copied to clipboard

Kaikai An, Li Sheng, Ganqu Cui, Shuzheng Si, Ning Ding, Yu Cheng, Baobao Chang

AutoFigure-Edit: Generating Editable Scientific Illustrations via Reference-Guided Styling (2026.acl-demo)

Challenge:	a lack of transparency has resulted in a gap between research community and leading companies . large language models have demonstrated remarkable capabilities in following complex instructions .
Approach:	They propose a method to build large language models that can follow complex instructions with open-source data.
Outcome:	The proposed approach can synergize complex instructions and filter responses with evaluation questions.

Copied to clipboard

Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, QiYao Sun, Enhao Gu, Yiran Ding, Ke Sun, Fang Guo, Panzhong Lu, Zhiyuan Ning, Yixuan Weng, Yue Zhang

Green & Sustainable NLP

Challenge:	Existing automated systems for scientific illustrations are limited in editability, stylistic controllability, and efficiency.
Approach:	They propose an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images.
Outcome:	The proposed system generates fully editable scientific illustrations from long-form scientific texts while enabling flexible style adaptation through user-provided reference images.

Prompt-learning for Fine-grained Entity Typing (2022.findings-emnlp)

Copied to clipboard

Ning Ding, Yulin Chen, Xu Han, Guangwei Xu, Xiaobin Wang, Pengjun Xie, Haitao Zheng, Zhiyuan Liu, Juanzi Li, Hong-Gee Kim

Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification (2026.findings-acl)

Challenge:	Extensive experiments on fine-grained entity typing under fully supervised, few-shot, and zero-shot settings show the effectiveness of prompt-learning.
Approach:	They propose a prompt-learning pipeline that stimulates versatile knowledge of pre-trained language models (PLMs) by constructing entity-oriented verbalizers and templates and conducting masked language modeling.
Outcome:	The proposed approach can be applied to fine-grained entity typing in fully supervised, few-shot, and zero-shot scenarios.

Copied to clipboard

Xiangtao Meng, Yingkai Dong, Ning Yu, Li Wang, Zheng Li, Shanqing Guo

ControlMath: Controllable Data Generation Promotes Math Generalist Models (2024.emnlp-main)

Challenge:	Existing safety defenses typically intervene internally within the generative model, but suffer from severe concept entanglement, leading to degradation of benign generation quality.
Approach:	They propose a structurally isolated safety module that performs external, interpretable rectification without modifying the base model.
Outcome:	The proposed module performs external, interpretable rectification without modifying the base model.

Copied to clipboard

Nuo Chen, Ning Wu, Jianhui Chang, Linjun Shou, Jia Li

GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression (2025.emnlp-main)

Challenge:	Currently, mathematical reasoning is one of the most challenging areas for closed-source LLMs.
Approach:	They propose an iterative method involving an equation-generator module and two LLM-based agents that generate diverse equations and transform them into math word problems.
Outcome:	The proposed method enables the generation of diverse math problems, not limited to specific domains or distributions.

Copied to clipboard

Kainan Liu, Yong Zhang, Ning Cheng, Zhitao Li, Shaojun Wang, Jing Xiao

Green & Sustainable NLP

Challenge:	Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing these layers to reduce inference cost.
Approach:	They propose a framework that removes redundant layers to reduce inference cost by preserving sensitivity-aware singular values.
Outcome:	The proposed framework outperforms existing methods in 90% of the original model under a 20% compression ratio.

Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations (2024.findings-emnlp)

Copied to clipboard

Nuo Chen, Zinan Zheng, Ning Wu, Ming Gong, Dongmei Zhang, Jia Li

RoChBert: Towards Robust BERT Fine-tuning for Chinese (2022.findings-emnlp)

Challenge:	Existing research focuses on developing powerful large language models for mathematical reasoning within monolingual languages.
Approach:	They propose to use translation to build powerful multilingual math reasoning models . they propose different training strategies to build xMR LLMs that outperform open-source LLM .
Outcome:	The proposed model outperforms open-source LLMs and surpasses ChatGPT in few-shot scenarios.

Copied to clipboard

Zihan Zhang, Jinfeng Li, Ning Shi, Bo Yuan, Xiangyu Liu, Rong Zhang, Hui Xue, Donghong Sun, Chao Zhang

Temporal Cognitive Tree: A Hierarchical Modeling Approach for Event Temporal Relation Extraction (2024.findings-emnlp)

Challenge:	Pre-trained language models (e.g., BERT) have been proved vulnerable to adversarial texts.
Approach:	They propose to fuse Chinese phonetic and glyph features into pre-trained models by using a more comprehensive adversarial graph.
Outcome:	The proposed framework outperforms existing methods in significant ways on a wide range of tasks while remaining accurate on benign texts.

Copied to clipboard

Wanting Ning, Lishuang Li, Xueyang Qin, Yubo Feng, Jingyao Tang

Information Extraction & Text Mining

Challenge:	Recent studies focus on locating relative position of event pairs on timeline . hierarchical modeling approach neglects multidimensional information in temporal relation and hierarchy of reasoning.
Approach:	They propose a novel hierarchical modeling approach that mimics human logical reasoning by introducing a Temporal Cognitive Tree.
Outcome:	The proposed model outperforms existing methods on TB-Dense and MATRES datasets.

PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free (2025.acl-long)

Copied to clipboard

Hao Li, Xiaogeng Liu, Ning Zhang, Chaowei Xiao

AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists (2025.emnlp-main)

Challenge:	Prompt injection attacks pose a critical threat to large language models, enabling goal hijacking and data leakage.
Approach:	They propose a prompt guard model that incorporates a new training strategy to mitigate over-defense for free . PIGuard significantly reduces the bias on trigger words, enabling fine-grained evaluation .
Outcome:	The proposed model outperforms the existing model on diverse benchmarks by 30.4%.

Copied to clipboard

Yifei Li, Hanane Nour Moussa, Ziru Chen, Shijie Chen, Botao Yu, Mingyi Xue, Benjamin Burns, Tzu-Yao Chiu, Vishal Dey, Zitong Lu, Chen Wei, Qianheng Zhang, Tianyu Zhang, Song Gao, Xuhui Huang, Xia Ning, Nesreen K. Ahmed, Ali Payani, Huan Sun

Event Detection with Trigger-Aware Lattice Neural Network (D19-1)

Challenge:	AutoSDT-5K is the only automatically collected and the largest open dataset for data-driven scientific discovery.
Approach:	They propose an automatic pipeline that collects high-quality coding tasks in real-world data-driven discovery workflows.
Outcome:	The proposed pipeline synthesizes accurate tasks and tasks from a dataset of 5,404 tasks covering four scientific disciplines and 756 Python packages.

Copied to clipboard

Ning Ding, Ziran Li, Zhiyuan Liu, Haitao Zheng, Zibo Lin

Information Extraction & Text Mining

Challenge:	Event detection is a key part of event extraction, but there are two issues with word-based models in languages without natural delimiters, such as Chinese.
Approach:	They propose a framework that can solve the problem of word- trigger mismatch . they also use an external knowledge base to model polysemous characters and words .
Outcome:	The proposed model outperforms state-of-the-art methods on two benchmark datasets and outperformed previous state- of-the art methods significantly.

In Search of the Long-Tail: Systematic Generation of Long-Tail Inferential Knowledge via Logical Rule Guided Search (2024.emnlp-main)

Copied to clipboard

Huihan Li, Yuting Ning, Zeyi Liao, Siyuan Wang, Xiang Li, Ximing Lu, Wenting Zhao, Faeze Brahman, Yejin Choi, Xiang Ren

Information Retrieval

Challenge:	Logic-Induced-Knowledge-Search (LINK) is a framework for generating factually-correct yet long-tail inferential knowledge.
Approach:	They introduce a framework to obtain factually-correct yet long-tail inferential statements using variable-wise prompting grounded on symbolic rules.
Outcome:	The proposed framework is able to obtain factually-correct yet long-tail inferential statements while ensuring factual correctness.

Interactive Text-to-SQL Generation via Editable Step-by-Step Explanations (2023.emnlp-main)

Copied to clipboard

Yuan Tian, Zheng Zhang, Zheng Ning, Toby Li, Jonathan K. Kummerfeld, Tianyi Zhang

Programming Languages in NLP

Challenge:	Existing approaches to generate SQL from natural language are still making many mistakes . a new interaction mechanism allows users to edit a step-by-step explanation of a query to fix errors.
Approach:	They propose a mechanism that allows users to edit a step-by-step explanation of a query to fix errors.
Outcome:	The proposed approach can achieve better performance than multiple SOTA approaches on multiple datasets and 24 participants.

Identifying Emotional and Polar Concepts via Synset Translation (2024.starsem-1)

Copied to clipboard

Logan Woudstra, Moyo Dawodu, Frances Igwe, Senyu Li, Ning Shi, Bradley Hauer, Grzegorz Kondrak

Text Classification

Challenge:	Emotion identification and polarity classification seek to determine sentiment expressed by a writer.
Approach:	They propose a translation-based method for labeling each individual word sense and lexical concept into 20 different languages and translate them into multilingual sentiment lexicons.
Outcome:	The proposed method outperforms existing methods and is available on GitHub . it contains 12,429 emotional synsets and 15,567 polar synset.

Unified Speech-Text Pre-training for Speech Translation and Recognition (2022.acl-long)

Copied to clipboard

Yun Tang, Hongyu Gong, Ning Dong, Changhan Wang, Wei-Ning Hsu, Jiatao Gu, Alexei Baevski, Xian Li, Abdelrahman Mohamed, Michael Auli, Juan Pino

Text Generation

Challenge:	Existing methods to pre-train speech and text use unlabeled data to learn universal feature representations.
Approach:	They propose a method to jointly pre-train speech and text in an encoder-decoder modeling framework for speech translation and recognition.
Outcome:	The proposed method achieves between 1.7 and 2.3 BLEU improvement above the state of the art on the MuST-C speech translation dataset and comparable WERs to wav2vec 2.0 on the Librispeech speech recognition task.

Structured Optimal Brain Pruning for Large Language Models (2024.emnlp-main)

Copied to clipboard

Jiateng Wei, Quan Lu, Ning Jiang, Siqi Li, Jingyang Xiang, Jun Chen, Yong Liu

Is Parameter Collision Hindering Continual Learning in LLMs? (2025.coling-main)

Challenge:	Existing pruning methods for Large Language Models rely on unstructured pruning or require special hardware to accelerate computation.
Approach:	They propose a retraining-free structured pruning method called SoBP . they evaluate the effectiveness of SoBP across 14 models from 3 LLM families .
Outcome:	The proposed method outperforms current state-of-the-art pruning methods on 8 datasets.

Copied to clipboard

Shuo Yang, Kun-Peng Ning, Yu-Yang Liu, Jia-Yu Yao, Yong-Hong Tian, Yi-Bing Song, Li Yuan

Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding (2024.findings-acl)

Challenge:	Existing methods to learn multiple tasks in parallel often lead to catastrophic forgetting, resulting in overwriting knowledge.
Approach:	They propose a non-collision low-rank Adaptation approach that leverages low collision rates to enhance continual learning (CL) in large language models.
Outcome:	The proposed approach achieves better task orthogonality and higher task orthognality than existing SOTA methods.

Copied to clipboard

Hanling Yi, Feng Lin, Hongbin Li, Ning Peiyang, Xiaotian Yu, Rong Xiao