Papers by Qi Liu

Through the MUD: A Multi-Defendant Charge Prediction Benchmark with Linked Crime Elements (2024.acl-long)

Challenge:	Existing domain-specific knowledge of domain-related tasks is lacking in pre-trained language models.
Approach:	They propose a domain-adaptation method which can dynamically select domain-specific tokens and guide the discriminator to emphasize them, without introducing new training parameters.
Outcome:	The proposed method can capture domain-specific knowledge of domain-related tasks without introducing new training parameters.

Copied to clipboard

Xiao Wei, Qi Xu, Hang Yu, Qian Liu, Erik Cambria

Towards Explainable Computerized Adaptive Testing with Large Language Model (2024.findings-emnlp)

Challenge:	Existing charge prediction datasets focus on single-defendant cases, but real-world cases involve multiple defendants.
Approach:	They propose a benchmark that encompasses legal cases involving multiple defendants . they develop an interpretable model called EJudge that incorporates crime elements and legal rules to infer charges.
Outcome:	The proposed model outperforms state-of-the-art models in predicting crime charges while providing corresponding rationales.

Copied to clipboard

Cheng Cheng, GuanHao Zhao, Zhenya Huang, Yan Zhuang, Zhaoyuan Pan, Qi Liu, Xin Li, Enhong Chen

Explainability & Interpretability in NLP

Challenge:	Existing methods focus on minimizing the number of questions required to assess ability, lacking clear and reliable explanations for the question selection process.
Approach:	They propose to use large language models to enhance computer adaptive testing (CAT) by providing human-like interpretability and explanations.
Outcome:	The proposed agent-based CAT performs comparably or superior to traditional CAT methods in accuracy and significantly improves student trust and satisfaction.

Optimizing Code Retrieval: High-Quality and Scalable Dataset Annotation through Large Language Models (2024.emnlp-main)

Copied to clipboard

Rui Li, Qi Liu, Liyang He, Zheng Zhang, Hao Zhang, Shengyu Ye, Junyu Lu, Zhenya Huang

Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQL (2025.acl-long)

Challenge:	Existing methods for code retrieval struggle to balance scalability and annotation quality.
Approach:	They propose a method that integrates functions called within the repository and information on third-party APIs to enhance the annotation context.
Outcome:	The proposed method improves the annotation context by incorporating functions called within the repository and information on third-party API functionalities.

Copied to clipboard

Hanbing Liu, Haoyang Li, Xiaokang Zhang, Ruotong Chen, Haiyong Xu, Tian Tian, Qi Qi, Jing Zhang

GLoCIM: Global-view Long Chain Interest Modeling for news recommendation (2025.coling-main)

Challenge:	Direct Preference Optimization (DPO) is effective in complex reasoning tasks like math word problems and code generation, but Text-to-SQL datasets often include only final answers (gold SQL queries) without detailed CoT solutions.
Approach:	They found that Direct Preference Optimization (DPO) is crucial for unlocking DPO's potential by augmenting Text-to-SQL datasets with synthetic CoT solutions.
Outcome:	The proposed method achieves consistent and significant performance improvements on Text-to-SQL datasets.

Copied to clipboard

Zhen Yang, Wenhui Wang, Tao Qi, Peng Zhang, TianYun Zhang, Ru Zhang, Jianyi Liu, Yongfeng Huang

Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play (2022.findings-emnlp)

Challenge:	Recent efforts to extract local subgraph information from click graphs have hindered collaboratively utilizing global click graph information.
Approach:	They propose a global-view long chain interests model that models a click graph with neighbor interest to enhance news recommendation.
Outcome:	The proposed method surpasses baseline methods on two real-world datasets.

Copied to clipboard

Qi Liu, Zihuiwen Ye, Tao Yu, Linfeng Song, Phil Blunsom

VLA-Mark: A cross modal watermark for large vision-language alignment models (2025.emnlp-main)

Challenge:	Numerous architectures and pretraining methods have been proposed for context-dependent text-to-SQL, but the size of the datasets used has been limited due to the high cost of annotating multi-turn dialogue and SQL pairs.
Approach:	They propose to augment training datasets using self-play which leverages contextual information to synthesize new interactions to adapt the model to new databases.
Outcome:	The proposed model improves accuracy on SParC and CoSQL, two widely used cross-domain text-to-SQl datasets.

Copied to clipboard

Shuliang Liu, Zheng Qi, Jesse Jiaxi Xu, Yibo Yan, Junyan Zhang, He Geng, Aiwei Liu, Peijie Jiang, Jia Liu, Yik-Cheung Tam, Xuming Hu

Sentence-State LSTM for Text Representation (P18-1)

Challenge:	Existing text watermarking methods disrupt visual-textual alignment, leaving semantic-critical concepts vulnerable.
Approach:	They propose a vision-aligned framework that embeds detectable watermarks into outputs . they combine localized patch affinity, global semantic coherence, contextual attention patterns .
Outcome:	The proposed framework shows lower PPL and higher BLEU than conventional methods with near-perfect detection (98.8% AUC).

Copied to clipboard

Yue Zhang, Qi Liu, Linfeng Song

ParaMac: A General Unsupervised Paraphrase Generation Framework Leveraging Semantic Constraints and Diversifying Mechanisms (2022.findings-emnlp)

Challenge:	LSTMs have been shown to suffer from various limitations due to their sequential nature.
Approach:	They propose to model hidden states of all words simultaneously at each recurrent step rather than one word at a time.
Outcome:	The proposed model has strong representation power, giving competitive performances compared to stacked BiLSTM models with similar parameter numbers.

Copied to clipboard

Jinxin Liu, Jiaxin Shi, Ji Qi, Lei Hou, Juanzi Li, Qi Tian

Feature Projection for Improved Text Classification (2020.acl-main)

Challenge:	Existing unsupervised methods for paraphrase generation are weak in semantic equivalence or expression diversity.
Approach:	They propose a framework for unsupervised paraphrase generation that employs multi-aspect equivalence constraints and multi-granularity diversifying mechanisms to achieve good semantic equvalence and expressive diversity.
Outcome:	The proposed framework achieves 9.1% and 3.3% absolute gains over previous SOTA on Quora and MSCOCO and can improve to 18.0% and 4.6% on GLUE.

Copied to clipboard

Qi Qin, Wenpeng Hu, Bing Liu

Text Classification

Challenge:	In sentiment classification, there are some good features that are indicative of class labels, but there are also many common features that do not discriminate for classification.
Approach:	They propose to project existing features into the orthogonal space of the common features and make them more discriminative for classification.
Outcome:	The proposed method improves CNN, RNN, Transformer, and Bert based text classification and obtains markedly better results.

Large Language Models are not Fair Evaluators (2024.acl-long)

Copied to clipboard

Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui

DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections (2026.findings-acl)

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

Haebin Shin, Lei Ji, Xiao Liu, Zhiwei Yu, Hyunwoo Yoo, Qi Chen, Yeyun Gong

Challenge:	Several studies rely on additional models to optimize mixtures.
Approach:	They propose a method that dynamically optimizes instruction-tuning dataset mixtures by prior-scaled Boltzmann Exploration and a multi-armed bandit setup.
Outcome:	The proposed method improves the TÜLU-2-mixture and TÜLO-3-mixtures across 10 benchmarks while introducing minimal computational overhead over naive sampling.

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

Copied to clipboard

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

Towards relation extraction from speech (2022.emnlp-main)

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

Tongtong Wu, Guitao Wang, Jinming Zhao, Zhaoran Liu, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari

Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification (2025.findings-emnlp)

Challenge:	Existing methods for extracting relations from speech have been neglected due to the nature of speech.
Approach:	They propose a listening information extraction task that uses speech to extract relation extraction from speech . they use a text-to-speech system and crowd-sourced native English speakers to test the task .
Outcome:	The proposed task extracts semantic relationships from speech data using a new model . the proposed task is more challenging than the existing method due to the characteristics of speech .

Copied to clipboard

Aofan Liu, Song Shiyuan, Haoxuan Li, Cehao Yang, Yiyan Qi

MARS2: Scaling Multi-Agent Tree Search via Reinforcement Learning for Code Generation (2026.acl-long)

Challenge:	escalating complexity of modern codebases has intensified the need for code retrieval systems capable of interpreting cross-component change intents.
Approach:	RepoAlignBench is a benchmark designed to evaluate repository-level code retrieval . the benchmark proposes an adversarial reflection-augmented dual-tower architecture .
Outcome:	The proposed framework achieves 12.2% Top-5 Accuracy and 7.1% Recall improvements over state-of-the-art benchmarks.

Copied to clipboard

Pengfei Li, Shijie Wang, Fangyuan Li, Yikun Fu, Kaifeng Liu, Kaiyan Zhang, Dazhi Zhang, Yuqiang Li, Biqing Qi, Bowen Zhou

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

Challenge:	Existing approaches to reinforcement learning are decoupled from structured search due to limited trajectory diversity.
Approach:	They propose a unified RL framework that integrates multiple agents within a shared tree-structured search environment.
Outcome:	Experiments show that MARS2 improves performance across diverse model combinations and training settings.

Copied to clipboard

Yizhu Liu, Qi Jia, Kenny Zhu

FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)

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

Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev

Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training (2025.acl-long)

Challenge:	Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity.
Approach:	They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models.
Outcome:	The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models.

Copied to clipboard

Zheheng Luo, Xin Zhang, Xiao Liu, Haoling Li, Yeyun Gong, Qi Chen, Peng Cheng

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection (2024.findings-emnlp)

Challenge:	Existing methods to optimise pretraining performance have not addressed the complexities of domain-adaptive continual pretraining.
Approach:	They propose a framework that dynamically assesses learning velocity and adjusts data proportions accordingly, favouring slower learning domains while de-emphasising faster learning ones.
Outcome:	The proposed framework achieves performance gains in math and code reasoning tasks and command-line generation benchmarks.

Copied to clipboard

Tianxiang Chen, Zhentao Tan, Tao Gong, Yue Wu, Qi Chu, Bin Liu, Jieping Ye, Nenghai Yu

Challenge:	Existing methods to augment pre-trained large language models require extensive computational efforts and massive data volumes, challenging the widespread accessibility of LLM research.
Approach:	They propose a post-pretraining strategy of selectively enhancing shallow layers while pruning less effective deep ones to augment pretrained large language models.
Outcome:	The proposed approach improves performance on the corpus of code & math and a legal corpus and is widely applicable.

ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)

Copied to clipboard

Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou

Challenge:	Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth.
Approach:	They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning.
Outcome:	The proposed framework outperforms existing methods on ICLR 2025 papers.

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

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

Context-DPO: Aligning Language Models for Context-Faithfulness (2025.findings-acl)

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

Baolong Bi, Shaohan Huang, Yiwei Wang, Tianchi Yang, Zihan Zhang, Haizhen Huang, Lingrui Mei, Junfeng Fang, Zehao Li, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Shenghua Liu

TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators (2025.findings-acl)

Challenge:	Context-DPO is the first alignment method specifically designed to enhance contextfaithfulness for large language models.
Approach:	They propose a benchmark that simulates Retrieval-Augmented Generation scenarios with knowledge conflicts to evaluate context-faithfulness.
Outcome:	The proposed method improves LLMs' context-faithfulness by 35% to 280% over open-source models.

Copied to clipboard

Jianling Li, ShangZhan Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, WangHaojie WangHaojie, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun

I-AM-G: Interest Augmented Multimodal Generator for Item Personalization (2024.emnlp-main)

Challenge:	Triton is a high-level Python-like programming language for building efficient GPU kernels.
Approach:	They propose a TritonBench benchmark that provides a comprehensive evaluation of Tritonic operators on widely deployed GPUs.
Outcome:	The proposed benchmarks show that current LLMs struggle to generate efficient Triton operators on widely deployed GPUs aligned with industry applications.

Copied to clipboard

Xianquan Wang, Likang Wu, Shukang Yin, Zhi Li, Yanjiang Chen, Hufeng Hufeng, Yu Su, Qi Liu

Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization (2024.findings-acl)

Challenge:	e-commerce and recommender systems lack a framework for personalized generation . a new framework extracts tags from multimodal information of items that the user has interacted with .
Approach:	They propose a framework that extracts tags from multimodal information and rewrites item description . they then use a decoupled text-to-text and image-to image retriever to search for similar item text .
Outcome:	The proposed framework can generate results aligned with user preferences . it can be used in e-commerce and recommender systems to win over diverse user base .

Copied to clipboard

Yanghai Zhang, Ye Liu, Shiwei Wu, Kai Zhang, Xukai Liu, Qi Liu, Enhong Chen

From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM (2025.coling-main)

Challenge:	Multimodal Summarization with Multimodal Output (MSMO) is a new approach to produce a multimodal summary that integrates both text and relevant images.
Approach:	They propose an Entity-Guided Multimodal Summarization model that integrates both text and relevant images to produce a multimodal summary.
Outcome:	The proposed model integrates text-image and entity-image information and refines image selection through knowledge distillation from a pre-trained vision-language model.

Copied to clipboard

Jianyu Liu, Yi Huang, Sheng Bi, Junlan Feng, Guilin Qi

Knowledge Representation

Challenge:	Existing methods for generating follow-up questions are limited to shallow contextual questions that are uninspiring and have a large gap to the human level.
Approach:	They propose a three-stage external knowledge-enhanced follow-up question generation method which generates questions by identifying contextual topics, building a knowledge graph online, and finally combining these with a large language model to generate the final question.
Outcome:	The proposed method generates questions by identifying contextual topics, building a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question.

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

Copied to clipboard

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

On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)

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

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun

Entailment-Preserving First-order Logic Representations in Natural Language Entailment (2025.acl-long)

Challenge:	Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios.
Approach:	They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments.
Outcome:	The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings.

Copied to clipboard

Jinu Lee, Qi Liu, Runzhi Ma, Vincent Han, Ziqi Wang, Heng Ji, Julia Hockenmaier

Representation Learning

Challenge:	First-order logic (FOL) is often used to represent logical entailment, but determining natural language (NL) enanglement using FOL remains a challenge.
Approach:	They propose an Entailment-Preserving FOL representations task and a method which trains an NL-to-FOL translator by using the natural language entailment labels as verifiable rewards.
Outcome:	The proposed method achieves 1.8–2.7% improvement in EPR and 17.4–20.6% increase in E PR@16 compared to baselines in three datasets.

C-World: A Computer Use Agent Environment Creator (2026.acl-long)

Copied to clipboard

Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou

Challenge:	C-World enables users to build agent environments on demand.
Approach:	They propose a system that enables users to build agent environments on demand.
Outcome:	The proposed system outperforms baselines on 119k samples and achieves Spearman = 0.883 ranking correlation with real execution.

MAIN: Mutual Alignment Is Necessary for instruction tuning (2025.emnlp-main)

Copied to clipboard

Fanyi Yang, Jianfeng Liu, Xin Zhang, Haoyu Liu, Xixin Cao, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Qi Zhang

Discourse Heuristics For Paradoxically Moral Self-Correction (2025.findings-emnlp)

Challenge:	Instruction tuning has enabled large language models to achieve remarkable performance, yet its success heavily depends on the availability of high-quality instruction-response pairs.
Approach:	They propose a mutual alignment framework which enforces coherence between instructions and responses through mutual constraints.
Outcome:	The proposed framework generalizes well across model architectures and sizes, achieving state-of-the-art performance on LLaMA, Mistral, and Qwen models across diverse benchmarks.

Copied to clipboard

Guangliang Liu, Zimo Qi, Xitong Zhang, Kristen Johnson

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

Challenge:	moral self-correction is a promising approach for aligning output of Large Language Models with human moral values . authors show that moral self correction relies on discourse constructions that reflect heuristic shortcuts .
Approach:	a new method is proposed to strengthen moral self-correction using heuristics extracted from curated datasets.
Outcome:	a new method to strengthen moral self-correction is proposed . the proposed method is based on heuristics extracted from curated datasets.

Copied to clipboard

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

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

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

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

Explainability & Interpretability in NLP

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

Revealing and Enhancing Core Visual Regions: Harnessing Internal Attention Dynamics for Hallucination Mitigation in LVLMs (2026.findings-acl)

Copied to clipboard

Guangtao Lyu, Qi Liu, Chenghao Xu, Jiexi Yan, Muli Yang, Xueting Li, Fen Fang, Cheng Deng

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

Challenge:	Existing training-free methods are vulnerable to the attention sink phenomenon . Existing methods include contrastive decoding and auxiliary expert models .
Approach:	They propose a training-free attention intervention that constructs a PAD map to identify semantically core visual regions and applies per-head Median Absolute Deviation Scaling to adaptively control the intervention strength.
Outcome:	The proposed intervention improves visual grounding and reduces hallucinations on multiple LVLMs and benchmarks.

Copied to clipboard

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

A Web Scale Entity Extraction System (2021.findings-emnlp)

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

Xuanting Cai, Quanbin Ma, Jianyu Liu, Pan Li, Qi Zeng, Zhengkan Yang, Pushkar Tripathi

KARL: Reinforcement Learning for LLM Agents on Multi-Turn Knowledge-Intensive Agentic Tasks (2026.acl-long)

Challenge:	Existing systems for large-scale entity extraction are limited by the scale and variety of data available on internet platforms.
Approach:	They propose to build an entity extraction system for multiple document types at large scale using multi-modal Transformers.
Outcome:	The proposed system extracts multiple types of entities from multiple document types at large scale using multi-modal Transformers.

Copied to clipboard

Xueqiao Sun, Xiao Liu, Bowen Lv, Hanchen Zhang, Bohao Jing, Zehan Qi, Yifan Xu, Yuxiao Dong, Jie Tang

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy (2025.acl-long)

Challenge:	Large Language Models have shown remarkable potential as autonomous agents, but their effectiveness in knowledge-intensive tasks remains limited by passive knowledge utilization.
Approach:	They propose a framework that enables LLM agents to dynamically explore structured knowledge sources through multi-turn interactions.
Outcome:	The proposed framework outperforms existing retrieval-augmented approaches on knowledge graph and database tasks while maximizing tool-use behaviors end-to-end.

Copied to clipboard

Shuhao Guan, Moule Lin, Cheng Xu, Xinyi Liu, Jinman Zhao, Jiexin Fan, Qi Xu, Derek Greene

Hybrid Hierarchical Retrieval for Open-Domain Question Answering (2023.findings-acl)

Challenge:	Existing pipelines that combine document image restoration with semantic-aware post-OCR correction can improve text extraction from degraded images.
Approach:	They propose a two-stage pipeline that combines document image restoration with semantic-aware post-OCR correction to enhance both visual clarity and textual consistency.
Outcome:	The proposed pipeline reduces character error rates by 63.9-70.3% on 13,831 pages of real historical documents in English, French, and Spanish compared to OCR on raw images.

Copied to clipboard

Manoj Ghuhan Arivazhagan, Lan Liu, Peng Qi, Xinchi Chen, William Yang Wang, Zhiheng Huang

Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extraction (2023.emnlp-main)

Challenge:	Recent work shows that dense hierarchical retrieval (DHR) can outperform dense passage retrieval.
Approach:	They propose a framework that applies sparse, dense and a combination of them to document and passage retrieval.
Outcome:	The proposed framework can outperform dense hierarchical retrieval (DHR) and sparse retrievers (BM25) on open-domain question answering (ODQA) datasets with an average improvement of 4.69% on recall@100 over DHR.

Copied to clipboard

Ji Qi, Chuchun Zhang, Xiaozhi Wang, Kaisheng Zeng, Jifan Yu, Jinxin Liu, Lei Hou, Juanzi Li, Xu Bin

CLEAR: A Framework Enabling Large Language Models to Discern Confusing Legal Paragraphs (2025.findings-emnlp)

Challenge:	Existing evaluation benchmarks focus on pairwise matching, ignoring robustness . current models exhibit frustrating degradation, with a maximum drop of 23.43 F1 score .
Approach:	They propose a benchmark that simulates the evaluation of open information extraction models in the real world . they perform experiments on typical models published in the last decade and a representative large language model .
Outcome:	The proposed model is rated robust on a knowledge-invariant clique with different syntactic and expressive forms.

Copied to clipboard

Qi Xu, Qian Liu, Hao Fei, Hang Yu, Shuhao Guan, Xiao Wei

DARM: Distribution-Aware Reward Modeling by Alleviating Biases from Low Preference-Context Dependency Data (2026.acl-long)

Challenge:	Existing work focuses on enabling LLMs to leverage legal rules to tackle complex legal reasoning tasks, but ignores their ability to understand legal rules.
Approach:	They propose a legal paragraph prediction task that aims to predict the legal paragraph given criminal facts and a framework CLEAR to enhance their legal reasoning ability.
Outcome:	The proposed model improves the ability of LLMs to analyze legal cases with the guidance of legal rule insights.

Copied to clipboard

Shaofan Liu, Guoqiang Zhang, Shihan Dou, Huiyuan Zheng, Yiming Zhou, Junjie Ye, Shaowen Wang, Shichun Liu, Jiazheng Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing methods for training reward models are vulnerable to context neglect and degraded accuracy.
Approach:	They propose distribution-aware reward modeling that augments the RM objective with a conditional mutual information regularizer that maximizes context and the predicted reward conditioned on the response.
Outcome:	The proposed model improves performance in RLHF and improves accuracy in other settings.

SGPVT: Self-Generated Proximal Visual Tokens for Mitigating Proximal Collateral Damage in MLLM Unlearning (2026.acl-long)

Copied to clipboard

Jiaqi Li, Zhijing Zhang, Jiahui Geng, Sheng Bi, Chuanyi Zhang, Fan Liu, Guilin Qi

Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks (2022.emnlp-main)

Challenge:	Existing approaches focus on general utility metrics, overlooking the preservation of semantically related concepts.
Approach:	They propose a method that introduces self-generated proximal visual tokens to prevent forgetting vulnerability.
Outcome:	The proposed framework outperforms existing methods in preserving semantically related concepts while achieving effective target unlearning.

Copied to clipboard

Yangyi Chen, Fanchao Qi, Hongcheng Gao, Zhiyuan Liu, Maosong Sun

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

Challenge:	Existing textual backdoor attacks are vulnerable to backdoors . researchers add extra training task to distinguish poisoned and clean data .
Approach:	They propose two tricks that make existing backdoor attacks much more harmful . first trick is to add an extra task to distinguish poisoned and clean data . second trick is using all the clean training data rather than the original clean data.
Outcome:	The proposed tricks can significantly improve attack performance in three tough situations including clean data fine-tuning, low-poisoning-rate, and label-consistent attacks.

Copied to clipboard

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

NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning (2025.emnlp-main)

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 Liu, Siya Qi, Xinyu Wang, Chen Qian, Yali Du, Yulan He

Adaptive Preference Optimization with Uncertainty-aware Utility Anchor (2025.findings-emnlp)

Challenge:	Recent advances in reinforcement learning, such as DeepSeek R1-Zero, highlight the effectiveness of incentive training, but these methods rely on external verifiers, which limits their applicability to domains like mathematics and coding, where such verifier is readily available.
Approach:	They propose a general reinforcement learning framework that requires only standard supervised fine-tuning data with no need for an external verifier.
Outcome:	The proposed framework outperforms the model of the same size distilled from large reasoning models such as DeepSeek R1 671B by 7.7%.

Copied to clipboard

Xiaobo Wang, Zixia Jia, Jiaqi Li, Qi Liu, Zilong Zheng

Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation (2022.emnlp-main)

Challenge:	Offline preference optimization methods are efficient for large language models (LLMs) alignment.
Approach:	They propose an offline preference optimization framework that estimates uncertainties from preference data . the method enables training even in scenarios where the data is unpaired .
Outcome:	The proposed method enables training even in scenarios where the data is unpaired .

Copied to clipboard

Yang Yu, Fangzhao Wu, Chuhan Wu, Jingwei Yi, Qi Liu

HD-Eval: Aligning Large Language Model Evaluators Through Hierarchical Criteria Decomposition (2024.acl-long)

Challenge:	Existing work fine tunes the PLM with the news recommendation task, which can cause a domain shift problem.
Approach:	They propose a self-supervised method to adapt general PLM to news domain with a contrastive matching task between news titles and news bodies.
Outcome:	The proposed method can improve both the effectiveness and efficiency of the large PLM-based news recommendation model while maintaining its performance.

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP (2022.emnlp-main)

Challenge:	Large language models (LLMs) are a promising alternative to expensive human evaluations.
Approach:	They propose a framework that iteratively aligns LLM-based evaluators with human preference . they decompose a given evaluation task into finer-grained criteria .
Outcome:	The proposed framework iteratively aligns LLM-based evaluators with human preference . it decomposes a given evaluation task into finer-grained criteria . the framework is efficient to train and more explainable than relying solely on prompts .

Copied to clipboard

Yangyi Chen, Hongcheng Gao, Ganqu Cui, Fanchao Qi, Longtao Huang, Zhiyuan Liu, Maosong Sun

TransferTOD: A Generalizable Chinese Multi-Domain Task-Oriented Dialogue System with Transfer Capabilities (2024.emnlp-main)

Challenge:	Textual adversarial samples are often misrepresented in research on security, evaluation, explainability, and data augmentation.
Approach:	They propose to use adversarial samples to evaluate their methods on security tasks to demonstrate the real-world concerns rather than developing impractical methods.
Outcome:	The proposed method has higher practical value than the current benchmark.

Copied to clipboard

Ming Zhang, Caishuang Huang, Yilong Wu, Shichun Liu, Huiyuan Zheng, Yurui Dong, Yujiong Shen, Shihan Dou, Jun Zhao, Junjie Ye, Qi Zhang, Tao Gui, Xuanjing Huang

Mining Evidences for Concept Stock Recommendation (N18-1)

Challenge:	Current datasets cater to user-led systems and are limited to predefined specific scenarios and slots.
Approach:	They propose to use a Chinese dialogue dataset to train a model that authentically simulates human-computer dialogues in 30 popular life service scenarios.
Outcome:	The proposed model achieves a joint accuracy of 75.09% in out-of-domain evaluations . it also achieves notable abilities in slot filling and questioning .

Copied to clipboard

Qi Liu, Yue Zhang

PQR: Improving Dense Retrieval via Potential Query Modeling (2025.acl-long)

Challenge:	a recent announcement of a state plan to build a new economic region has led to the rise of hundreds of stocks . concepts can be useful for investors to find out relevant concept stocks for making investment decisions . a chinese research team uses deep learning to mine evidences from large textual data .
Approach:	They use distributed word similarities and deep reinforcement learning to learn a strategy of topic expansion from large scale textual data.
Outcome:	The proposed method outperforms a baseline method on two Chinese stock market datasets.

Copied to clipboard

Junfeng Kang, Rui Li, Qi Liu, Yanjiang Chen, Zheng Zhang, Junzhe Jiang, Heng Yu, Yu Su

P-FOLIO: Evaluating and Improving Logical Reasoning with Abundant Human-Written Reasoning Chains (2024.findings-emnlp)

Challenge:	Existing training data is sparse, with each document associated with one or a few labeled queries.
Approach:	They propose a training-free potential query retrieval framework to address this problem . they use a Gaussian mixture distribution to model all potential queries for a document .
Outcome:	The proposed method is able to capture comprehensive semantic information from a document with multiple queries.

Copied to clipboard

Simeng Han, Aaron Yu, Rui Shen, Zhenting Qi, Martin Riddell, Wenfei Zhou, Yujie Qiao, Yilun Zhao, Semih Yavuz, Ye Liu, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Dragomir Radev, Rex Ying, Arman Cohan

MasRouter: Learning to Route LLMs for Multi-Agent Systems (2025.acl-long)

Challenge:	Existing methods on understanding the capabilities of LLMs in logical reasoning rely on binary entailment classification or synthetically derived rationales.
Approach:	They propose to annotate a human-annotated dataset consisting of diverse and complex reasoning chains for a set of realistic logical reasoning stories also written by humans.
Outcome:	The proposed model outperforms existing methods on understanding the capabilities of LLMs in logical reasoning by 10% or more.

Copied to clipboard

Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng, Yiyan Qi

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

Challenge:	Multi-agent systems (MAS) powered by Large Language Models (LLMs) have been demonstrated to push the boundaries of LLM capabilities, yet they often face significant costs and challenges in dynamic LLM selection.
Approach:	They propose a multi-agent system routing solution that integrates all components of MAS into a unified routing framework.
Outcome:	The proposed solution is high-performing, cost-effective, and efficient . it reduces overhead by up to 52.07 compared to current methods on HumanEval .

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

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

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

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

VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment (2024.emnlp-main)

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.

Copied to clipboard

Lei Li, Zhihui Xie, Mukai Li, Shunian Chen, Peiyi Wang, Liang Chen, Yazheng Yang, Benyou Wang, Lingpeng Kong, Qi Liu

Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning (2022.acl-long)

Challenge:	Large vision-language models (LVLMs) are evolving rapidly and require data with human supervision to achieve better alignment.
Approach:	They introduce VLFeedback, the first large-scale vision-language feedback dataset . they train Silkie, an LVLM fine-tuned via direct preference optimization .
Outcome:	The proposed model outperforms its base model in helpfulness, visual faithfulness, and safety metrics and exhibits enhanced resilience against red-teaming attacks.

Copied to clipboard

Qin Liu, Rui Zheng, Bao Rong, Jingyi Liu, ZhiHua Liu, Zhanzhan Cheng, Liang Qiao, Tao Gui, Qi Zhang, Xuanjing Huang

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering (2025.findings-acl)

Challenge:	Existing approaches to generating adversarial perturbations scale up the cost of training computational complexity by the number of gradient steps it takes to obtain the adversarials.
Approach:	They propose a flood method which aims at better generalization and a criterion to bring hyper-parameter-dependent flooding into effect with a narrowed-down search space by measuring how the gradient steps taken within one epoch affect the loss of each batch.
Outcome:	The proposed method improves BERT’s resistance to textual adversarial attacks by a large margin and achieves state-of-the-art robust accuracy on various text classification and GLUE tasks.

Copied to clipboard

Jingqun Tang, Qi Liu, Yongjie Ye, Jinghui Lu, Shu Wei, An-Lan Wang, Chunhui Lin, Hao Feng, Zhen Zhao, Yanjie Wang, Yuliang Liu, Hao Liu, Xiang Bai, Can Huang

ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis (2025.findings-naacl)

Challenge:	Text-Centric Visual Question Answering (TEC-VQA) is a text-centric visual task understanding tool.
Approach:	They introduce a benchmark that features human expert annotations across 9 languages . they prioritize the text in question-answer pairs while disregarding visual text in images .
Outcome:	The proposed benchmarks prioritize the text in question-answer pairs while disregarding visual text in images.

Copied to clipboard

Zeao Tu, Xiangdi Meng, Yu He, Zihan Yao, Tianyu Qi, Jun Liu, Ming Li

Relational Memory-Augmented Language Models (2022.tacl-1)

Challenge:	Existing methods for enhancing large language models lack clear metrics for evaluating data characteristics.
Approach:	They propose a method that integrates models, data, and tasks to refine datasets.
Outcome:	The proposed method achieves comparable results to full-scale fine-tuning using only half the data in mathematical tasks and exhibits strong generalization across different models and domains.

Copied to clipboard

Qi Liu, Dani Yogatama, Phil Blunsom

ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation (2025.acl-long)

Challenge:	Existing language models rely on word correlation and are difficult to interpret . existing models often lack explicit representations for such information .
Approach:	They propose a memory-augmented approach to condition autoregressive language models on knowledge graphs.
Outcome:	The proposed model improves perplexity and bits per character in an autoregressive language model . it is complementary to token-based memory and enables causal interventions .

Copied to clipboard

Xuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen, Shuo Wang, Zhiyuan Liu, Maosong Sun

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)

Challenge:	Existing open-source MLLMs fail to fully capture dense information embedded in charts . current models still face significant challenges in understanding and analyzing visual tasks such as captioning and question answering.
Approach:	They propose a chart-to-code MLLM which leverages Code LLMs as the language backbone to enhance the executability of the generated code.
Outcome:	The proposed model surpasses existing open-source models on chart-to-code benchmarks with only 7B parameters and provides lossless representations that contain all critical details.

Copied to clipboard

Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui

Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement (2023.findings-emnlp)

Challenge:	coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored .
Approach:	They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding.
Outcome:	The proposed benchmark aims to accelerate the development of more scaffold-aware agents.

Copied to clipboard

Zhiheng Xi, Senjie Jin, Yuhao Zhou, Rui Zheng, Songyang Gao, Jia Liu, Tao Gui, Qi Zhang, Xuanjing Huang

AutoRubric: Rubric-Based Generative Rewards for Faithful Multimodal Reasoning (2026.findings-acl)

Challenge:	Existing prompting methods have been used to enhance multistep reasoning capabilities of large language models, but they have overlooked the potential of formulating higher-quality problems.
Approach:	They propose a method that starts from the problem side and refines problems to be more comprehensible and solvable for models.
Outcome:	The proposed method achieves notable and consistent effectiveness on five reasoning benchmarks across different models.

Copied to clipboard

Mengzhao Jia, Zhihan Zhang, Ignacio Cases, Zheyuan Liu, Meng Jiang, Peng Qi

MCS: An In-battle Commentary System for MOBA Games (2022.coling-1)

Challenge:	Multimodal large language models (MLLMs) have advanced from perception tasks to complex multi-step reasoning.
Approach:	They propose a framework that integrates reinforcement learning with verifiable rewards with process-level supervision through automatically collected rubric-based generative rewards.
Outcome:	The proposed framework achieves state-of-the-art performance on six multimodal reasoning benchmarks and significantly improves reasoning faithfulness in dedicated evaluations.

Copied to clipboard

Xiaofeng Qi, Chao Li, Zhongping Liang, Jigang Liu, Cheng Zhang, Yuanxin Wei, Lin Yuan, Guang Yang, Lanxiao Huang, Min Li

Challenge:	In-battle commentary is an important component of live streaming of e-sports competitions and is applicable to a wide range of scenarios like combat information analysis and live streaming.
Approach:	They propose a generative system for in-battle real-time commentary in mobile MOBA games and propose 'transform' method to convert match statistics and utterances into consistent encoding space.
Outcome:	The proposed system is based on real-time match statistics and events and can be used for live streaming, e-sports commentary and combat information analysis.

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution (2021.acl-long)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Fanchao Qi, Yuan Yao, Sophia Xu, Zhiyuan Liu, Maosong Sun

Se2: Sequential Example Selection for In-Context Learning (2024.findings-acl)

Challenge:	Recent studies show that neural natural language processing models are vulnerable to backdoor attacks.
Approach:	They propose to inject neural models with backdoors activated by word substitution . their results raise a serious alarm to the security of NLP models, they argue .
Outcome:	The proposed backdoors are activated by a learnable combination of word substitution and exhibit higher invisibility than previous methods.

Copied to clipboard

Haoyu Liu, Jianfeng Liu, Shaohan Huang, Yuefeng Zhan, Hao Sun, Weiwei Deng, Furu Wei, Qi Zhang

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

Challenge:	Prior work has explored the selection of examples for in-context learning, neglecting the internal relationships between examples and exist an inconsistency between training and inference.
Approach:	They propose a sequential-aware method that leverages the LLM’s feedback on varying context, aiding in capturing inter-relationships and sequential information among examples.
Outcome:	Experiments on 23 NLP tasks show that Se2 surpasses baselines and achieves 42% relative improvement over random selection.

Copied to clipboard

Jiayu Li, Jennifer Zhu, Fang Liu, Yanjun Qi

DuReadervis: A Chinese Dataset for Open-domain Document Visual Question Answering (2022.findings-acl)

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

Le Qi, Shangwen Lv, Hongyu Li, Jing Liu, Yu Zhang, Qiaoqiao She, Hua Wu, Haifeng Wang, Ting Liu

ProphetNet: Predicting Future N-gram for Sequence-to-SequencePre-training (2020.findings-emnlp)

Challenge:	Open-domain question answering is a task that requires answering questions based on a collection of document images.
Approach:	They propose to use document images to answer questions using layouts and visual features instead of text.
Outcome:	The proposed approach reduces human cost and improves scalability of QA systems by incorporating layouts and visual features.

Copied to clipboard

Weizhen Qi, Yu Yan, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei Zhang, Ming Zhou

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)

Challenge:	Existing sequence-to-sequence models are optimized for future n-gram prediction and n stream self-attention mechanism.
Approach:	They propose a self-supervised objective called future n-gram prediction and the proposed n stream self-attention mechanism to optimize the model for sequence-to-sequence learning.
Outcome:	The proposed model achieves state-of-the-art on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks compared to the models using the same scale pre-training corpus.

Copied to clipboard

Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng

Challenge:	Existing studies on large language model-based agents focus on evaluation benchmarks without training support.
Approach:	They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents.
Outcome:	The proposed model performs poorly in a large-scale and challenging shopping environment in China.

Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition (2021.naacl-main)

Copied to clipboard

Dingmin Wang, Chenghua Lin, Qi Liu, Kam-Fai Wong

Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding (2025.emnlp-main)

Challenge:	Existing approaches for dialogue state tracking are mainly based on classification-based and extraction-based methods.
Approach:	They propose a model which incorporates both classification-based and extraction-based methods and integrates four modules to jointly extract dialogue states.
Outcome:	The proposed model outperforms the state-of-the-art models in multi-domain dialogues with many turns of utterances.

Copied to clipboard

Jinglin Chen, Qiwei Li, Zuchao Li, Baoyuan Qi, Liu Guoming, Haojun Ai, Hai Zhao, Ping Wang

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

Challenge:	In-Context Learning (ICL) is a key method in prompt engineering, but its long retrieved contexts and limited token throughput will slow reasoning speeds.
Approach:	They propose a method that leverages the overlap between context and model output to generate drafts from the context.
Outcome:	The proposed method achieves the highest mean speedup on Vicuna-7B, Llama2-7B-Chat, and Llma3-8B-Instruct tasks.

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

Word-level Textual Adversarial Attacking as Combinatorial Optimization (2020.acl-main)

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

Yuan Zang, Fanchao Qi, Chenghao Yang, Zhiyuan Liu, Meng Zhang, Qun Liu, Maosong Sun

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond (2025.acl-industry)

Challenge:	Existing word-level attack models are far from perfect because of unsuitable search space reduction methods and inefficient optimization algorithms.
Approach:	They propose a novel adversarial adversarialist model that incorporates word substitution and particle swarm optimization to solve two problems separately.
Outcome:	The proposed model achieves much higher success rates and crafts more high-quality adversarial examples as compared to baseline methods.

Copied to clipboard

Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang

A Survey of Post-Training Scaling in Large Language Models (2025.acl-long)

Challenge:	Experimental results show that opensource curriculum training is more effective when distinct datasets are available for different training stages.
Approach:	They propose an opensource suite for training long reasoning models using publicdata and models.
Outcome:	The proposed model outperforms DeepSeek-R1-DistillQwen-32B models in math reasoning.

Copied to clipboard

Hanyu Lai, Xiao Liu, Junjie Gao, Jiale Cheng, Zehan Qi, Yifan Xu, Shuntian Yao, Dan Zhang, Jinhua Du, Zhenyu Hou, Xin Lv, Minlie Huang, Yuxiao Dong, Jie Tang

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding (2025.acl-srw)

Challenge:	Large language models (LLMs) have demonstrated proficiency in understanding and generating human natural languages.
Approach:	They propose a framework for scaling large language models using supervised fine-tuning, RLxF and test-time compute methodologies.
Outcome:	The proposed model can be used to understand and generate human natural languages.

Copied to clipboard

Qi Feng, Yihong Liu, Hinrich Schuetze

Sub-Character Tokenization for Chinese Pretrained Language Models (2023.tacl-1)

Challenge:	Existing curriculum learning approaches rely on manually defined difficulty metrics which may not accurately reflect the model’s own perspective.
Approach:	They propose a self-adaptive curriculum learning paradigm that prioritizes fine-tuning examples based on difficulty scores predicted by pre-trained language models (PLMs) they evaluate four datasets covering binary and multi-class classification tasks.
Outcome:	The proposed model leads to faster convergence and improved performance compared to standard random sampling.

Copied to clipboard

Chenglei Si, Zhengyan Zhang, Yingfa Chen, Fanchao Qi, Xiaozhi Wang, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun

Divide-Verify-Refine: Can LLMs Self-align with Complex Instructions? (2025.findings-acl)

Challenge:	Existing tokenization methods for Chinese PLMs treat each character as an indivisible token, but ignore the unique feature of the writing system where additional linguistic information exists below the character level.
Approach:	They propose to encode Chinese characters into short sequences and construct Chinese vocabulary based on the encoded text.
Outcome:	The proposed tokenizers can tokenize inputs into much shorter sequences, improving computational efficiency.

Copied to clipboard

Xianren Zhang, Xianfeng Tang, Hui Liu, Zongyu Wu, Qi He, Dongwon Lee, Suhang Wang

Low-Resource NLP

Challenge:	Existing research shows LLMs struggle with complex instructions involving multiple constraints.
Approach:	They propose a framework to divide complex instructions into single constraints and prepare appropriate tools to verify responses.
Outcome:	The proposed framework doubles Llama3.1-8B’s constraint adherence and triples Mistral-7B’ s performance.

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

Copied to clipboard

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

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)

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

Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He

GeAR: Generation Augmented Retrieval (2025.findings-acl)

Challenge:	Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps.
Approach:	They propose a method to identify critical reasoning steps using perplexity as a measure of their importance.
Outcome:	The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT.

Copied to clipboard

Haoyu Liu, Shaohan Huang, Jianfeng Liu, Yuefeng Zhan, Hao Sun, Weiwei Deng, Feng Sun, Furu Wei, Qi Zhang

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training (2022.findings-emnlp)

Challenge:	Document retrieval techniques are used to compute semantic similarity between a query and documents, but the scalar similarity fails to reflect enough information, hindering the interpretation of retrieval results.
Approach:	They propose a method which improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.
Outcome:	The proposed method improves the global document-query similarity through contrastive learning and integrates well-designed fusion and decoding modules.

Copied to clipboard

Qi Shi, Qian Liu, Bei Chen, Yu Zhang, Ting Liu, Jian-Guang Lou

Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild (2024.acl-long)

Challenge:	Existing approaches to language-based environment manipulation are difficult to generalize across environments.
Approach:	They propose a general framework for language-based environment manipulation tasks that can deal with various environments using the same generative language model.
Outcome:	The proposed framework achieves new state-of-the-art results on four of the tasks and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.

Copied to clipboard

Ting Wu, Jingyi Liu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang

Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation (2024.acl-srw)

Challenge:	Existing methods for continual relation extraction (CRE) excel in preserving old knowledge but falter when confronted with contaminated data streams.
Approach:	They propose a noise-resistant contrastive framework for continual relation extraction (CRE) that preserves old knowledge while learning incremental corrupted relations.
Outcome:	The proposed framework outperforms state-of-the-art methods on various benchmarks with increasing noise rates.

Copied to clipboard

Yikun Wang, Rui Zheng, Haoming Li, Qi Zhang, Tao Gui, Fei Liu

One LLM Does Not Simulate All Students: Ability-Aware Student Simulation via Cognitive Diagnosis Guided LLM Assignment (2026.findings-acl)

Challenge:	Customizing LLMs for a specific task involves separating high-quality responses from lower-quality ones. Obtaining a large volume of expert-annotated data is costly for most tasks.
Approach:	They propose a method that trains the model to prioritize the best responses from a pool of candidates created for a task using ranking metrics.
Outcome:	The proposed method is more robust, less sensitive to noise, and can be achieved with limited human annotations or through heuristic methods.

Copied to clipboard

Huixing Que, Qi Liu, Weibo Gao, Zhenya Huang

Linguistics & Cognitive NLP

Challenge:	Existing methods rely on a single high-capacity LLM to represent an entire population of diverse learners.
Approach:	They propose an ability-aware student simulation framework that matches students with appropriate LLM backbones through cognitive alignment.
Outcome:	The proposed framework significantly reduces simulation bias and outperforms single-model baselines across the entire proficiency spectrum.

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)

Copied to clipboard

Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Bowen Yu, Fei Huang, Junyang Lin

Towards Trustworthy Smart Contract Synthesis: A Multi-Agent Framework with Lean-Based Verification (2026.acl-long)

Challenge:	Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF.
Approach:	They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench.
Outcome:	The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%.

Copied to clipboard

Bowei Zhang, Hanbing Liu, Qixin Tian, Siyu Chen, Ziyuan Wang, Qi Qi

Democratizing Reasoning Ability: Tailored Learning from Large Language Model (2023.emnlp-main)

Challenge:	Smart Contracts are the foundation of Decentralized Finance (DeFi), executing financial logic without trusted intermediaries.
Approach:	They propose a framework that integrates LLM-based generation with Lean-based auto-formalization and verification.
Outcome:	LeVer is the first trustworthy smart contract synthesis framework that integrates LLM-based generation with Lean-based auto-formalization and verification.

Copied to clipboard

Zhaoyang Wang, Shaohan Huang, Yuxuan Liu, Jiahai Wang, Minghui Song, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks (2021.emnlp-main)

Challenge:	Large language models (LLMs) exhibit impressive emergent abilities in natural language processing, but their democratization is hindered due to huge computation requirements and closed-source nature.
Approach:	They propose a tailored learning approach to distill the exclusive reasoning ability to smaller LMs to facilitate democratization.
Outcome:	The proposed approach enables the democratization of the exclusive reasoning ability by leveraging the black-box model as a reasoning teacher.

Copied to clipboard

Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, Maosong Sun

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

Challenge:	Backdoor attacks can manipulate the output of deep neural networks and possess high insidiousness.
Approach:	They propose a textual backdoor defense based on outlier word detection that can handle all the textual attacks.
Outcome:	The proposed method can handle all the textual backdoor attack situations.

Copied to clipboard

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

A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)

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

Copied to clipboard

Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang

PLAWBENCH: A Rubric-Based Benchmark for Evaluating LLMs in Real-World Legal Practice (2026.acl-long)

Challenge:	Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs .
Approach:	They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding .
Outcome:	The proposed model shows an increase in performance in KIE and VQA tasks.

Copied to clipboard

Yuzhen Shi, Huanghai Liu, Yiran HU, Song Gaojie, Xu Xinran, Yubo Ma, Tianyi Tang, Li Zhang, Qingjing Chen, Feng Di, Wenbo Lv, Weiheng Wu, Kexin Yang, Sen Yang, Wei Wang, Rongyao Shi, Qiu Yuanyang, Yuemeng Qi, Zhang Jingwen, Sui Xiaoyu, Yifan Chen, Zhang Yi, An Yang, Bowen Yu, Dayiheng Liu, Junyang Lin, Weixing Shen, Bing Zhao, Charles L. A. Clarke, HU Wei

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

Challenge:	Existing benchmarks for large language models (LLMs) are coarse, single-dimensional metrics and do not explicitly assess fine-grained legal reasoning.
Approach:	They propose a Practical Law Benchmark to evaluate large language models in real-world legal practice scenarios.
Outcome:	The proposed model is based on 850 questions and 13 scenarios with expert-designed evaluation rubrics.

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

TestAgent: An Adaptive and Intelligent Expert for Human Assessment (2025.findings-acl)

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

Junhao Yu, Yan Zhuang, Yuxuan Sun, Weibo Gao, Qi Liu, Mingyue Cheng, Zhenya Huang, Enhong Chen

A Multi-Task Learning Framework for Extracting Bacteria Biotope Information (D19-57)

Challenge:	Existing adaptive testing methods face several challenges due to mechanized nature of most algorithms and noisy response data.
Approach:	They propose to use large language models to enhance adaptive testing through interactive engagement to capture test-takers’ responses and anomalies.
Outcome:	The proposed agent achieves more accurate results with 20% fewer questions than state-of-the-art baselines and testers preferred it in speed, smoothness, and other dimensions.

Copied to clipboard

Qi Zhang, Chao Liu, Ying Chi, Xuansong Xie, Xiansheng Hua

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation (2025.findings-emnlp)

Challenge:	Existing methods to extract information from unstructured text are slow or expensive to get.
Approach:	They propose a multi-task transfer multi-learning method for Bacteria Biotope rel+ner task . they use BERT and pre-train it using mask language models and next sentence prediction .
Outcome:	The proposed method achieves the best performance on all metrics including slot error rate, precision and recall in the Bacteria Biotope rel+ner subtask.

Copied to clipboard

Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Longxiang Liu, Kaiyuan Zhang, Jianpeng Jiao, Ge Zhang, Wenhao Huang, Nenghai Yu

WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have been widely adopted in real-world dialogue applications, but their robustness is criticized all along.
Approach:	They propose to use play-by-play text commentary to build a multi-turn athletic real-world scenario dialogue benchmark to evaluate three critical aspects of multi-turned conversations: ultra multi- turn, interactive multi-twist, and cross-turn tasks.
Outcome:	The proposed benchmarks outperform open-source LLMs on three critical aspects of multi-turn conversations: ultra multi-turned, interactive multi- turn, and cross-turn tasks.

Copied to clipboard

An-Lan Wang, Jingqun Tang, Lei Liao, Hao Feng, Qi Liu, Xiang Fei, Jinghui Lu, Han Wang, Hao Liu, Yuliang Liu, Xiang Bai, Can Huang

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

Challenge:	Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world .
Approach:	They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions.
Outcome:	The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents.

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.

Going “Deeper”: Structured Sememe Prediction via Transformer with Tree Attention (2022.findings-acl)

Copied to clipboard

Yining Ye, Fanchao Qi, Zhiyuan Liu, Maosong Sun

LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)

Challenge:	Existing studies ignore hierarchical structures of sememes in sememe-based semantic description systems.
Approach:	They propose a structured sememe prediction problem to predict a sememes tree with hierarchical structures rather than a set of sememas.
Outcome:	The proposed model outperforms baseline models and shows its effectiveness . it predicts a sememe tree with hierarchical structures rather than a set of sememes .

Copied to clipboard

Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan, Qiyuan Peng, Yue Zhang, Junzhe Wang, Shichun Liu, Yueyuan Huang, Jingqi Tong, Changhao Jiang, Yilong Wu, Zhihao Zhang, Mingqi Wu, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang

Design Choices for Extending the Context Length of Visual Language Models (2025.acl-long)

Challenge:	Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting.
Approach:	LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data .
Outcome:	LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm .

Copied to clipboard

Mukai Li, Lei Li, Shansan Gong, Qi Liu

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

Challenge:	Existing open-source Visual Language Models lack systematic exploration into extending their context length, and commercial models often provide limited details.
Approach:	They propose to extend Visual Language Models (VLMs) to 128K lengths and open-source the code, data, and models.
Outcome:	The proposed model is based on the Qwen-VL series model and is competitive with commercial model GPT-4V.

Copied to clipboard

Qi Jia, Yizhu Liu, Haifeng Tang, Kenny Zhu

Open Domain Question Answering with Conflicting Contexts (2025.findings-naacl)

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

Siyi Liu, Qiang Ning, Kishaloy Halder, Zheng Qi, Wei Xiao, Phu Mon Htut, Yi Zhang, Neha Anna John, Bonan Min, Yassine Benajiba, Dan Roth

Your Vision-Language Model Itself Is a Strong Filter: Towards High-Quality Instruction Tuning with Data Selection (2024.findings-acl)

Challenge:	Open domain question answering systems often rely on information retrieved from large collections of text to answer questions.
Approach:	They evaluate and benchmark three powerful Large Language Models with a dataset . they find that 25% of unambiguous open domain questions can lead to conflicting contexts .
Outcome:	The proposed model can't be used to answer questions with conflicting contexts . it can be fine tuned to provide richer information into the model's training .

Copied to clipboard

Ruibo Chen, Yihan Wu, Lichang Chen, Guodong Liu, Qi He, Tianyi Xiong, Chenxi Liu, Junfeng Guo, Heng Huang

RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)

Challenge:	Existing data selection methods for instruction-following large language models rely on unreliable scores or use downstream tasks for selection.
Approach:	They propose a method that utilizes the VLM itself as a filter to select high-quality instruction-tuning data.
Outcome:	The proposed method can reach better results compared to full data settings with merely about 15% samples and can achieve superior performance against competitive baselines.

Copied to clipboard

Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji

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

Challenge:	Existing methods for event prediction are incomplete and noisy.
Approach:	They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework .
Outcome:	The proposed framework can be applied to a wide variety of newsworthy scenarios.

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

MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality (2025.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

Shuaike Li, Kai Zhang, Qi Liu, Enhong Chen

Challenge:	Existing knowledge editing methods overfit to specific models, causing edited knowledge to be discarded during each LLM update and requiring frequent re-editing.
Approach:	They propose a solution that allows editors to edit knowledge in multiple LLMs at the same time.
Outcome:	The proposed solution performs better even in editing tens of thousands of knowledge entries and can adapt to different LLMs.

Speculating LLMs’ Chinese Training Data Pollution from Their Tokens (2025.emnlp-main)

Copied to clipboard

Qingjie Zhang, Di Wang, Haoting Qian, Liu Yan, Tianwei Zhang, Ke Xu, Qi Li, Minlie Huang, Hewu Li, Han Qiu

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

Challenge:	Experiments on GPT and other 23 LLMs indicate that tokens widely exist while GPT’s vocabulary behaves the worst: more than 23% long Chinese tokens (i.e., a token with more than two Chinese characters) are either porn or online gambling.
Approach:	They propose to locate Polluted Chinese (PoC) tokens in LLMs and build a PoC token detector to label them in vocabularies by considering each token’s semantics and related contents from the search engines.
Outcome:	The proposed method predicts that the ratio of “*” related webpages in GPT-4o's training data is around 0.5%.

Copied to clipboard

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

OneNet: A Fine-Tuning Free Framework for Few-Shot Entity Linking via Large Language Model Prompting (2024.emnlp-main)

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

Xukai Liu, Ye Liu, Kai Zhang, Kehang Wang, Qi Liu, Enhong Chen

LitVISTA: A Benchmark for Narrative Orchestration in Literary Text (2026.acl-long)

Challenge:	Entity Linking (EL) is the process of associating ambiguous textual mentions to specific entities in a knowledge base.
Approach:	They propose a framework that utilizes the few-shot learning capabilities of Large Language Models without the need for fine-tuning to improve the accuracy of EL.
Outcome:	The framework outperforms current state-of-the-art methods in a few-shot entity linking task.

Copied to clipboard

Mingzhe Lu, Yiwen Wang, Yanbing Liu, Qi You, Chong Liu, Ruize Qin, Haoyu Dong, Wenyu Zhang, JiaRui Zhang, Yue Hu, Yunpeng Li

Challenge:	Existing large language models focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives.
Approach:	They propose a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space.
Outcome:	The proposed framework unifies human and model perspectives while jointly characterizing narrative function and structure in a common space.

CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation (2025.findings-acl)

Copied to clipboard

Guangya Yu, Yanhao Li, Zongying Jiang, Yuxiong Jin, Li Dai, Yupian Lin, Ruihui Hou, Weiyan Zhang, Yongqi Fan, Qi Ye, Jingping Liu, Tong Ruan

Automatic Construction of Sememe Knowledge Bases via Dictionaries (2021.findings-acl)

Challenge:	Medical quality control indicators are essential to assess the qualifications of healthcare institutions for medical services.
Approach:	They propose a Chinese electronic medical records-based dataset for MQCIC and propose CF-IR method that disentangles clinical fact verification and inferential rule reasoning actions.
Outcome:	The proposed method outperforms Chain-of-Thought methods on 20 representative LLMs, covering general and medical models.

Copied to clipboard

Fanchao Qi, Yangyi Chen, Fengyu Wang, Zhiyuan Liu, Xiao Chen, Maosong Sun

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation (2025.acl-long)

Challenge:	Sememe knowledge bases (SKBs) are used to analyze natural language processing.
Approach:	They propose a method to build sememe knowledge bases from an existing dictionary . they propose to use existing dictionaries to build an English and a French SKB .
Outcome:	The proposed method is superior to HowNet, the most widely used SKB that takes decades to build manually.

Copied to clipboard

Zijun Yao, Weijian Qi, Liangming Pan, Shulin Cao, Linmei Hu, Liu Weichuan, Lei Hou, Juanzi Li

Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning (2026.acl-long)

Challenge:	Adaptive Retrieval-Augmented Generation (RAG) is an effective strategy to alleviate hallucination of large language models (LLMs).
Approach:	They propose a novel adaptive RAG model that extracts self-aware uncertainty of large language models from their internal states and invokes retrieval accordingly.
Outcome:	The proposed model outperforms existing adaptive RAG methods on complex and simple Question Answering datasets.

Copied to clipboard

Yanrui Du, Fenglei Fan, Sendong Zhao, Jiawei Cao, Ming Ma, Danyang Zhao, Shuren Qi, Ting Liu, Bing Qin

BloomEval: A Bloom’s Cognitive Taxonomy-Based Benchmark for Evaluating LRMs via Cognitive Hierarchy Trace (2026.findings-acl)

Challenge:	Instruction Fine-Tuning (IFT) has emerged as a critical technique for customizing Large Language Models (LLMs) however, recent studies have revealed that IFT can compromise the built-in security mechanisms of LLMs, posing significant security risks.
Approach:	They propose a method that shifts learning burden onto security-robust parameters and propose 'warm-up' phase that preferentially trains Mods_Rob to learn low-level features with minimal security risk.
Outcome:	The proposed method reduces security risks without sacrificing performance gains across knowledge-intensive datasets.

Copied to clipboard

Zhiyi Duan, Lei Gao, Jiangshan Guan, Qi Wang, Rui Liu

Causal Intervention for Abstractive Related Work Generation (2023.findings-emnlp)

Challenge:	Existing benchmarks for Large Reasoning Models rely on answer correctness, but fail to assess the structural coherence and cognitive soundness of the reasoning process itself.
Approach:	They propose a framework that maps a model's reasoning trajectory onto hierarchical cognitive levels and an annotation pipeline to ensure a scalable yet reliable annotation pipeline.
Outcome:	The proposed framework detects hierarchy jumps, breaks, and overthinking errors and enables scalable yet reliable annotation.

Copied to clipboard

Jiachang Liu, Qi Zhang, Chongyang Shi, Usman Naseem, Shoujin Wang, Liang Hu, Ivor Tsang

Challenge:	Existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability.
Approach:	They propose a Causal Intervention Module for Related Work Generation (CaM) that captures causal relationships in related work generation and implements causal interventions to mitigate the negative impact of spurious correlations.
Outcome:	The proposed framework improves the quality and coherence of generated related work by capturing causalities in the generation process.

Learning Domain Representation for Multi-Domain Sentiment Classification (N18-1)

Copied to clipboard

Qi Liu, Yue Zhang, Jiangming Liu

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Training data for sentiment analysis is abundant in multiple domains, yet scarce for other domains.
Approach:	They propose to use domain-specific representations of input sentences to improve sentiment classification . they use a descriptor vector to map adversarially trained domain-general Bi-LSTM inputs into domain- specific representations .
Outcome:	The proposed model outperforms existing methods on multi-domain sentiment analysis significantly.

Copied to clipboard

Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi

CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval (2025.findings-acl)

Challenge:	Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability .
Approach:	They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval .
Outcome:	The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets.

Copied to clipboard

Heng Yu, Junfeng Kang, Rui Li, Qi Liu, Liyang He, Zhenya Huang, Shuanghong Shen, Junyu Lu

A General Framework to Enhance Fine-tuning-based LLM Unlearning (2025.findings-acl)

Challenge:	Recent techniques such as Generation-Augmented Retrieval (GAR) and Generative Document Retrieleval (GDR) leverage LLMs to enhance retrieval performance but face key challenges: GAR’s generated content may not always align with the target document corpus, while GDR limits the generative capacity of LLM.
Approach:	They propose a Context-Aware Generation-Augmented Retrieval approach which integrates corpus information into their generation process.
Outcome:	Experimental results show that CA-GAR outperforms existing methods on seven tasks and four non-English languages.

Copied to clipboard

Jie Ren, Zhenwei Dai, Xianfeng Tang, Hui Liu, Jingying Zeng, Zhen Li, Rahul Goutam, Suhang Wang, Yue Xing, Qi He, Hui Liu

Anchored Cyclic Generation: A Novel Paradigm for Long-Sequence Symbolic Music Generation (2026.findings-acl)

Challenge:	Existing approaches to remove copyrighted and privacy-sensitive data from Large Language Models (LLMs) have been proposed to remove specific data from LLMs without requiring full retraining.
Approach:	They propose a general framework that enhances the utility of fine-tuning-based methods by distinguishing target data and suppressing related generations.
Outcome:	The proposed framework improves the unlearning and utility of fine-tuning-based methods by distinguishing the target data and suppressing related generations.

Copied to clipboard

Boyu Cao, Lekai Qian, Dehan Li, Haoyu Gu, Mingda Xu, Qi Liu

RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)

Challenge:	Autoregressive sequence modeling has been successful in many domains, but maintaining long-term coherence and structural integrity remains a challenge.
Approach:	They propose an ACG paradigm that relies on anchor features from previously generated musical content to guide subsequent generation during the autoregressive process.
Outcome:	The proposed framework outperforms existing methods in symbolic music generation tasks.

Copied to clipboard

Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth

SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)

Challenge:	Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains.
Approach:	They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control .
Outcome:	The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control.

Copied to clipboard

Shuang Cheng, Yihan Bian, Dawei Liu, Yuhua Jiang, Yihao Liu, Linfeng Zhang, Qian Yao, Zhongbo Tian, Wenhai Wang, Qipeng Guo, Kai Chen, Biqing Qi, Bowen Zhou

Modeling and Solving Stable Matching under Probabilistic Preferences with Large Language Models (2026.findings-acl)

Challenge:	Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling.
Approach:	They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation.
Outcome:	The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes.

Copied to clipboard

Yuqi Kong, Shiyu Liu, Jiaxu Li, Hongtao Liu, Qi Qi, Weiran Shen

Cross-lingual Lexical Sememe Prediction (D18-1)

Challenge:	Large language models (LLMs) have shown strong capability in understanding and simulating humans’ decisions, suggesting a new way to use LLMs as tools to study social systems.
Approach:	They propose a Hybrid GS–LLM matching method that integrates Gale–Shapley with probabilistic acceptance decisions.
Outcome:	The proposed method outperforms classical baselines in terms of stability and improves robustness under uncertainty.

Copied to clipboard

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

PlugAT: A Plug and Play Module to Defend against Textual Adversarial Attack (2022.coling-1)

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

Rui Zheng, Rong Bao, Qin Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Rui Xie, Wei Wu

XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression (2025.emnlp-main)

Challenge:	Recent studies have shown that adversarial examples can be easily fooled by adversarially perturbed examples.
Approach:	They propose a pluggable defense module PlugAT to provide robust predictions by adding a few trainable parameters to the model inputs while keeping the original model frozen.
Outcome:	The proposed model improves robustness over several strong baselines whilst training only 9.1% parameters.

Copied to clipboard

Haoqi Yang, Yao Yao, Zuchao Li, Baoyuan Qi, Liu Guoming, Hai Zhao

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks. however, their extensive memory requirements present significant challenges for deployment in resource-constrained environments.
Approach:	They propose a training-free framework that achieves ultra-low equivalent bit-width KV cache quantization.
Outcome:	The proposed framework outperforms state-of-the-art methods on TruthfulQA and LongBench.

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)

Copied to clipboard

Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun

Detecting Adversarial Samples through Sharpness of Loss Landscape (2023.findings-acl)

Challenge:	Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning .
Approach:	a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path .
Outcome:	Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness.

Copied to clipboard

Rui Zheng, Shihan Dou, Yuhao Zhou, Qin Liu, Tao Gui, Qi Zhang, Zhongyu Wei, Xuanjing Huang, Menghan Zhang

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models (2024.acl-long)

Challenge:	Existing studies have shown that adversarial samples are more vulnerable than normal ones to textual adversarials.
Approach:	They propose a simple and effective sharpness-based detector that can distinguish adversarial samples by maximizing the loss increment within the region where the inference sample is located.
Outcome:	The proposed method outperforms previous detection methods by large margins on three text classification tasks.

Copied to clipboard

Xudong Lu, Qi Liu, Yuhui Xu, Aojun Zhou, Siyuan Huang, Bo Zhang, Junchi Yan, Hongsheng Li

PKAD: Pretrained Knowledge is All You Need to Detect and Mitigate Textual Backdoor Attacks (2024.findings-emnlp)

Challenge:	Mixture-of-Experts (MoE) LLMs achieve higher performance with fewer active parameters, but are still difficult to deploy due to their immense parameter sizes.
Approach:	They propose expert-level sparsification techniques to enhance the deployment efficiency of large language models by introducing plug-and-play expert pruning and skipping techniques.
Outcome:	The proposed methods reduce model sizes and increase inference speed while maintaining satisfactory performance across a wide range of tasks.

Copied to clipboard

Yu Chen, Qi Cao, Kaike Zhang, Xuchao Liu, Huawei Shen

The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models (2023.emnlp-main)

Challenge:	Current defense methods can be classified into inference-time and training-time ones based on their execution phase.
Approach:	They propose a two-stage poison detection strategy using pre-trained language models to detect poisoned samples before model training.
Outcome:	The proposed method achieves better performance than current methods more quickly and with fewer training costs.

Copied to clipboard

Jingyuan Qi, Zhiyang Xu, Ying Shen, Minqian Liu, Di Jin, Qifan Wang, Lifu Huang

Geo-BERT Pre-training Model for Query Rewriting in POI Search (2021.findings-emnlp)

Challenge:	Chain-of-Thought (CoT) prompting relies on the initial decisions, causing errors in early steps to accumulate and impact the final answers.
Approach:	They propose a divide-and-conquer style algorithm that leverages large language models to raise and answer sub-questions until collecting enough information to tackle the original one.
Outcome:	The proposed algorithm is more robust to errors and errors than CoT prompting and Tree-of-Thought prompting methods.

Copied to clipboard

Xiao Liu, Juan Hu, Qi Shen, Huan Chen

AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage (2026.acl-long)

Challenge:	Existing methods to solve the word mismatch between queries and documents are often inadequate to integrate geographic information into the pre-training model.
Approach:	They propose to train a pre-training model to integrate semantics and geographic information in the pre-trained representations of POIs.
Outcome:	The proposed model achieves excellent accuracy on a wide range of real-world datasets of map services.

Copied to clipboard

Xuanle Zhao, Zilin Sang, Yuxuan Li, Qi Shi, Weilun Zhao, Shuo Wang, Duzhen Zhang, Xu Han, Zhiyuan Liu, Maosong Sun

Challenge:	Efficient reproduction of research papers requires deep domain expertise.
Approach:	They propose a framework that systematically mines implicit knowledge from the cited literature to reproduce experimental code in a complete, end-to-end manner.
Outcome:	The proposed framework surpasses baselines across all metrics and reproduces experimental code in a complete, end-to-end manner.

DeMAC: Enhancing Multi-Agent Coordination with Dynamic DAG and Manager-Player Feedback (2025.findings-emnlp)

Copied to clipboard

Yuhan Liu, Cong Xu, Lu Liu, Yihua Wang, Feiyu Chen, Qi Jia, Yaqian Zhao, Zhichun Wang, Xiang Li

All Information is Valuable: Question Matching over Full Information Transmission Network (2022.findings-naacl)

Challenge:	Multi-agent systems (MAS) powered by large language models struggle to adapt to evolving task dependencies and to handle uncertainties.
Approach:	They propose a Dynamic Environment-Aware Manager-Player Agents Coordination framework that enhances multi-agent coordination through long-term strategic planning.
Outcome:	The proposed framework outperforms traditional reinforcement learning and human-agent collaboration in the Overcooked simulation.

Copied to clipboard

Le Qi, Yu Zhang, Qingyu Yin, Guidong Zheng, Wen Junjie, Jinlong Li, Ting Liu

Counterfactual Data Augmentation for Neural Machine Translation (2021.naacl-main)

Challenge:	Existing methods for question matching only transmit one kind of information while failing to utilize both kinds of information simultaneously.
Approach:	They propose a question matching network that can transmit both representation and interactive information together in a simultaneous fashion.
Outcome:	The proposed approach outperforms strong baseline models on two standard benchmarks.

Copied to clipboard

Qi Liu, Matt Kusner, Phil Blunsom

AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models (2025.findings-acl)

Challenge:	Neural machine translation models often rely on large-scale parallel corpora for training, exhibiting degraded performance on low-resource languages.
Approach:	They propose a method that interprets language models and phrasal alignment causally and generates augmented parallel translation corpora by sampling new source phrases from a masked language model.
Outcome:	The proposed method improves translation, backtranslation and translation robustness on IWSLT’15 English Vietnamese, WMT’17 English - German, and WMT'18 English – Turkish.

Copied to clipboard

Qi Liu, Jingqing Ruan, Hao Li, Haodong Zhao, Desheng Wang, Jiansong Chen, Wan Guanglu, Xunliang Cai, Zhi Zheng, Tong Xu

OpenAttack: An Open-source Textual Adversarial Attack Toolkit (2021.acl-demo)

Challenge:	Existing multi-objective preference alignment methods for large language models face limitations such as auxiliary reward/reference models and computational complexity.
Approach:	They propose a framework that achieves dynamic balance across preference dimensions by using dimension-aware generation metrics as implicit rewards.
Outcome:	Empirical results show that AMoPO outperforms state-of-the-art methods by 28.5% .

Copied to clipboard

Guoyang Zeng, Fanchao Qi, Qianrui Zhou, Tingji Zhang, Zixian Ma, Bairu Hou, Yuan Zang, Zhiyuan Liu, Maosong Sun

Eval-RAR: Evaluation-Driven Retrieval-Augmented Reasoning via Reinforcement Learning (2026.findings-acl)

Challenge:	Various attack models are distinct and implemented with different programming frameworks and settings, which hinders quick utilization and fair comparison of attack models.
Approach:	They propose an open-source textual adversarial attack toolkit to solve these issues by combining 15 typical attack models into one toolkit.
Outcome:	The proposed toolkit supports all attack types, multilinguality, and parallel processing.

Copied to clipboard

Heng Yu, Rui Li, Qi Liu, Wenjun Feng, Junfeng Kang, Yi Zhan

Empirical Study of Zero-Shot NER with ChatGPT (2023.emnlp-main)

Challenge:	Existing methods for retrieval-augmented generation fail to provide explicit supervision for internal reasoning process.
Approach:	They propose an Evaluation-driven Retrieval-Augmented Reasoning framework that uses reinforcement learning and a fine-grained evaluation reward to optimize the process.
Outcome:	Eval-RAR outperforms existing methods on QA benchmarks on seven single-hop and multi-hop tasks.

Copied to clipboard

Tingyu Xie, Qi Li, Jian Zhang, Yan Zhang, Zuozhu Liu, Hongwei Wang

Low-Resource NLP

Challenge:	Large language models (LLMs) have been a key component of natural language processing (NLP) .
Approach:	They propose to decompose the NER task into simpler subproblems by labels and propose a syntactic augmentation strategy to stimulate model's intermediate thinking.
Outcome:	The proposed methods achieve remarkable improvements for zero-shot NER across seven benchmarks, including Chinese and English datasets.

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering (2024.emnlp-main)

Copied to clipboard

Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang

Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization (2025.findings-emnlp)

Challenge:	Existing retrieval-augmented generation methods rely on multiple calls of large language models (LLMs) Large-language models lack knowledge underrepresented in training data and still face hallucinations.
Approach:	They propose an efficient retriever for multi-hop question answering that generates new queries iteratively without the need for LLM calls.
Outcome:	The proposed method surpasses existing methods on three open-domain multi-hop question-answering datasets.

Copied to clipboard

Guangliang Liu, Zimo Qi, Xitong Zhang, Lei Jiang, Kristen Johnson

MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs (2025.findings-acl)

Challenge:	Prior research has shown that LLMs fail to perform satisfactorily on moral cognizance tasks .
Approach:	They propose to use curated datasets to improve LLMs' moral cognizance . they find pragmatic dilemma constrains generalization ability of current learning paradigms .
Outcome:	The proposed learning paradigms fail to perform on moral cognizance tasks, the authors show . they show that the pragmatic dilemma is the primary bottleneck for moral reasoning acquisition .

Copied to clipboard

Yongqi Fan, Yating Wang, Guandong Wang, Zhai Jie, Jingping Liu, Qi Ye, Tong Ruan

Question Answering

Challenge:	Existing evaluation methods overlook the distinction between factoid and non-factoidic questions.
Approach:	They propose a method that distinguishes open-ended questions and ranks candidate answers . they propose QA requires longer answer statements and nuanced reasoning processes .
Outcome:	The proposed method better aligns with human annotations and offers more interpretable results.

Characterizing the Impacts of Instances on Robustness (2023.findings-acl)

Copied to clipboard

Rui Zheng, Zhiheng Xi, Qin Liu, Wenbin Lai, Tao Gui, Qi Zhang, Xuanjing Huang, Jin Ma, Ying Shan, Weifeng Ge

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

Challenge:	Existing defense approaches focus on developing new model structures or training algorithms, but they do little to tap the potential of training instances.
Approach:	They propose a method that can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.
Outcome:	The proposed method can distinguish between robust and non-robust instances according to the model’s sensitivity to perturbations on individual instances during training.

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

LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding (2025.emnlp-main)

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

Yuxuan Hu, Jihao Liu, Ke Wang, Jinliang Zheng, Weikang Shi, Manyuan Zhang, Qi Dou, Rui Liu, Aojun Zhou, Hongsheng Li

DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression (2025.acl-long)

Challenge:	Recent advances in Large Language Models have opened new avenues for solving complex optimization problems, including Neural Architecture Search (NAS).
Approach:	They propose a framework that leverages LLMs for cross-domain neural architecture optimization without extensive domain-specific tuning.
Outcome:	The proposed framework achieves competitive performance in both in-domain and out-of-domain tasks.

Copied to clipboard

Yi Zhao, Zuchao Li, Hai Zhao, Baoyuan Qi, Liu Guoming

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

Challenge:	Existing methods rely on information entropy as the metric to compress lexical units, but ignore attention-critical tokens and information . recent advent of In-Context Learning (ICL), Chain-of-Thought (CoT), and Retrieval Augmented Generation (RAG) technologies has significantly invigorated the landscape of applications based on Large Language Models (LLMs).
Approach:	They propose a dynamic attention-aware approach to task-agnostic prompt compression . they integrate entropy and attention information to achieve fine-grained prompt compression.
Outcome:	Experiments show that the proposed approach improves across tasks and LLMs.

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

SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

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

Yiyang Gu, Junwei Yang, Junyu Luo, Ye Yuan, Bin Feng, Yingce Xia, Shufang Xie, Kaili Liu, Bohan Wu, Qi Shi, Haoran Li, Beier Xiao, Zhiping Xiao, Xiao Luo, Weizhi Zhang, Philip S. Yu, Zequn Liu, Ming Zhang

WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement (2026.acl-long)

Challenge:	Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach:	They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome:	The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.

Copied to clipboard

Fangyuan Li, Pengfei Li, Shijie Wang, Junqi Gao, Jianxing Liu, Biqing Qi, Yuqiang Li

Using the Past Knowledge to Improve Sentiment Classification (2020.findings-emnlp)

Challenge:	Existing methods for self-improvement of large language models with verifiable rewards (RLVR) can drift over iterations, while corpus-grounded approaches rely on curated data environments.
Approach:	They propose a Web-grounded Iterative Self-play Tree framework for domain-targeted reasoning improvement that learns directly from the open-web without requiring any pre-arranged domain corpus.
Outcome:	The proposed framework outperforms both purely endogenous self-evolution and corpus-grounded self-play baselines and is domain-steerable.

Copied to clipboard

Qi Qin, Wenpeng Hu, Bing Liu

Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases (2025.acl-long)

Challenge:	Existing model retains knowledge learned from past tasks and selectively transfers it to new task to help it learn better.
Approach:	They propose a lifelong learning model that can retain and selectively transfer the knowledge learned in the past to help learn the new task.
Outcome:	The proposed model outperforms strong baselines, including even multiple task learning.

Copied to clipboard

Rena Wei Gao, Xuetong Wu, Tatsuki Kuribayashi, Mingrui Ye, Siya Qi, Carsten Roever, Yuanxing Liu, Zheng Yuan, Jey Han Lau

SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains (2025.naacl-long)

Challenge:	Large Language Models (LLMs) can simulate non-native-like English use observed in human second language (L2) learners interfered with by their native first language (N1) knowledge.
Approach:	They use large language models to simulate non-native-like English use observed in human second language (L2) learners, and then compare their outputs to real L2 learner data.
Outcome:	The proposed models replicate L1-dependent patterns observed in human second language (L2) learners, with distinct influences from various languages.

Copied to clipboard

Ran Xu, Hui Liu, Sreyashi Nag, Zhenwei Dai, Yaochen Xie, Xianfeng Tang, Chen Luo, Yang Li, Joyce C. Ho, Carl Yang, Qi He

ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs’ Capability via Chart Editing (2025.findings-acl)

Challenge:	Retrieval-augmented generation (RAG) enhances the question answering abilities of large language models (LLMs) however, adapting general-purpose RAG systems to specialized fields poses unique challenges due to distribution shifts and limited access to domain-specific data.
Approach:	They propose a method that equips large language models with joint capabilities of question answering and question generation for domain adaptation.
Outcome:	Experiments on 11 datasets across three different domains verify the efficacy of SimRAG over baselines by 1.2%–8.6%.

Copied to clipboard

Xuanle Zhao, Xuexin Liu, Yang Haoyue, Xianzhen Luo, Fanhu Zeng, Jianling Li, Qi Shi, Chi Chen

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

Challenge:	Existing evaluations of multimodal large language models rely on limited case studies . however, they lack the ability to generate accurate edits according to the instructions .
Approach:	They propose a benchmark for chart editing that includes 1,405 edit instructions applied to 233 real-world charts.
Outcome:	The proposed benchmark includes 1,405 diverse editing instructions applied to 233 real-world charts.

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

QuoteR: A Benchmark of Quote Recommendation for Writing (2022.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

Fanchao Qi, Yanhui Yang, Jing Yi, Zhili Cheng, Zhiyuan Liu, Maosong Sun

Challenge:	Existing methods to recommend quotes are evaluated on unpublished datasets .
Approach:	They propose to build a dataset that is open and contains three parts including English, standard Chinese and classical Chinese.
Outcome:	The proposed model outperforms existing methods on all three parts of QuoteR.

Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information (2022.findings-acl)

Copied to clipboard

Fanchao Qi, Chuancheng Lv, Zhiyuan Liu, Xiaojun Meng, Maosong Sun, Hai-Tao Zheng

MASFactory: A Graph-centric Framework for Orchestrating LLM-Based Multi-Agent Systems with Vibe Graphing (2026.acl-demo)

Challenge:	Existing sememe KBs only cover a few languages, which hinders the wide utilization of sememes.
Approach:	They propose to build a multilingual sememe KB based on a dictionary called BabelNet . they use multilingual synonyms, multilingual glosses and images to encode sememes .
Outcome:	The proposed model outperforms previous methods in terms of MAP and F1 scores.

Copied to clipboard

Yang Liu, Jinxuan Cai, Yishen Li, Qi Meng, Zedi Liu, Xin Li, Chen Qian, Chuan Shi, Cheng Yang

OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)

Challenge:	Large language model-based multi-agent systems (MAS) are increasingly used to extend agentic problem solving via role specialization and collaboration.
Approach:	They propose a graph-centric framework for orchestrating large language model-based multi-agent systems . they compile a user's natural-language intent into an editable workflow specification and then into an executable graph .
Outcome:	The proposed framework compiles natural-language intent into an executable graph and then compile and executes it at runtime.

Copied to clipboard

Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks.
Approach:	They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions.
Outcome:	The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning.

Copied to clipboard

Hexiang Tan, Fei Sun, Sha Liu, Du Su, Qi Cao, Xin Chen, Jingang Wang, Xunliang Cai, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng

Challenge:	Existing detection methods fail to account for self-consistent error . study identifies self-consistency errors and evaluates them .
Approach:	They propose a method that fuses hidden state evidence from an external verifier LLM to detect self-consistent errors.
Outcome:	The proposed method significantly enhances performance on self-consistent errors across three LLM families.

Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage (2026.acl-long)

Copied to clipboard

Xueting Li, Qi Liu, Chenghao Xu, Xu Yang, Guangtao Lyu, Jiahua Li, Cheng Deng

Explainability & Interpretability in NLP

Challenge:	Existing visual token pruning methods leverage simple metrics derived from human experience, such as attention or similarity, to rank and select tokens within a highly entangled feature space.
Approach:	They propose a novel visual token pruning method that uses a concept-driven paradigm to quantify the Marginal Semantic Gain of each token's contribution to uncovered concepts.
Outcome:	The proposed method outperforms state-of-the-art methods in a concept-driven model while maintaining semantic completeness.

SDAR-VL: Stable and Efficient Block-wise Diffusion for Vision-Language Understanding (2026.acl-long)

Copied to clipboard

Shuang Cheng, Yuhua Jiang, Zineng Zhou, Dawei Liu, Tao Wang, Linfeng Zhang, Biqing Qi, Bowen Zhou

GLGE: A New General Language Generation Evaluation Benchmark (2021.findings-acl)

Challenge:	Existing block-wise discrete diffusion models lack robust autoregressive (AR) decoders.
Approach:	They propose a block-wise discrete diffusion framework for large-scale vision-language understanding with a progressive beta noise curriculum.
Outcome:	The proposed framework improves training efficiency, convergence stability, and task performance over conventional block diffusion.

Copied to clipboard

Dayiheng Liu, Yu Yan, Yeyun Gong, Weizhen Qi, Hang Zhang, Jian Jiao, Weizhu Chen, Jie Fu, Linjun Shou, Ming Gong, Pengcheng Wang, Jiusheng Chen, Daxin Jiang, Jiancheng Lv, Ruofei Zhang, Winnie Wu, Ming Zhou, Nan Duan

Toward Optimal LLM Alignments Using Two-Player Games (2025.findings-emnlp)

Challenge:	Multi-task benchmarks focus on a range of Natural Language Understanding (NLU) tasks without considering the Natural Language Generation (NLG) models.
Approach:	They propose a multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks.
Outcome:	The proposed benchmarks are based on GLUE and Su-perGLUE for English and several other languages.

Copied to clipboard

Rui Zheng, Hongyi Guo, Zhihan Liu, Xiaoying Zhang, Yuanshun Yao, Xiaojun Xu, Zhaoran Wang, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang, Yang Liu, Hang Li

Text Anomaly Detection with Simplified Isolation Kernel (2025.findings-emnlp)

Challenge:	Alignment of large language models (LLM) is a process that ensures the model’s responses to user prompts align with human intentions and social values.
Approach:	They propose an alignment method based on a two-agent game consisting of an adversarial agent and a defensive agent.
Outcome:	The proposed method improves on a two-agent game with an adversarial agent and a defensive agent.

Copied to clipboard

Yang Cao, Sikun Yang, Yujiu Yang, Lianyong Qi, Ming Liu

GEM: Gestalt Enhanced Markup Language Model for Web Understanding via Render Tree (2023.emnlp-main)

Challenge:	High-dimensional dense embeddings extracted by large language models pose memory requirements and high computation time.
Approach:	They propose a method that maps high-dimensional dense embeddings to lower-dimensional sparse representations while preserving crucial anomaly characteristics.
Outcome:	The proposed method achieves better detection performance than 11 SOTA anomaly detection algorithms while maintaining computational efficiency and low memory cost.

Copied to clipboard

Zirui Shao, Feiyu Gao, Zhongda Qi, Hangdi Xing, Jiajun Bu, Zhi Yu, Qi Zheng, Xiaozhong Liu

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger (2021.acl-long)

Challenge:	Existing models that use plain HTMLs do not include crucial visual information in the rendered web.
Approach:	They propose a Gestalt Enhanced Markup Language Model for hosting visual information without visual input.
Outcome:	The proposed model can handle multiple downstream tasks without visual input.

Copied to clipboard

Fanchao Qi, Mukai Li, Yangyi Chen, Zhengyan Zhang, Zhiyuan Liu, Yasheng Wang, Maosong Sun

Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer (2021.emnlp-main)

Challenge:	Existing methods for textual backdoor attacks insert additional contents into normal samples as triggers, causing detection and blocking of backdoors.
Approach:	They propose to use syntactic structure as trigger in textual backdoor attacks . they propose to achieve similar attack performance but have higher invisibility .
Outcome:	The proposed method achieves almost 100% success rate but has higher invisibility and stronger resistance to defenses than the insertion-based methods.

Copied to clipboard

Fanchao Qi, Yangyi Chen, Xurui Zhang, Mukai Li, Zhiyuan Liu, Maosong Sun

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization (2025.findings-emnlp)

Challenge:	Experimental results show that popular NLP models are vulnerable to both adversarial and backdoor attacks based on text style transfer.
Approach:	They propose to conduct adversarial and backdoor attacks based on text style transfer . the authors propose to use text style to alter the style of a sentence .
Outcome:	The proposed methods show that popular models are vulnerable to both attacks based on text style transfer . the results show that the proposed methods perform better than baselines in many aspects .

Copied to clipboard

Zhensheng Jin, Xinze Li, Yifan Ji, Chunyi Peng, Zhenghao Liu, Qi Shi, Yukun Yan, Shuo Wang, Furong Peng, Ge Yu

Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems (2021.emnlp-main)

Challenge:	Existing methods to train LLMs suffer from overthinking, leading to lengthy reasoning traces . Existing approaches to train large language models suffer from this problem .
Approach:	They propose a method to combine multiple reasoning chains for training LLMs . they use stepwise exploration and long-short switched sampling to evaluate reasoning paths .
Outcome:	The proposed method reduces reasoning lengths by approximately 30-50% . it also maintains or improves reasoning accuracy compared to baselines .

Copied to clipboard

Yicheng Zou, Zhihua Liu, Xingwu Hu, Qi Zhang

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation (2025.emnlp-main)

Challenge:	Existing models with seq2seq framework lack ability to effectively manage concept transitions . lack of concept management strategies might lead to incoherent dialogue due to loosely connected concepts .
Approach:	They propose a concept-guided non-autoregressive model for open-domain dialogue generation that learns to identify multiple associated concepts from a conceptual graph and a customized Insertion Transformer to perform concept-directed generation to complete a response.
Outcome:	The proposed model outperforms state-of-the-art models in automatic and human evaluations with substantially faster inference speed.

Copied to clipboard

Daiye Miao, Yufang Liu, Jie Wang, Changzhi Sun, Yunke Zhang, Demei Yan, Shaokang Dong, Qi Zhang, Yuanbin Wu

Incorporating Dynamic Semantics into Pre-Trained Language Model for Aspect-based Sentiment Analysis (2022.findings-acl)

Challenge:	Existing studies have shown that LoRA introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning.
Approach:	They propose a method that leverages importance information from the pretrained model’s weights to mitigate LoRA redundancy.
Outcome:	The proposed method significantly reduces the number of trainable parameters required for task adaptation while providing a task-aligned perspective for LoRA redundancy reduction.

Copied to clipboard

Kai Zhang, Kun Zhang, Mengdi Zhang, Hongke Zhao, Qi Liu, Wei Wu, Enhong Chen

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) predicts sentiment polarity towards a specific aspect in a sentence.
Approach:	They propose to use a dynamic aspect-oriented semantics-based method to learn ABSA.
Outcome:	The proposed method can learn dynamic aspect-oriented semantics for ABSA on three benchmark datasets.

Divide and Conquer: Legal Concept-guided Criminal Court View Generation (2024.findings-emnlp)

Copied to clipboard

Qi Xu, Xiao Wei, Hang Yu, Qian Liu, Hao Fei

UER: An Open-Source Toolkit for Pre-training Models (D19-3)

Challenge:	Existing methods for creating rationales for criminal cases do not pay enough attention to the important legal concepts.
Approach:	They propose a legal concept-guided court view generation framework that generates rationales based on predicted legal concepts . they first divide the court view into sub-views, then employ a solver and verifier to generate and select rationale.
Outcome:	The proposed model generates coherent and coherent court views on a real-world criminal case dataset.

Copied to clipboard

Zhe Zhao, Hui Chen, Jinbin Zhang, Xin Zhao, Tao Liu, Wei Lu, Xi Chen, Haotang Deng, Qi Ju, Xiaoyong Du

Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models (2024.emnlp-main)

Challenge:	Existing work on pre-training models have shown that it is important to use a framework to deploy various pre- training models efficiently.
Approach:	They propose an assemble-on-demand pre-training toolkit that assembles pre-trained models on demand and encapsulates them with rich modules.
Outcome:	The proposed framework can reproduce state-of-the-art models or develop models that remain unexplored.

Copied to clipboard

Yu Yuan, Lili Zhao, Kai Zhang, Guangting Zheng, Qi Liu

Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models (2020.findings-emnlp)

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in various tasks, but may rely on dataset biases as shortcuts for prediction.
Approach:	They propose to use a test suite to evaluate the impact of shortcuts on LLMs' performance.
Outcome:	The proposed test suite incorporates six shortcut types, five evaluation metrics, and four prompting strategies.

Copied to clipboard

Zhiyuan Zhang, Xiaoqian Liu, Yi Zhang, Qi Su, Xu Sun, Bin He

Orca: A Few-shot Benchmark for Chinese Conversational Machine Reading Comprehension (2023.findings-emnlp)

Challenge:	Existing knowledge graph embedding models suffer from limited knowledge representation due to sparse and noisy dataset annotations.
Approach:	They propose to use pretrained language models to enhance knowledge representation by leveraging world knowledge from pretrained models.
Outcome:	Extensive experiments show that the proposed framework can improve results over existing models.

Copied to clipboard

Nuo Chen, Hongguang Li, Junqing He, Yinan Bao, Xinshi Lin, Qi Yang, Jianfeng Liu, Ruyi Gan, Jiaxing Zhang, Baoyuan Wang, Jia Li

Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Challenge:	Existing benchmarks for conversational machine reading comprehension are inconsistent with real scenarios.
Approach:	They propose to use a Chinese CMRC benchmark to evaluate model's generalization ability towards diverse domains by using zero-shot/few-shot settings.
Outcome:	The proposed benchmarks are based on 831 hot-topic driven conversations with 4,742 turns and cover 33 domains.

Copied to clipboard

Chang Ma, Haiteng Zhao, Lin Zheng, Jiayi Xin, Qintong Li, Lijun Wu, Zhihong Deng, Yang Lu, Qi Liu, Sheng Wang, Lingpeng Kong

Pretraining the Noisy Channel Model for Task-Oriented Dialogue (2021.tacl-1)

Challenge:	Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach:	They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome:	The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.

Copied to clipboard

Qi Liu, Lei Yu, Laura Rimell, Phil Blunsom

EVIDENCEMINER: Textual Evidence Discovery for Life Sciences (2020.acl-demos)

Challenge:	Current research on task-oriented dialogue models suffers from the explaining-away effect, manifested in models that favor short and generic responses.
Approach:	They propose to factorize the dialogue task into two models, the distribution of the context given the response, and the prior for the response itself, using Bayes' theorem.
Outcome:	The proposed model mitigates the explaining-away effect and allows the principled incorporation of large pretrained models for the response prior.

Copied to clipboard

Xuan Wang, Yingjun Guan, Weili Liu, Aabhas Chauhan, Enyi Jiang, Qi Li, David Liem, Dibakar Sigdel, John Caufield, Peipei Ping, Jiawei Han

Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data (2025.findings-naacl)

Challenge:	EVIDENCEMINER is a web-based system that allows users to query a natural language statement and retrieve textual evidence from a background corpora for life sciences.
Approach:	They propose a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences.
Outcome:	EVIDENCEMINER is a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences.

Copied to clipboard

Juanhui Li, Sreyashi Nag, Hui Liu, Xianfeng Tang, Sheikh Muhammad Sarwar, Limeng Cui, Hansu Gu, Suhang Wang, Qi He, Jiliang Tang

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

Challenge:	Large Language Models (LLMs) have demonstrated superior language understanding abilities in many real-world NLP applications.
Approach:	They propose a learning-based sample selection method that incorporates signals from both teacher and student to enhance model performance.
Outcome:	The proposed method improves model performance across datasets with higher data efficiency.

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

MPII: Multi-Level Mutual Promotion for Inference and Interpretation (2022.acl-long)

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

Yan Liu, Sanyuan Chen, Yazheng Yang, Qi Dai

Dynamic Multi-granularity Attribution Network for Aspect-based Sentiment Analysis (2024.emnlp-main)

Challenge:	Existing methods for providing interpretations provide human-unfriendly interpretations, resulting in sub-optimal performance.
Approach:	They propose a multi-level Mutual Promotion mechanism for self-evolved inference and sentence-level interpretation that integrates inference with interpretation in an autoregressive manner.
Outcome:	The proposed approach outperforms baseline models on NLI and CQA tasks for both inference performance and interpretation quality.

Copied to clipboard

Yanjiang Chen, Kai Zhang, Feng Hu, Xianquan Wang, Ruikang Li, Qi Liu

Sentiment Analysis

Challenge:	Existing methods for predicting sentiment polarity of aspects are susceptible to interference caused by irrelevant contexts and lack sentiment knowledge at a data-specific level.
Approach:	They propose a novel Aspect-based sentiment analysis method that leverages attention scores to model the relationships between aspects and contexts.
Outcome:	The proposed method is able to predict sentiments from a set of five benchmark datasets.

SUA: Stealthy Multimodal Large Language Model Unlearning Attack (2025.emnlp-main)

Copied to clipboard

Xianren Zhang, Hui Liu, Delvin Ce Zhang, Xianfeng Tang, Qi He, Dongwon Lee, Suhang Wang

Towards Long Context Hallucination Detection (2025.findings-naacl)

Challenge:	Multimodal Large Language Models (MLLMs) trained on massive data may memorize sensitive personal information and photos, posing privacy and copyright concerns.
Approach:	They propose a framework that learns a universal noise pattern to recover unlearned information from MLLMs.
Outcome:	The proposed framework learns a universal noise pattern and can reveal unlearned content when applied to images.

Copied to clipboard

Siyi Liu, Kishaloy Halder, Zheng Qi, Wei Xiao, Nikolaos Pappas, Phu Mon Htut, Neha Anna John, Yassine Benajiba, Dan Roth

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Challenge:	Large language models are prone to contextual hallucination, generating information that is either unsubstantiated or contradictory to the given context.
Approach:	They propose a dataset specifically designed for long-context hallucination detection.
Outcome:	The proposed architecture outperforms existing models while providing faster inference.

Copied to clipboard

Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang

Visual Data in NLP

Challenge:	Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach:	They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome:	The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.

Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models (2024.naacl-short)

Copied to clipboard

Tingyu Xie, Qi Li, Yan Zhang, Zuozhu Liu, Hongwei Wang

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers (2025.acl-long)

Challenge:	Existing studies exploring the performance of large language models on named entity recognition tasks have focused on training task-specific LLMs for NER.
Approach:	They propose a training-free self-improving framework that utilizes an unlabeled corpus to stimulate the self-learning ability of LLMs.
Outcome:	The proposed framework improves performance on the named entity recognition task by using an unlabeled corpus.

Copied to clipboard

Zicong Tang, Shi Luohe, Zuchao Li, Baoyuan Qi, Liu Guoming, Lefei Zhang, Ping Wang

Challenge:	Large language models (LLMs) have impressive capabilities across various fields, but their widespread use is facing a severe and realistic challenge, which is their high demand for GPU memory.
Approach:	They propose a KV cache reduction method which balances both shallow and deep layers by using an attention weight based eviction method and a codebook based replacement approach.
Outcome:	The proposed method reduces the KV cache for shallower layers while preserving similar or even better model performance.

Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation (2025.naacl-long)

Copied to clipboard

Tianyu Liu, Jirui Qi, Paul He, Arianna Bisazza, Mrinmaya Sachan, Ryan Cotterell

LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validation (2025.findings-emnlp)

Challenge:	Existing methods to improve language models' performance do not exploit this phenomenon .
Approach:	They propose to use contextual information to select and construct prompts that improve model performance.
Outcome:	The proposed methods show that the mutual information between a context and a question is an effective gauge for language model performance.

Copied to clipboard

Ming Zhang, Yujiong Shen, Zelin Li, Huayu Sha, Binze Hu, Yuhui Wang, Chenhao Huang, Shichun Liu, Jingqi Tong, Changhao Jiang, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang

LCAN: A Label-Aware Contrastive Attention Network for Multi-Intent Recognition and Slot Filling in Task-Oriented Dialogue Systems (2025.findings-emnlp)

Challenge:	Current medical benchmarks have limitations in question design, data sources and evaluation methods.
Approach:	They propose a new benchmark covering five core medical areas . it includes 2,996 questions created from real-world electronic health records .
Outcome:	The proposed model covers five core medical areas and includes 2,996 questions created from real-world electronic health records and expert-designed clinical scenarios.

Copied to clipboard

Shuli Zhang, Zhiqiang You, Xiao Xiang Qi, Peng Liu, Gaode Wu, Kan Xia, Shenguang Huang

Semantic Parsing

Challenge:	Multi-intent utterances processing remains a persistent challenge due to intricate intent-slot dependencies and semantic ambiguities.
Approach:	They propose a label-aware contrastive attention network (LCAN) that integrates label-based attention and contrastive learning strategies to improve semantic understanding and generalization in multi-intent scenarios.
Outcome:	The proposed model improves intent recognition and slot filling performance in multi-intent dialogue systems.

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

Copied to clipboard

Qi Jia, Siyu Ren, Yizhu Liu, Kenny Zhu

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

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

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Copied to clipboard

Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou

Language Agnostic Multilingual Information Retrieval with Contrastive Learning (2023.findings-acl)

Challenge:	XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach:	They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome:	The proposed dataset is labeled in English and includes only natural language understanding tasks.

Copied to clipboard

Xiyang Hu, Xinchi Chen, Peng Qi, Deguang Kong, Kunlun Liu, William Yang Wang, Zhiheng Huang

SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection (2026.acl-industry)

Challenge:	Annotated training data is costly to obtain in many languages .
Approach:	They propose a semantic contrastive loss to align parallel sentences that share the same semantics in different languages and a language contrastive gain to leverage parallel sentence pairs to remove language-specific information from non-parallel corpora.
Outcome:	The proposed model improves retrieval performance while requiring less computational effort.

Copied to clipboard

Zhiyong Cao, Dunqiang Liu, Qi Dai, Haojun Xu, Huai Yuen Khor, Hao Wang, Huan He, Yafei Liu, Ke Ma, Ruqian Shi, Sicheng Zhou, Sijia Yao

Interventional Rationalization (2023.emnlp-main)

Challenge:	High-quality data in training proactive dialogue agents is scarce, despite fine-tuning and reinforcement learning . a recent study has shown that the effectiveness of supervised fine-touring is limited by the lack of high-quality, domain-specific training data.
Approach:	They propose a framework for training recruitment proactive dialogue agents using a high-fidelity user simulator and a multi-dimensional evaluation framework based on Chain-of-Intention.
Outcome:	The proposed framework outperforms existing simulator-based data selection strategies in a real-world recruitment scenario.

Copied to clipboard

Linan Yue, Qi Liu, Li Wang, Yanqing An, Yichao Du, Zhenya Huang

TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval (2026.acl-long)

Challenge:	Existing methods for rationalization use spurious correlations in data to compose rationales and make predictions.
Approach:	They propose a method to discover the causal rationales by using a structural causal model.
Outcome:	The proposed method is based on the causal theory and validates on three real-world datasets.

Copied to clipboard

Yuhang Zhang, Keyan Ding, Peilin Chen, Han Liu, Can Lin, Ruixi Chen, Shiqi Wang, Qi Song

Red Teaming Visual Language Models (2024.findings-acl)

Challenge:	Existing approaches to enzyme–reaction retrieval suffer from poor generalization across tasks and distributions . TIGER is a text-informed generalized enzyme-reaction retrieval framework that bridges enzymes and biochemical reactions.
Approach:	They propose a text-informed generalized enzyme-reaction retrieval framework that leverages protein-to-text generation models to distill textual knowledge from enzyme sequences.
Outcome:	The proposed framework outperforms state-of-the-art methods in enzyme–reaction retrieval tasks and distributions.

Copied to clipboard

Mukai Li, Lei Li, Yuwei Yin, Masood Ahmed, Zhenguang Liu, Qi Liu

Visual Data in NLP

Challenge:	VLMs (Vision-Language Models) can be induced to generate harmful or inaccurate content through specific test cases.
Approach:	They propose a red teaming dataset which encompasses 12 subtasks under 4 primary aspects (faithfulness, privacy, safety, fairness) this dataset is the first to benchmark current VLMs in terms of these 4 aspects .
Outcome:	The proposed dataset shows that 10 open-source VLMs struggle with red teaming in different degrees and have up to 31% performance gap with GPT-4V.

RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering (2024.emnlp-main)

Copied to clipboard

Rujun Han, Yuhao Zhang, Peng Qi, Yumo Xu, Jenyuan Wang, Lan Liu, William Yang Wang, Bonan Min, Vittorio Castelli

SUT: Active Defects Probing for Transcompiler Models (2023.emnlp-main)

Challenge:	Existing datasets for question answering based on retrieval augmented generation (RAG-QA) are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization.
Approach:	They propose a dataset that integrates short extractive answers from multiple documents into a single coherent narrative.
Outcome:	The proposed dataset integrates short extractive answers from multiple documents into a single coherent narrative, covering 26K queries and large corpora across seven different domains.

Copied to clipboard

Mengnan Qi, Yufan Huang, Maoquan Wang, Yongqiang Yao, Zihan Liu, Bin Gu, Colin Clement, Neel Sundaresan

Machine Translation

Challenge:	Existing datasets are often criticized for their lack of granularity, which can mask deficiencies in basic syntactic elements that humans care about.
Approach:	They propose a new program translation metrics that address basic syntax errors . they propose BLUE, CodeBLUE and computation accuracy metrics which address these errors based on a highly interpretable evaluation harness.
Outcome:	The proposed model passes the unit tests with a 26.15% pass rate compared to previous models .

CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference (2025.acl-long)

Copied to clipboard

Jinglong Luo, Guanzhong Chen, Yehong Zhang, Shiyu Liu, Hui Wang, Yue Yu, Xun Zhou, Yuan Qi, Zenglin Xu

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

Challenge:	Existing privacy-preserving Transformer Inference frameworks suffer from high computational overhead and performance losses.
Approach:	They propose a framework that integrates random permutations and SMPC to address the "impossible trinity" CENTAUR resists diverse data reconstruction attacks and boosts inference speed by 5.030.4 times .
Outcome:	CENTAUR achieves an unprecedented balance between privacy, efficiency, and performance.

Copied to clipboard

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

NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Queries (2024.findings-acl)

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

Copied to clipboard

Shudan Zhang, Hanlin Zhao, Xiao Liu, Qinkai Zheng, Zehan Qi, Xiaotao Gu, Yuxiao Dong, Jie Tang

RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)

Challenge:	Large language models (LLMs) generate code for productive activities, but current benchmarks for code synthesis are oriented towards introductory tasks on algorithm and data science.
Approach:	They propose a code benchmark to mirror the complexity and variety of scenarios in real-world coding tasks.
Outcome:	The proposed benchmark improves on 39 large language models with close HumanEval scores and achieves an efficiency increase of more than 4 times.

Copied to clipboard

Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang

Think and Recall: Layer-Level Prompting for Lifelong Model Editing (2025.emnlp-main)

Challenge:	Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks.
Approach:	They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes.
Outcome:	The proposed training framework significantly improves upon translation baselines.

Copied to clipboard

Jinke Wang, Zenan Ying, Qi Liu, Wei Chen, Tong Xu, Huijun Hou, Zhi Zheng

Low-Resource NLP

Challenge:	Existing methods for lifelong model editing suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits.
Approach:	They propose a plug-and-play method for knowledge retrieval and storage, i.e., Layer-Level Prompting, which enables seamless and efficient lifelong model editing.
Outcome:	The proposed method outperforms existing methods on question answering and hallucination benchmarks across different LLMs.

VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding (2025.emnlp-main)

Copied to clipboard

Zhaowei Liu, Xin Guo, Haotian Xia, Lingfeng Zeng, Fangqi Lou, Jinyi Niu, Mengping Li, Qi Qi, Jiahuan Li, Wei Zhang, Yinglong Wang, Weige Cai, Weining Shen, Liwen Zhang

OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026.acl-long)

Challenge:	Existing benchmarks focus on text comprehension, but MLLMs lack the ability to integrate visual data over financial visuals.
Approach:	They evaluate 21 state-of-the-art multimodal large language models in a zero-shot setting . they use an annotated question–answer pair from eight common financial image modalities .
Outcome:	The new benchmark outperforms existing models but trailed financial experts by 14 percentage points.

Copied to clipboard

Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong

Challenge:	Existing methods for detecting unsafe mobile GUI agents are underexplored.
Approach:	They propose a mobile agent safety detection framework that integrates a formal verifier and a VLM-based contextual judge to detect system-level violations.
Outcome:	The proposed framework achieves 10%–30% improvements over existing approaches across multiple metrics.

A Survey on Proactive Defense Strategies Against Misinformation in Large Language Models (2025.findings-acl)

Copied to clipboard

Shuliang Liu, Hongyi Liu, Aiwei Liu, Duan Bingchen, Zheng Qi, Yibo Yan, He Geng, Peijie Jiang, Jia Liu, Xuming Hu

Robust Membership Inference for Large Language Models under Adversarial Generative Corruption (2026.acl-long)

Challenge:	Existing methods for detection of misinformation generated by large language models fail to mitigate societal risks . authors propose a paradigm shift from passive detection to anticipatory mitigation strategies . existing defenses remain reactionary in an era demanding proactive defense, authors say .
Approach:	They propose a three-pillar approach to prevent misinformation by fortifying integrity of training data and inference reliability by embedding self-corrective mechanisms during reasoning.
Outcome:	The proposed framework improves existing methods in misinformation prevention by 63% . it demonstrates that existing methods exhibit false negative rates against misinformation .

Copied to clipboard

Yuanhong Huang, Huili Wang, Xueying Bai, Jinrui Wang, Jiajun Liu, Ziqin Wang, Wanchun Ni, Shangguang Wang, Tao Qi

Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling (2024.findings-acl)

Challenge:	Membership inference attacks are a promising tool for auditing training data of LLMs . existing methods rely on the assumption that LLM's assign higher confidence scores to training samples than to non-training ones.
Approach:	They propose a membership inference framework that can be robust against adversarial MIAs.
Outcome:	The proposed framework can be robust against adversarial MIA methods and AIGT detectors while maintaining the performance of baselines.

Copied to clipboard

Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang

Challenge:	Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents.
Approach:	They propose a cognitive framework that incorporates first-order and second-order perspective transitions into LLMs to enhance their ability to identify and counteract deceptive information.
Outcome:	The proposed framework enhances LLMs’ ability to identify and counteract deceptive information without extra fine-tuning and data.

Improving Abstractive Dialogue Summarization with Hierarchical Pretraining and Topic Segment (2021.findings-emnlp)

Copied to clipboard

MengNan Qi, Hao Liu, YuZhuo Fu, Ting Liu

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

Challenge:	Existing methods for meeting summary have limited the ability to deal with long-term dependency.
Approach:	They propose a hierarchical transformer encoder-decoder network with multi-task pre-training to capture key sentences at word level and generate them at word-level.
Outcome:	The proposed model is superior to the previous methods in meeting summary datasets AMI and ICSI.

Copied to clipboard

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

Implicit Personalization in Language Models: A Systematic Study (2024.findings-emnlp)

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

Zhijing Jin, Nils Heil, Jiarui Liu, Shehzaad Dhuliawala, Yahang Qi, Bernhard Schölkopf, Rada Mihalcea, Mrinmaya Sachan

EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving (2026.acl-long)

Challenge:	Existing studies have focused on the implicit personalization problem, but no unified framework exists to study it.
Approach:	They propose a mathematical formulation and a moral reasoning framework to study the phenomenon of Implicit Personalization (IP) they propose 'direct intervention' to estimate causal effect of mediator variable that cannot be directly intervened upon.
Outcome:	The proposed method estimates the causal effect of a mediator variable that cannot be directly intervened upon.

Copied to clipboard

Mukai Li, Linfeng Song, Zhenwen Liang, Jiahao Xu, Shansan Gong, Qi Liu, Haitao Mi, Dong Yu

Tiny Scales, Great Challenges: The Limits of Multimodal LLMs in Scale Recognition (2026.acl-long)

Challenge:	Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP) Existing cost analyses regulate only the number of sampling passes, ignoring the substantial disparities in sampling costs.
Approach:	They propose to integrate two complementary methods into a unified EconRL pipeline to increase pass rates under constrained sampling passes.
Outcome:	The proposed method reduces token usage and sample passes while maintaining the original performance.

Copied to clipboard

Jihang Jin, Ronghao Chen, Hao Zhang, Ziyan Liu, Huacan Wang, Qi Ye, Jingping Liu

Larger-Context Tagging: When and Why Does It Work? (2021.naacl-main)

Challenge:	Existing benchmarks focus on a single type of quantity or a specific format, lacking a comprehensive evaluation of scale recognition capabilities.
Approach:	They propose a visual scale recognition benchmark built using images from COCO, Open Images, and Flickr to evaluate scale recognition capabilities of multimodal large language models.
Outcome:	The proposed model achieves 42.60% accuracy, lower than the 97.40% of humans.

Copied to clipboard

Jinlan Fu, Liangjing Feng, Qi Zhang, Xuanjing Huang, Pengfei Liu

Syntactic Text Processing

Challenge:	Existing tagging systems that use sentence-level data are not well understood.
Approach:	They propose a larger-context approach to tagging tasks that incorporates contextual information into existing tapping systems.
Outcome:	The proposed aggregators improve on four tagging tasks and 13 datasets.

E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence (2026.acl-long)

Copied to clipboard

Junbo Qi, Yi Zhang, Hanchu Ni, Che Liu, Zhimin Yao, Ruilin Yang, Xiancong Ren, Liangjian Wen, Wei Ge, Yuya Ieiri, Osamu Yoshie, Yong Dai, Xiaozhu Ju

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

Challenge:	Existing Vision-Language Models (VLMs) lack spatial reasoning, despite text-based CoTs . e-ViC reframes spatial intelligence as a verifiable, tool-using capability, argues a new study.
Approach:	They propose a framework that moves reasoning beyond text into the visual domain . they ground reasoning in pixel-level interactions to enable human-like "look-and-confirm" strategies .
Outcome:	The proposed framework outperforms existing Vision-Language Models with an average gain of 10.1%.

Copied to clipboard

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

Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning (2025.acl-long)

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

Copied to clipboard

Junqi Gao, Xiang Zou, Ying Ai, Dong Li, Yichen Niu, Biqing Qi, Jianxing Liu

H-MAS: Hierarchical Multi-Agent Scheduling for Multi-Tenant LLM Serving (2026.findings-acl)

Challenge:	Existing methods for enhancing LLM reliability suffer from inefficient information aggregation and rigid reasoning schemes.
Approach:	They propose a method that explicitly models external knowledge integration capabilities by explicitly modeling knowledge relationships.
Outcome:	The proposed method outperforms existing methods in multiple graph reasoning tasks.

Copied to clipboard

Yuhan Liu, Cong Xu, Qi Jia, Yihua Wang, Feiyu Chen, Liang Jin, Lu Liu, Yaqian Zhao, Yuting Ding, Xiang Li

Challenge:	Multi-tenant Model-as-a-Service (MaaS) workloads exhibit non-stationarity across multiple time scales . existing request schedulers often rely on a fixed policy that remains unchanged at runtime .
Approach:	They propose a hierarchical multi-agent scheduler that operates in a layered closed loop . they propose to maintain 1.2–3.0 higher Goodput than SGLang and vLLM .
Outcome:	Experiments show that H-MAS achieves 1.2–3.0 higher Goodput than SGLang and vLLM . it maintains more stable QoS under diverse request lengths and heterogeneous SLO targets .

Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference Modeling (2025.acl-long)

Copied to clipboard

Shihan Dou, Jiayi Chen, Chenhao Huang, Feng Chen, Wei Chengzhi, Huiyuan Zheng, Shichun Liu, Yan Liu, Chenxiao Liu, Chao Xin, Lin Yan, Zongzhang Zhang, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Existing reward models concatenate contexts and responses, but they often ignore crucial segments of the context that are important for evaluating the response quality.
Approach:	They propose a reward model that evaluates the response quality based on a given context and assigns a rewards reward.
Outcome:	The proposed framework significantly improves preference modeling by increasing attention to relevant information within the context and achieves better generalizability.

Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification (2021.emnlp-main)

Copied to clipboard

Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu

Fine-grained Medical Vision-Language Representation Learning for Radiology Report Generation (2023.emnlp-main)

Challenge:	Existing methods leverage programs that contain rich logical information to enhance the verification process.
Approach:	They propose a table-based fact verification task as an evidence retrieval framework . they retrieve logic-level program-like evidence from the given table and a statement as supplementary evidence for the table .
Outcome:	The proposed method is able to retrieve logic-level program-like evidence from a table and a statement as supplementary evidence for the table.

Copied to clipboard

Siyuan Wang, Bo Peng, Yichao Liu, Qi Peng

Visual Data in NLP

Challenge:	Existing methods to learn medical vision-language representations by contrasting images with entire reports are not effective.
Approach:	They propose a phenotype-driven medical vision-language representation learning framework to bridge the gap between visual and textual modalities for improved text-oriented generation.
Outcome:	The proposed framework bridges the gap between visual and textual modalities for improved radiology report generation.

Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMs (2025.findings-emnlp)

Copied to clipboard

Yunzhe Qi, Jinjin Tian, Tianci Liu, Ruirui Li, Tianxin Wei, Hui Liu, Xianfeng Tang, Monica Xiao Cheng, Jingrui He

Cognitive Alpha Mining via LLM-Driven Code-Based Evolution (2026.acl-long)

Challenge:	Learning to Instruct is a new paradigm for black-box LLMs with inaccessible internal states.
Approach:	They propose a new paradigm that formulates instruction optimization as an LLM fine-tuning objective for a white-box “instruction engineer” LLM.
Outcome:	The proposed framework outperforms strong baselines in performance and efficiency.

Copied to clipboard

Fengyuan Liu, Yi Huang, Sichun Luo, Yuqi Wang, Yazheng Yang, Xinye Li, Zefa Hu, Junlan Feng, Qi Liu

metaCAT: A Metadata-based Task-oriented Chatbot Annotation Tool (2020.aacl-demo)

Challenge:	Existing approaches to finding effective predictive signals from financial data are limited by their complexity and low signal-to-noise ratio.
Approach:	They propose a framework that combines code-level alpha representation with LLM-driven reasoning and evolutionary search.
Outcome:	The proposed framework combines code-level alpha representation with LLM-driven reasoning and evolutionary search.

Copied to clipboard

Ximing Liu, Wei Xue, Qi Su, Weiran Nie, Wei Peng

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

Challenge:	Creating high-quality annotated dialogue corpora necessitates a high level of human engagements.
Approach:	They propose to develop an annotation tool specifically for developing task-oriented dialogue data that provides comprehensive metadata annotation coverage to the domain, intent, and span information.
Outcome:	The tool provides comprehensive metadata annotation coverage to domain, intent, and span information.

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

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models (2024.findings-naacl)

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

Wei He, Shichun Liu, Jun Zhao, Yiwen Ding, Yi Lu, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

WantWords: An Open-source Online Reverse Dictionary System (2020.emnlp-demos)

Challenge:	Existing methods that rely on limited demos and out-of-demonstration (OOD) queries fail when faced with out- of-demotion queries.
Approach:	They propose a query-aware prompting method that elicits the inherent generalizability of large language models by query-based demo generation.
Outcome:	The proposed method outperforms state-of-the-art methods in the OOD setting and two public math benchmarks.

Copied to clipboard

Fanchao Qi, Lei Zhang, Yanhui Yang, Zhiyuan Liu, Maosong Sun

Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? (2026.findings-acl)

Challenge:	Existing reverse dictionary systems only support English reverse dictionary queries . a reverse dictionary can help people who can't remember a word from memory .
Approach:	They propose an online reverse dictionary system that outperforms other reverse dictionary systems . it supports Chinese and English-Chinese as well as Chinese-English cross-lingual reverse dictionary queries .
Outcome:	The proposed reverse dictionary outperforms other reverse dictionary systems on performance . it supports Chinese and English-Chinese as well as Chinese-English queries .

Copied to clipboard

Zewen Liu, Juntong Ni, Xianfeng Tang, Max SY Lau, Qi He, Wenpeng Yin, Wei Jin

UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost (2021.naacl-main)

Challenge:	Large Language Models (LLMs) and Multimodal LLMs (MLLMs) show strong performance in complex reasoning tasks, but their ability to extract symbolic laws from time series data remains underexplored.
Approach:	They propose a benchmark to assess symbolic reasoning over real-world time series across three tasks: multivariate symbolic regression, Boolean network inference, and causal discovery.
Outcome:	The proposed framework integrates LLMs with genetic programming to form a closed-loop symbolic reasoning system.

Copied to clipboard

Zhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie, Tao Qin, Xinyu Dai, Tie-Yan Liu

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code (2026.findings-acl)

Challenge:	Existing approaches to improve the performance of natural language processing models are over-parameterized and overfitted.
Approach:	They propose an approach to integrate dropout techniques into the training of Transformer models.
Outcome:	The proposed approach can achieve 1.5 BLEU improvement on IWSLT14 translation tasks and better accuracy for the classification even using strong pre-trained RoBERTa as backbone.

Copied to clipboard

ShangZhan Li, Xinyu Yin, Xuanyu Jin, Ye He, Yuxin Zhou, Yuxuan Li, Xu Han, Wanxiang Che, Qi Shi, Ting Liu, Maosong Sun

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

Challenge:	Current development practices face a dichotomy between automation and performance.
Approach:	They propose a framework to empower LLMs with the capability of automated explicit vectorization.
Outcome:	The proposed framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench.

Copied to clipboard

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

ReAL: How Can LLMs Simulate the Real Teacher? Retrieval-enhanced Agent for Adaptive Learning (2025.findings-emnlp)

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

Rui Lv, Qi Liu, Weibo Gao, Jiatong Li, Kai Zhang, Shiwei Tong

SMR: State Memory Replay for Long Sequence Modeling (2024.findings-acl)

Challenge:	Prior methods model learner-item interactions based only on ID sequences, leading to insufficient use of both learner and item information.
Approach:	They propose a Retrieval-enhanced Agent for Adaptive Learning powered by large language models to simulate teacher decision-making with extensive prior knowledge and teaching experience.
Outcome:	The proposed model outperforms existing models on three real-world datasets in both internal and external perspectives.

Copied to clipboard

Biqing Qi, Junqi Gao, Kaiyan Zhang, Dong Li, Jianxing Liu, Ligang Wu, Bowen Zhou

Challenge:	Existing state space models (SSMs) address non-uniform sampling, but their recursive structures impede efficient SSM computation via convolution.
Approach:	They propose a plug-and-play mechanism to solve the Non-Stable State problem by adjusting input sequences with early memories.
Outcome:	The proposed method overcomes the non-uniform sample processing problem . it can achieve Sampling Step Adaptation (SSA) by adjusting input sequences with early memories.

StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)

Copied to clipboard

Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang

Towards Better Entity Linking with Multi-View Enhanced Distillation (2023.acl-long)

Challenge:	Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective.
Approach:	They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality.
Outcome:	The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality.

Copied to clipboard

Yi Liu, Yuan Tian, Jianxun Lian, Xinlong Wang, Yanan Cao, Fang Fang, Wen Zhang, Haizhen Huang, Weiwei Deng, Qi Zhang

MIND: A Large-scale Dataset for News Recommendation (2020.acl-main)

Challenge:	Entity linking is a fundamental task in Natural Language Processing (NLP), connecting mentions within unstructured contexts to their corresponding entities in a Knowledge Base (KB).
Approach:	They propose a dual-encoder framework that can efficiently match mentions to two-encoding frameworks by a global-view.
Outcome:	The proposed framework achieves state-of-the-art on several entity linking benchmarks.

Copied to clipboard

Fangzhao Wu, Ying Qiao, Jiun-Hung Chen, Chuhan Wu, Tao Qi, Jianxun Lian, Danyang Liu, Xing Xie, Jianfeng Gao, Winnie Wu, Ming Zhou

PRIMO: Progressive Induction for Multi-hop Open Rule Generation (2024.lrec-main)

Challenge:	Personalized news recommendation is an important technique for personalized news service.
Approach:	They propose to build a large-scale news recommendation dataset from Microsoft News . they demonstrate that news recommendation relies on the quality of news content understanding .
Outcome:	The proposed dataset contains 1 million users and more than 160k English news articles, each of which has rich textual content such as title, abstract and body.

Copied to clipboard

Jianyu Liu, Sheng Bi, Guilin Qi

Try to Substitute: An Unsupervised Chinese Word Sense Disambiguation Method Based on HowNet (2020.coling-main)

Challenge:	Existing approaches focus on single-hop open rule generation, ignoring scenarios involving multiple hops, leading to logical inconsistencies between premise and hypothesis atoms, as well as semantic duplication of generated rule atom.
Approach:	They propose a multi-stage open rule generation method called PRIMO that introduces ontology information during the rule generation stage to reduce ambiguity and improve rule accuracy.
Outcome:	The proposed method reduces the repetition rate of rule atoms while preserving the latent knowledge within the model.

Copied to clipboard

Bairu Hou, Fanchao Qi, Yuan Zang, Xurui Zhang, Zhiyuan Liu, Maosong Sun

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors (2025.acl-long)

Challenge:	Existing unsupervised methods for word sense disambiguation cannot work for HowNet-based WSD because of its uniqueness.
Approach:	They propose a method which exploits the masked language model task of pre-trained language models to conduct word sense disambiguation using a lexical knowledge base as the sense inventory.
Outcome:	The proposed method achieves significantly better performance than baseline methods.

Copied to clipboard

Yu Yan, Sheng Sun, Zenghao Duan, Teli Liu, Min Liu, Zhiyi Yin, LeiJingyu LeiJingyu, Qi Li

Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks (2023.findings-emnlp)

Challenge:	Recent studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks.
Approach:	They propose a framework that exploits AdVersArial meTAphoR to induce LLMs to calibrate harmful metaphors for jailbreaking.
Outcome:	The proposed framework can successfully jailbreak Large Language Models (LLMs) by leveraging the AdVersArial meTAphoR (AVATAR) framework achieves state-of-the-art attack success rate across multiple advanced LLMs.

Copied to clipboard

Kaiser Sun, Peng Qi, Yuhao Zhang, Lan Liu, William Wang, Zhiheng Huang

Question Answering

Challenge:	Pretrained sequence-to-sequence (seq2sequ) models have been widely used to solve extractive tasks, where parts of the input are extracted to form the desired output.
Approach:	They propose a simple fix to tokenization inconsistency that damages extractive nature of generative models by causing performance drop and hallucination.
Outcome:	The proposed model performs better in both in-domain and out-of-domain datasets with a notable average of +1.7 F1 gain when a BART model is trained on SQuAD and evaluated on 8 QA datasets.

Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents (2022.findings-acl)

Copied to clipboard

Yicheng Zou, Hongwei Liu, Tao Gui, Junzhe Wang, Qi Zhang, Meng Tang, Haixiang Li, Daniell Wang

Calibrating LLM-Based Evaluator (2024.lrec-main)

Challenge:	Existing text semantic matching models do not provide granularity for text comparison.
Approach:	They propose a simple yet effective training strategy for text semantic matching by disentangling keywords from intents.
Outcome:	The proposed approach achieves stable performance improvements against a wide range of models on three benchmarks.

Copied to clipboard

Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang

High-Quality Medical Dialogue Synthesis for Improving EMR Generation (2025.emnlp-industry)

Challenge:	Existing models for large language models lack the ability to calibrate their outputs towards human preference.
Approach:	They propose a multi-stage, gradient-free approach to calibrate an LLM-based evaluator toward human preference.
Outcome:	The proposed approach improves correlation with expert evaluation on multiple text quality evaluation datasets.

Copied to clipboard

Chengze Ge, Yu Xu, Qi Shao, Shengping Liu

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation (2023.emnlp-main)

Challenge:	Existing methods for generating EMRs from doctor-patient dialogues produce rigid and repetitive dialogues.
Approach:	They propose a framework that integrates Intent Graph Planning, Dual-Agent Simulation and Rule-Reward Quality Control to generate realistic doctor-patient dialogues.
Outcome:	The proposed framework significantly enhances realism, diversity and downstream EMR quality, reducing physician editing efforts.

Copied to clipboard

Daixuan Cheng, Shaohan Huang, Junyu Bi, Yuefeng Zhan, Jianfeng Liu, Yujing Wang, Hao Sun, Furu Wei, Weiwei Deng, Qi Zhang

POS-Constrained Parallel Decoding for Non-autoregressive Generation (2021.acl-long)

Challenge:	Large Language Models (LLMs) have impressive capabilities but need for task-specific prompt engineering can hinder their generalization.
Approach:	They propose a lightweight and versatile retriever that automatically retrieves prompts for a given zero-shot task input.
Outcome:	The proposed model is universally applicable across tasks and models . it mitigates hallucination problem in chatGPT, and it improves even the strongest LLMs.

Copied to clipboard

Kexin Yang, Wenqiang Lei, Dayiheng Liu, Weizhen Qi, Jiancheng Lv

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

Challenge:	Existing non-autoregressive generation systems face multimodality problem due to conditionally independent decoding.
Approach:	They propose to incorporate linguistic structure into NAG inference instead of teacher AG . they propose a method that provides a specific POS sequence to constrain the NAG model .
Outcome:	The proposed method improves NAG models on four text generation tasks to a greater extent compared to knowledge distillation.

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

Stepwise Reasoning Disruption Attack of LLMs (2025.acl-long)

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

Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu

QTSumm: Query-Focused Summarization over Tabular Data (2023.emnlp-main)

Challenge:	Existing attacks on LLM reasoning are constrained by specific settings or lack of imperceptibility, limiting their feasibility and generalizability.
Approach:	They propose a stepwise rEasoning error disruption attack that subtly injects errors into prior reasoning steps to mislead the model into producing incorrect subsequent reasoning and final answers.
Outcome:	The proposed attack is compatible with zero-shot and few-shot settings, maintains the natural reasoning flow, and ensures covert execution without modification of the instruction.

Copied to clipboard

Yilun Zhao, Zhenting Qi, Linyong Nan, Boyu Mi, Yixin Liu, Weijin Zou, Simeng Han, Ruizhe Chen, Xiangru Tang, Yumo Xu, Dragomir Radev, Arman Cohan

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

Challenge:	Existing text generation systems that can provide accurate table summaries can facilitate more efficient access to relevant data insights.
Approach:	They propose a query-focused task where text generation models have to perform human-like reasoning and analysis over the given table to generate a tailored table summary.
Outcome:	The proposed method improves existing baselines on table-to-text generation and large language models by concatenating generated facts to the model input.

Copied to clipboard

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

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)

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

Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou

ImgTrojan: Jailbreaking Vision-Language Models with ONE Image (2025.naacl-long)

Challenge:	Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains.
Approach:	They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains.
Outcome:	The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains.

Copied to clipboard

Xijia Tao, Shuai Zhong, Lei Li, Qi Liu, Lingpeng Kong

RethinkCWS: Is Chinese Word Segmentation a Solved Task? (2020.emnlp-main)

Challenge:	Existing studies on the safety of large language models (LLMs) with human values have focused on the integration of multi-modal user input into these models.
Approach:	They propose a method to bypass safety constraints of large language models by using poisoned images instead of original textual captions.
Outcome:	The proposed attack bypasses safety constraints of large language models (VLMs) by replacing the original textual captions with malicious jailbreak prompts.

Copied to clipboard

Jinlan Fu, Pengfei Liu, Qi Zhang, Xuanjing Huang

Syntactic Text Processing

Challenge:	Recent years have seen remarkable success in the use of deep neural networks on Chinese word segmentation (CWS) however, the performance of CWS systems has gradually reached a plateau with the rapid development of deep networks.
Approach:	They propose a fine-grained evaluation for existing Chinese word segmentation systems that allows us to diagnose the strengths and weaknesses of existing models.
Outcome:	The proposed model can diagnose strengths and weaknesses of existing models and alleviate negative transfer problem when doing multi-criteria learning.

FastBERT: a Self-distilling BERT with Adaptive Inference Time (2020.acl-main)

Copied to clipboard

Weijie Liu, Peng Zhou, Zhiruo Wang, Zhe Zhao, Haotang Deng, Qi Ju

AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)

Challenge:	Pre-trained language models like BERT have proven to be highly performant, but are often computationally expensive in many practical scenarios.
Approach:	They propose a speed-tunable FastBERT with adaptive inference time that can be flexibly adjusted under varying demands.
Outcome:	The proposed model achieves promising results in English and Chinese datasets.

Copied to clipboard

Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu

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

Challenge:	Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias.
Approach:	They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints.
Outcome:	The proposed benchmarks show that the models fail under causal, structural, or functional constraints.

Copied to clipboard

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

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

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

Copied to clipboard

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

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

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

Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations (2026.findings-acl)

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

Copied to clipboard

Haitong Luo, Fali Wang, Weiyao Zhang, Xianren Zhang, Zhiwei Zhang, Tianxiang Zhao, Minhua Lin, Jiahao Zhang, Hui Liu, Xianfeng Tang, Qi He, Suhang Wang, Xuying Meng, Yujun Zhang

Efficiently Selecting Response Generation Strategies for Synthetic Data Construction by Self-Aligned Perplexity (2025.findings-emnlp)

Challenge:	Large language models exhibit intrinsic limitations such as knowledge cutoff, single-threaded reasoning that hinders finer-grained branch and aggregation, and rigid collaboration mechanisms that struggle to coordinate specialized capabilities.
Approach:	They propose a taxonomy spanning Graph-Assisted Knowledge Augmentation, Graph Assisted Reasoning and Planning, and Graphed LLM Collaboration.
Outcome:	The proposed models show that graphs can augment and correct LLMs and support dynamic coordination among experts and agents in collaborative settings.

Copied to clipboard

Xuan Ren, Qi Chen, Lingqiao Liu

Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models (2025.findings-emnlp)

Challenge:	Using a small sample of data, we find that perplexity is suboptimal in characterizing “familiarity” .
Approach:	They propose a method that assesses a small subset of generated data to estimate suitability for a specific target LLM.
Outcome:	The proposed method assesses a small subset of generated data to estimate suitability for a specific target LLM.

Copied to clipboard

Xiaojun Wu, Junxi Liu, Huan-Yi Su, Zhouchi Lin, Yiyan Qi, Chengjin Xu, Jiajun Su, Jiajie Zhong, Fuwei Wang, Saizhuo Wang, Fengrui Hua, Jia Li, Jian Guo

Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning (2021.findings-acl)

Challenge:	Existing financial benchmarks suffer from limited language and task coverage, low-quality datasets, and inadequate adaptability for LLM evaluation.
Approach:	They propose a bilingual benchmark for financial LLMs that assesses models’ language understanding and generation capabilities.
Outcome:	The proposed bilingual benchmark assesses models’ language understanding and generation capabilities.

Copied to clipboard

Chenglei Si, Zhengyan Zhang, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun

LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)

Challenge:	Pretrained language models perform poorly under adversarial attacks due to the large search space.
Approach:	They propose a method to cover a much larger proportion of the attack search space by adding textual adversarial examples during training.
Outcome:	The proposed method covers a much larger proportion of the attack search space.

Copied to clipboard

Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun

HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Existing studies have focused on extending the context length of large language models (LLMs) due to their quadratic computational complexity and a lack of high-quality long training examples, most LLMs are trained with a limited window size.
Approach:	They propose a training-free framework that enables large language models to effectively process long texts using a divide-and-conquer strategy for comprehensive document understanding.
Outcome:	The proposed framework outperforms open-source and commercial long-context LLMs and is compatible with several models.

Copied to clipboard

Jie Ouyang, Tingyue Pan, Mingyue Cheng, Ruiran Yan, Yucong Luo, Jiaying Lin, Qi Liu

SoulChat: Improving LLMs’ Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversations (2023.findings-emnlp)

Challenge:	Current approaches to addressing knowledge outdating in LLMs struggle with retrieval and generation aspects when handling outdated information.
Approach:	They propose a benchmark to evaluate the impact of outdated information on RAG . they use token-level diff algorithms and LLM pipelines to create a large-scale QA dataset .
Outcome:	The proposed benchmark analyzes the impact of outdated information on RAG performance.

Copied to clipboard

Yirong Chen, Xiaofen Xing, Jingkai Lin, Huimin Zheng, Zhenyu Wang, Qi Liu, Xiangmin Xu

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors (2026.acl-long)

Challenge:	Large language models (LLMs) are used in psychological counseling to provide universal advice.
Approach:	They constructed a multi-turn empathetic conversation dataset with 2 million samples . they found that the model's empathy ability is enhanced when finetuning .
Outcome:	Experiments show that large language models can be finetuned to provide empathy . but, when applied to mental health or emotional support conversation, there are three main issues .

Copied to clipboard

Chenghao Yang, Yuning Zhang, Zhoufutu Wen, Tao Gong, Jiaheng Liu, Qi Chu, Nenghai Yu

PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models (2024.acl-long)

Challenge:	Existing metrics fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model’s autonomous preferences.
Approach:	They propose to use response pattern similarity and action graph similarity to isolate non-mandatory behaviors from mandatory behaviors.
Outcome:	Evaluating 18 models from 8 providers on -Bench and 2-Bench against Claude Sonnet 4.5, the authors find that within-family model pairs score 5.9 pp higher in response pattern similarity and action graph similarity .

Copied to clipboard

Haoran Li, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, Yuan Yao, Yangqiu Song

CiteEval: Principle-Driven Citation Evaluation for Source Attribution (2025.acl-long)

Challenge:	generative large language models (LLMs) exhibit surprising capability and integrate previous tasks into a unified text generation formulation.
Approach:	They propose a privacy evaluation benchmark to quantify the privacy leakage of language models.
Outcome:	The proposed benchmark compares PPLMs with different privacy implementations to find out how privacy leakage is handled.

Copied to clipboard

Yumo Xu, Peng Qi, Jifan Chen, Kunlun Liu, Rujun Han, Lan Liu, Bonan Min, Vittorio Castelli, Arshit Gupta, Zhiguo Wang

Challenge:	Current evaluation frameworks rely on NLI to assess binary or ternary support from cited sources, which is suboptimal for citation evaluation.
Approach:	They propose a citation evaluation framework based on fine-grained citation ratings within a broad context and construct a multi-domain benchmark with high-quality human annotations.
Outcome:	The proposed framework provides a high-quality human annotation benchmark and a suite of model-based metrics that exhibit strong correlation with human judgments.

Learn to Combine Linguistic and Symbolic Information for Table-based Fact Verification (2020.coling-main)

Copied to clipboard

Qi Shi, Yu Zhang, Qingyu Yin, Ting Liu

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

Challenge:	Existing methods for fact verification lack attention to combine linguistic and symbolic information.
Approach:	They propose a graph-based reasoning approach that learns to combine linguistic and symbolic information effectively.
Outcome:	The proposed method can combine linguistic and symbolic information effectively.

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

Can Language Models Understand Physical Concepts? (2023.emnlp-main)

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

Lei Li, Jingjing Xu, Qingxiu Dong, Ce Zheng, Xu Sun, Lingpeng Kong, Qi Liu

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

Challenge:	Existing language models do not understand basic physical concepts in the human world.
Approach:	They propose a method to transfer embodied knowledge from visual models to LMs . they use visual concepts and embodies concepts learned from interaction with the world .
Outcome:	The proposed method achieves comparable performance with scaling up parameters of LMs 134.

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

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)

Challenge:	Existing approaches to textual robustness evaluation focus on slightly modifying the input data, which maintains the original meaning and results in a different prediction.
Approach:	They propose a multilingual robustness evaluation toolkit for NLP that integrates universal text transformations, task-specific transformations and adversarial attack.
Outcome:	The toolkit includes universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analyses.

Copied to clipboard

SongYang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)

Challenge:	Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training.
Approach:	They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings.
Outcome:	The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods.

Copied to clipboard

Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang

Modeling Semantic Compositionality with Sememe Knowledge (P19-1)

Challenge:	Current document image parsing solutions rely on specialized models or generate content autoregressively.
Approach:	They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation.
Outcome:	The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency.

Copied to clipboard

Fanchao Qi, Junjie Huang, Chenghao Yang, Zhiyuan Liu, Xiao Chen, Qun Liu, Maosong Sun

Fisher-Driven Adaptive Locating for Knowledge Editing in Large Language Models (2026.acl-long)

Challenge:	Semantic compositionality (SC) is defined as the phenomenon that the meaning of a complex linguistic unit can be composed of the meanings of its constituents.
Approach:	They propose to incorporate sememes into SC models and employ them in learning multiword expressions.
Outcome:	The proposed models achieve significant performance boost compared to baseline methods without sememe knowledge.

Copied to clipboard

Chenghao Xu, Jiexi Yan, Guangtao Lyu, Qi Liu, Muli Yang, Cheng Deng

NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application (2021.findings-emnlp)

Challenge:	Existing methods for locating and editing static knowledge are costly and risk catastrophic forgetting or error.
Approach:	They propose a Fisher-driven adaptation-aware locating strategy that dynamically identifies which model components should be edited for a given knowledge update.
Outcome:	Experiments on standard benchmarks show that FiDAL improves editing effectiveness and knowledge preservation across multiple editing methods.

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Yang Yu, Tao Qi, Yongfeng Huang, Qi Liu

Once is Enough: A Light-Weight Cross-Attention for Fast Sentence Pair Modeling (2023.emnlp-main)

Challenge:	Existing language models are pre-trained and distilled on general corpus like Wikipedia, which has gaps with the news domain and may be suboptimal for news intelligence.
Approach:	They propose a method to distill existing language models on Wikipedia to enable efficient news intelligence.
Outcome:	The proposed model can be used to build and test a news intelligence application on Wikipedia and Wikipedia.

Copied to clipboard

Yuanhang Yang, Shiyi Qi, Chuanyi Liu, Qifan Wang, Cuiyun Gao, Zenglin Xu

Challenge:	Recent studies suggest that transformer-based models perform cross-attention over input pairs, leading to computational cost.
Approach:	They propose a lightweight cross-attention mechanism that performs query encoding only once while modeling the query-candidate interaction in parallel.
Outcome:	The proposed model speeds up sentence pairing by over 113x while achieving comparable performance as the more expensive models.

KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding (2025.acl-long)

Copied to clipboard

Shi Luohe, Zuchao Li, Lefei Zhang, Baoyuan Qi, Liu Guoming, Hai Zhao

Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification (D19-1)

Challenge:	Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI.
Approach:	They propose a paradigm called KV-Latent to reduce the KV cache footprint and improve inference speed by down-sampling the Key-Value vector dimensions into a latent space.
Outcome:	The proposed paradigm reduces the KV Cache footprint and improves inference speed with a small amount of extra training, less than 1% of pre-training takes.

Copied to clipboard

Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Tong Xu, Ming Liu

Sentiment Analysis

Challenge:	Existing methods for aspect-level sentiment classification are limited for dealing with overlapped features.
Approach:	They propose to use capsule network to construct vector-based feature representation and cluster features by an EM routing algorithm to model semantic relationship between aspect terms and context.
Outcome:	The proposed model achieves state-of-the-art on three datasets.

Reference-free Summarization Evaluation via Semantic Correlation and Compression Ratio (2022.naacl-main)

Copied to clipboard

Yizhu Liu, Qi Jia, Kenny Zhu

Summarization

Challenge:	Existing evaluation metrics for summarization use human annotations as reference.
Approach:	They propose a new automatic reference-free evaluation metric that compares semantic distribution between source document and summary by pretrained language models and considers summary compression ratio.
Outcome:	The proposed metric is more consistent with human evaluation in terms of coherence, consistency, relevance and fluency.

ModularMoE: Fast LLM Customization with Parameter-Sharing Mixture-of-Experts for Low-Resource Settings (2026.findings-acl)

Copied to clipboard

Jiaxing Liu, Qi Qi, Haifeng Sun, Dunjun Li, Zirui Zhuang, Bo He, Xiang Yang, Cong Liu, Jianxin Liao, Jingyu Wang