Papers by Xueqi Cheng

Transductive Learning for Unsupervised Text Style Transfer (2021.emnlp-main)

Challenge:	Existing methods to analyze black-box jailbreaks lack direct optimization signals to refine adversarial prompts.
Approach:	They propose a distribution-jailbreak attack method that selects effective jailbreak templates and iteratively optimizes adversarial suffixes by maximizing the KL divergence from the standard refusal distribution.
Outcome:	The proposed method achieves state-of-the-art Attack Success Rate (ASR) on all tested open-source models and delivers over 94% ASR on GPT-4.1.

Copied to clipboard

Fei Xiao, Liang Pang, Yanyan Lan, Yan Wang, Huawei Shen, Xueqi Cheng

QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory (2025.findings-emnlp)

Challenge:	Existing methods for style transfer are based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases.
Approach:	They propose a retrieval-based context-aware style representation that involves top-K relevant sentences in the target style in the transfer process.
Outcome:	The proposed method outperforms several strong baselines and is general and effective to the task of unsupervised style transfer.

Copied to clipboard

Yihang Wang, Xu Huang, Bowen Tian, Yueyang Su, Lei Yu, Huaming Liao, Yixing Fan, Jiafeng Guo, Xueqi Cheng

Linguistic Theories

Challenge:	Existing methods for compressing context by removing redundant tokens are inconsistent with the objective of retaining the most important tokens when conditioning on a given query.
Approach:	They propose a method that uses information bottleneck theory to compress context . they propose to remove redundant tokens using metrics such as self-information or perplexity .
Outcome:	The proposed method achieves a 25% increase in compression rate compared to the state-of-the-art .

Lost in Decomposition: Analyzing and Mitigating the Limitations of Long Context Methods via Context Dependency (2026.findings-acl)

Copied to clipboard

Jiayuan Guo, Yueyang Su, Yuyao Ge, Saiping Guan, Lei Yu, Jiafeng Guo, Xueqi Cheng

Challenge:	Existing workflow-based long context methods do not perform well on specific datasets . performance degradation is associated with the indiscriminate application of long context models .
Approach:	They propose a training-free adaptive routing strategy to improve long context large language models' robustness.
Outcome:	The proposed method can be generalized to all types of datasets, but performance degradation is a concern.

Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs (2021.acl-long)

Copied to clipboard

Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

Temporal Knowledge Graph Reasoning Based on N-tuple Modeling (2023.findings-emnlp)

Challenge:	Temporal Knowledge Graphs (TKGs) are used in many different areas of research.
Approach:	They propose to use a beam search policy to induce multiple clues from historical facts . they propose to adopt a graph convolution network based sequence method to deduce answers from clues .
Outcome:	The proposed model can predict future facts in two stages, Clue Searching and Temporal Reasoning.

Copied to clipboard

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Saiping Guan, Yutao Zeng, Jiafeng Guo, Xueqi Cheng

Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts (2025.acl-long)

Challenge:	Existing Temporal Knowledge Graphs (TKGs) only contain their core entities and form them as quadruples.
Approach:	They propose to describe a temporal fact more accurately as an n-tuple . they propose to use a neural network to learn evolutional representations of entities .
Outcome:	The proposed model oversimplifies and causes information loss on two datasets.

Copied to clipboard

Baolong Bi, Shenghua Liu, Lingrui Mei, Yiwei Wang, Junfeng Fang, Pengliang Ji, Xueqi Cheng

BSFA: Leveraging the Subspace Dichotomy to Accelerate Neural Network Training (2025.emnlp-main)

Challenge:	In-context knowledge editing (ICE) is currently the most effective method for knowledge editing, but it is constrained by the black-box modeling of LLMs and lacks interpretability.
Approach:	They propose a method to decode new knowledge by comparing logits with unedited knowledge to improve the accuracy of LLMs.
Outcome:	The proposed method improves the performance of LLaMA3-8B-instruct on MQuAKE by up to 219%.

Copied to clipboard

WenJie Zhou, Bohan Wang, Wei Chen, Xueqi Cheng

Green & Sustainable NLP

Challenge:	Recent studies highlight a fundamental dichotomy in deep learning optimization: parameter updates along the top eigendirections of the loss Hessian (Dom-space) capture most of the update magnitude, while updates in the orthogonal component (Bulk-space), have smaller magnitudes but drive most learning progress.
Approach:	They propose a plug-and-play framework that scales update components projected onto distinct subspaces and a block-wise strategy that applies this estimation on a per-parameter-block basis.
Outcome:	The proposed framework accelerates training by differentially scaling update components projected onto distinct subspaces, while enhancing stability by moderating updates in dominant subspace and boosting convergence speed by amplifying updates in bulk-space.

Gated Differentiable Working Memory for Long-Context Language Modeling (2026.acl-long)

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Yuyao Ge, Baolong Bi, Jiayu Yao, Jun Wan, Ziling Yin, Jiafeng Guo, Xueqi Cheng

SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs (2025.naacl-long)

Challenge:	Long contexts break transformers, attention scores dilute, model cannot adapt to novel patterns at inference time.
Approach:	They propose a framework that gates the memory consolidation process by estimating Contextual Utility . they propose GDWM to maintain a form of working memory with constant contexts .
Outcome:	The proposed framework achieves comparable or superior performance on sparse-information tasks with 4 fewer gradient steps compared to uniform baselines.

Copied to clipboard

Zhichao Shi, Shaoling Jing, Yi Cheng, Hao Zhang, Yuanzhuo Wang, Jie Zhang, Huawei Shen, Xueqi Cheng

Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception (2025.acl-long)

Challenge:	Large Language Models (LLMs) have been used to evaluate the safety of their users . however, evaluation questions in current benchmarks are too straightforward and difficult to update with practical relevance due to their lack of correlation with real-world events.
Approach:	They propose a question-generation framework to evaluate the safety of LLMs in the Chinese context.
Outcome:	The proposed framework reduces decline rate while maintaining similar attack success rate.

Copied to clipboard

Shiyu Ni, Keping Bi, Jiafeng Guo, Lulu Yu, Baolong Bi, Xueqi Cheng

Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework (2024.findings-emnlp)

Challenge:	Large language models (LLMs) exhibit impressive performance across diverse tasks but struggle to accurately gauge their knowledge boundaries.
Approach:	They propose Consistency-based Confidence Calibration (C3) which assesses confidence consistency through question reformulation to improve LLMs’ ability to recognize their knowledge gaps.
Outcome:	The proposed method improves the unknown perception rate by 5.6% on NQ and 4.9% on HotpotQA.

Copied to clipboard

Lu Chen, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng

Low-Resource NLP

Challenge:	Existing studies on retrieval-augmented generation (RAG) rarely address the issue of predictive uncertainty, i.e., how likely it is that a RAG model’s prediction is incorrect.
Approach:	They propose a framework that induces RAG models to alter latent factors and analyzes the effect on their answers.
Outcome:	The proposed framework identifies two critical factors affecting RAG models' confidence in their answers and analyzes the effect on their answers.

MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework (2025.emnlp-main)

Copied to clipboard

ZhaoDan Zhang, Jin Zhang, Hui Xu, Jiafeng Guo, Xueqi Cheng

LPNL: Scalable Link Prediction with Large Language Models (2024.findings-acl)

Challenge:	Existing stance detection methods treat the task as a classification problem, where models output a stance label without providing interpretable reasoning paths.
Approach:	They propose a framework that generates, evaluates, and integrates multiple reasoning paths to improve accuracy, robustness, and transparency in stance detection.
Outcome:	The proposed framework outperforms existing models on the SEM16, VAST, and PStance datasets and is highly interpretable and reliable.

Copied to clipboard

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Xueqi Cheng

The Mirage of Model Editing: Revisiting Evaluation in the Wild (2025.acl-long)

Challenge:	Existing studies on graph learning with large language models have focused on the link prediction task on large graphs.
Approach:	They propose a framework for scalable link prediction on large-scale heterogeneous graphs based on large language models.
Outcome:	The proposed framework outperforms baselines in link prediction tasks on large graphs.

Copied to clipboard

Wanli Yang, Fei Sun, Jiajun Tan, Xinyu Ma, Qi Cao, Dawei Yin, Huawei Shen, Xueqi Cheng

Question Answering

Challenge:	despite near-perfect results, effectiveness of model editing in real-world applications remains unclear.
Approach:	They propose QAEdit and WILD to better reflect real-world use of model editing . they propose a benchmark aligned with widely used question answering datasets and a task-agnostic evaluation framework .
Outcome:	The proposed QAEdit benchmark and WILD evaluation framework show that current models perform worse than previously reported.

MLaKE: Multilingual Knowledge Editing Benchmark for Large Language Models (2025.coling-main)

Copied to clipboard

Zihao Wei, Jingcheng Deng, Liang Pang, Hanxing Ding, Huawei Shen, Xueqi Cheng

Efficient Sequence Learning with Group Recurrent Networks (N18-1)

Challenge:	Existing studies on knowledge editing focus on monolingual scenarios, neglecting the complexities presented by multilingual contexts and multi-hop reasoning.
Approach:	They propose a benchmark to evaluate the adaptability of multilingual knowledge editing methods.
Outcome:	The proposed benchmark evaluates the adaptability of multilingual knowledge editing methods across five languages.

Copied to clipboard

Fei Gao, Lijun Wu, Li Zhao, Tao Qin, Xueqi Cheng, Tie-Yan Liu

Green & Sustainable NLP

Challenge:	Recurrent neural networks have achieved state-of-the-art results in many artificial intelligence tasks, such as language modeling, neural machine translation and speech recognition.
Approach:	They propose an efficient architecture to improve the efficiency of such RNN model training by adopting the group strategy for recurrent layers while exploiting the representation rearrangement strategy between layers as well as time steps.
Outcome:	The proposed architecture achieves comparable or better accuracy compared with baselines, with a much smaller number of parameters and at a lower computational cost.

Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems (2026.findings-acl)

Copied to clipboard

Zixu Wang, Bingbing Xu, Yige Yuan, Huawei Shen, Xueqi Cheng

Challenge:	Existing approaches generate workflows either at task level or query level, but their relative costs and benefits remain unclear.
Approach:	They propose a query-level workflow generation framework that generates tasks at task level and query level.
Outcome:	The proposed framework reduces token usage by up to 83% compared to existing approaches . it maintains competitive performance with an average degradation of just 0.61% compared with existing approaches across multiple datasets .

ALiiCE: Evaluating Positional Fine-grained Citation Generation (2025.naacl-long)

Copied to clipboard

Yilong Xu, Jinhua Gao, Xiaoming Yu, Baolong Bi, Huawei Shen, Xueqi Cheng

Challenge:	Existing research on citation generation is limited to sentence-level statements . positional fine-grained citations can appear anywhere within sentences .
Approach:	They propose a framework that allows LLMs to generate citations from sentences . they use dependency tree-based methods to parse sentence-level claims into atomic claims .
Outcome:	The proposed framework evaluates citation quality using three metrics including positional fine-grained citation recall, precision, and coefficient of variation of citation positions.

Distilling Large Embeddings via Hyperspherical Householder Quantization (2026.acl-long)

Copied to clipboard

Yihang Wang, Bin Wu, Yueyang Su, Tianfu Zhang, Yiqi Du, Lei Yu, Jiafeng Guo, Xueqi Cheng

RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning (2026.findings-acl)

Challenge:	Existing methods for quantizing large embeddings rely on Euclidean quantization, which is poorly aligned with the angular geometry induced by contrastive embeddment training.
Approach:	They propose a geometry-aware distillation method that compresses large embeddings into short discrete representations via iterative Householder transformations on the unit hypersphere.
Outcome:	The proposed method reduces decoding cost and maintains strong semantic retrieval accuracy.

Copied to clipboard

Yucan Guo, Miao Su, Saiping Guan, Zihao Sun, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

NeuInfer: Knowledge Inference on N-ary Facts (2020.acl-main)

Challenge:	Existing graph-based or hybrid systems lack the ability to integrate supplementary evidence as reasoning unfolds.
Approach:	They propose a framework that integrates non-parametric knowledge into Large Language Models . they use a RL-based framework to optimize the entire generation process via RL .
Outcome:	The proposed framework outperforms existing RAG frameworks in five question answering benchmarks.

Copied to clipboard

Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems (2025.findings-acl)

Challenge:	Existing studies on knowledge inference on binary facts have focused on finding out connotative valid facts.
Approach:	They propose a neural network model, NeuInfer, for knowledge inference on n-ary facts.
Outcome:	The proposed model can cope with the task to infer an unknown element in a whole fact, while ignoring the binary facts.

Copied to clipboard

Hongru Song, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Jianming Lv, Maarten de Rijke, Xueqi Cheng

Compete to Complete: Co-opetition Adversarial Learning for Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing studies have focused on corpus poisoning, but there are no studies on adversarial attacks on RAG systems.
Approach:	They propose a novel imperceptible retrieve-to-generate attack against RAG systems . they propose regenerative reinforcement learning framework that tracks interactions between attacker and target RAG .
Outcome:	The proposed framework outperforms existing attacks on factual and non-factual RAG systems with small imperceptible text perturbations.

Copied to clipboard

Xin Liu, Yu-An Liu, Ruqing Zhang, Yixing Fan, Lixin Su, Jiafeng Guo, Xueqi Cheng

Iterative Structured Pruning for Large Language Models with Multi-Domain Calibration (2026.eacl-industry)

Challenge:	Existing approaches to reduce hallucination in large language models lack a robust mechanism for generating a generative model.
Approach:	They propose a framework that formulates retriever–generator training in RAG as a minimax game.
Outcome:	The proposed framework improves retrieval-augmented generation performance on seven benchmark datasets.

Copied to clipboard

Guangxin Wu, Hao Zhang, Zhang Zhibin, Jiafeng Guo, Xueqi Cheng

Think Before You Speak: Cultivating Communication Skills of Large Language Models via Inner Monologue (2024.findings-naacl)

Challenge:	Existing models with unstructured pruning often yield irregular sparsity patterns that necessitate specialized hardware or software support.
Approach:	They propose a structured pruning framework that eliminates entire architectural components and maintains compatibility with standard hardware accelerators.
Outcome:	The proposed model pruning framework achieves significant compression with minimal performance degradation on multiple models across diverse downstream tasks.

Copied to clipboard

Junkai Zhou, Liang Pang, Huawei Shen, Xueqi Cheng

From Relevance to Utility: Evidence Retrieval with Feedback for Fact Verification (2023.findings-emnlp)

Challenge:	emergence of large language models (LLMs) improves capabilities of dialogue systems . but they lack communication skills, which make them more like information seeking tools .
Approach:	They propose to empower LLMs with communication skills through inner monologues . they use a benchmark to evaluate the dialogue generation ability of the model .
Outcome:	The proposed model outperforms the baselines in the evaluation of communication skills.

Copied to clipboard

Hengran Zhang, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yixing Fan, Xueqi Cheng

Exploiting Contextual Information via Dynamic Memory Network for Event Detection (D18-1)

Challenge:	Existing evidence retrieval models are based on probability ranking principle . existing models do not align with retrieval-enhanced verification frameworks .
Approach:	They propose a feedback-based evidence retriever that optimizes the evidence retrieval process by incorporating feedback from the claim verifier.
Outcome:	Empirical studies show that the proposed method is superior to baseline methods.

Copied to clipboard

Shaobo Liu, Rui Cheng, Xiaoming Yu, Xueqi Cheng

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)

Challenge:	Existing methods for event detection only process context once . a multi-hop mechanism to capture contextual information improves performance .
Approach:	They propose to use dynamic memory network to capture contextual information . they propose to model event triggers by identifying word or phrase which most represents it .
Outcome:	The proposed model achieves best F1 score compared to the state-of-the-art models.

Copied to clipboard

Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

T-MAD: Target-driven Multimodal Alignment for Stance Detection (2025.emnlp-main)

Challenge:	Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps.
Approach:	They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts.
Outcome:	The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models.

Copied to clipboard

ZhaoDan Zhang, Jin Zhang, Xueqi Cheng, Hui Xu

Sentiment Analysis

Challenge:	Existing methods for Multimodal Stance Detection struggle with generalizing to unseen targets and handling modality inconsistencies.
Approach:	They propose a multimodal stability detection model which captures target-specific relationships and balances modality contributions by iterative reasoning.
Outcome:	Experiments on the MMSD and MultiClimate datasets show that the proposed model outperforms state-of-the-art models with optimal results achieved using RoBERTa, ViT, and an iterative depth of 5.

Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspective (2025.emnlp-main)

Copied to clipboard

Da Li, Keping Bi, Jiafeng Guo, Xueqi Cheng

Structured Data in NLP

Challenge:	Empirical results show that a hybrid retrieval approach to table retrieval outperforms state-of-the-art benchmarks.
Approach:	They propose a table-tailored HYbrid matching rEtriever which addresses table matching needs from a field-aware hybrid perspective.
Outcome:	Empirical results show that the proposed rEtriever outperforms state-of-the-art retrieval methods.

Detoxification for LLM: From Dataset Itself (2026.acl-long)

Copied to clipboard

Wei Shao, Yihang Wang, Gao yu Zhu, Ziqiang Cheng, Lei Yu, Jiafeng Guo, Xueqi Cheng

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective (2025.findings-acl)

Challenge:	Existing methods for large language models focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself.
Approach:	They propose to localize and rewrite toxic spans in raw corpora with SoCD, which guides an LLM to localized and preserving semantics while preserving toxicity.
Outcome:	The proposed method reduces TP from 0.42 to 0.18 and Expected Maximum Toxicity (EMT) from 0.43 to 0.20 on three LLMs.

Copied to clipboard

Yuchen Wen, Keping Bi, Wei Chen, Jiafeng Guo, Xueqi Cheng

BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval (2023.acl-long)

Challenge:	Existing studies have shown that large language models (LLMs) can elicit implicit biases that hurt certain demographics without explicit harmful words.
Approach:	They propose three attack approaches to elicit agreements to biased viewpoints from LLMs from a psychometric perspective and built two benchmarks to compare them.
Outcome:	The proposed methods elicit agreements to biased viewpoints more effectively than baselines.

Copied to clipboard

Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng

LINKAGE: Listwise Ranking among Varied-Quality References for Non-Factoid QA Evaluation via LLMs (2024.findings-emnlp)

Challenge:	Dense retrieval has shown promise in the first-stage retrieval process when trained on in-domain labeled datasets.
Approach:	They propose a method to capture matching signal to improve generalization of dense retrieval by capturing matching signal between two texts.
Outcome:	The proposed method can be combined with different training methods to improve generalization ability without additional inference overhead and target domain data.

Copied to clipboard

Sihui Yang, Keping Bi, Wanqing Cui, Jiafeng Guo, Xueqi Cheng

Question Answering

Challenge:	Non-factoid (NF) question answering is challenging to evaluate due to diverse potential answers and no objective criterion.
Approach:	They propose a listwise NFQA evaluation approach that uses Large Language Models to rank candidate answers in a descending list of reference answers sorted by descending quality.
Outcome:	The proposed method has higher correlations with human annotations than standard methods.

Towards Robust Universal Information Extraction: Dataset, Evaluation, and Solution (2025.acl-long)

Copied to clipboard

Jizhao Zhu, Akang Shi, Zixuan Li, Long Bai, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction (2024.acl-long)

Challenge:	Existing robust benchmark datasets generate only a limited range of perturbations for a single Information Extraction (UIE) task, which fails to evaluate the robustness of UIE models effectively.
Approach:	They propose a new benchmark dataset that utilizes Large Language Models to generate more diverse and realistic perturbations across different IE tasks.
Outcome:	The proposed model performs better with only 15% of the data and is more robust with other models.

Copied to clipboard

Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Lixiang Lixiang, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Multimodality

Challenge:	None. None.. None!
Approach:	None. None.. None!
Outcome:	None. None. No. :

Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models (2025.emnlp-main)

Copied to clipboard

Yilong Xu, Jinhua Gao, Xiaoming Yu, Yuanhai Xue, Baolong Bi, Huawei Shen, Xueqi Cheng

Tailored Sequence to Sequence Models to Different Conversation Scenarios (P18-1)

Challenge:	Utility-based retrieval has emerged as a promising topic for downstream tasks . however, capturing passage utility accurately remains unexplored due to insufficient understanding .
Approach:	They propose a framework for training utility-based retrievers in Retrieval-Augmented Language Models . it incorporates multi-task generalization and inter-passage interaction to improve performance .
Outcome:	The proposed framework improves performance on ten datasets across different tasks.

Copied to clipboard

Hainan Zhang, Yanyan Lan, Jiafeng Guo, Jun Xu, Xueqi Cheng

ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models (2025.acl-long)

Challenge:	Sequence to sequence (Seq2Sequeq) models fail to meet the diverse requirements for different conversation scenarios, such as customer service and chatbot.
Approach:	They propose two optimized criteria for Sequence to sequence (Seq2Sequeq) to meet different conversation scenarios, i.e., maximum generated likelihood for specific-requirement scenario, and conditional value-at-risk for diverse-requrement scenarios.
Outcome:	The proposed models satisfies diverse requirements for different conversation scenarios and yields better performances than existing models.

Copied to clipboard

Hanxing Ding, Shuchang Tao, Liang Pang, Zihao Wei, Jinyang Gao, Bolin Ding, Huawei Shen, Xueqi Cheng

a1: Steep Test-time Scaling Law via Environment Augmented Generation (2026.findings-acl)

Challenge:	Existing approaches to tool learning rely on hand-crafted prompts and natural language reasoning, making multi-step planning difficult and lacking precise error diagnosis and reflection mechanisms.
Approach:	They propose a framework that reformulates tool learning as a code generation task.
Outcome:	The proposed framework achieves superior performance in task completion accuracy and execution reliability compared to existing approaches.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Yuyao Ge, Jun Wan, Yurong Wu, Xueqi Cheng

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation (2024.acl-long)

Challenge:	Large Language Models (LLMs) have made remarkable advances in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during complex multi-step tasks.
Approach:	They propose a framework that enhances LLM reasoning through real-time environmental feedback validating each reasoning step, dynamic branch exploration for investigating alternative solution paths when faced with errors, and experience-based learning from successful reasoning trajectories.
Outcome:	The proposed model outperforms comparable models by 24.4 percentage points across benchmarks while outperforming comparable models.

Copied to clipboard

Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou

Knowledge-Enhanced Self-Supervised Prototypical Network for Few-Shot Event Detection (2022.findings-emnlp)

Challenge:	Existing studies show that LLMs face challenges in effectively using retrieved information . authors propose a method that considers LLM as "Information Refiner"
Approach:	They propose a method that considers LLMs as "Information Refiners" they propose INFO-RAG, which is low-cost and general across various tasks .
Outcome:	The proposed method improves performance of LLaMA2 by 9.39% relative points . it is low-cost and general across various tasks, and is robust and in-context learning is possible .

Copied to clipboard

Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

Event Detection with Multi-Order Graph Convolution and Aggregated Attention (D19-1)

Challenge:	Existing methods for few-shot event detection are inaccurate and lack a prototype representation module.
Approach:	They propose a Knowledge-Enhanced self-supervised prototypical network for few-shot event detection . it adopts hybrid rules which align event types to FrameNet and introduces knowledge to obtain more instances .
Outcome:	The proposed network improves few-shot event detection performance on three benchmark datasets.

Copied to clipboard

Haoran Yan, Xiaolong Jin, Xiangbin Meng, Jiafeng Guo, Xueqi Cheng

Syntactic Text Processing

Challenge:	Existing methods for event detection use first-order syntactic relations to identify trigger words.
Approach:	They propose a dependency tree-based method to model and aggregate multi-order syntactic representations in sentences.
Outcome:	The proposed method outperforms existing methods on a benchmark dataset . it uses a dependency tree based graph convolution network with aggregative attention .

KnowCoder-X: Boosting Multilingual Information Extraction via Code (2025.findings-acl)

Copied to clipboard

Yuxin Zuo, Wenxuan Jiang, Wenxuan Liu, Zixuan Li, Long Bai, Hanbin Wang, Yutao Zeng, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Multilinguality

Challenge:	Empirical evidence indicates that Large Language Models exhibit spontaneous cross-lingual alignment in Information Extraction (IE) however, a significant imbalance across languages persists, highlighting an underlying deficiency.
Approach:	They propose a code LLM with advanced cross-lingual and multilingual capabilities for universal IE that standardizes the representation of multilingual schemas using Python classes and conducts IE alignment instruction tuning on translated instance prediction task.
Outcome:	The proposed model surpasses ChatGPT and SoTA by 30.17% without training in 29 unseen languages and significantly improves cross-lingual IE transferability.

Qsnail: A Questionnaire Dataset for Sequential Question Generation (2024.lrec-main)

Copied to clipboard

Yan Lei, Liang Pang, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng

Selective Temporal Knowledge Graph Reasoning (2024.lrec-main)

Challenge:	Questionnaires are a professional research methodology used for qualitative and quantitative analysis of human opinions, preferences, and behaviors.
Approach:	They propose a questionnaire-based dataset that consists of 13,168 human-written questionnaires.
Outcome:	The proposed dataset contains 13,168 human-written questionnaires gathered from online platforms.

Copied to clipboard

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, Xueqi Cheng

ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation (P19-1)

Challenge:	Existing models cannot abstain from uncertain predictions, which will bring risks in real-world applications.
Approach:	They propose to abstain from uncertain future facts by using a confidence estimator . they take both the certainty of the current prediction and the accuracy of historical predictions into account .
Outcome:	The proposed abstention mechanism helps existing models make selective predictions instead of indiscriminate ones.

Copied to clipboard

Hainan Zhang, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

SLANG: New Concept Comprehension of Large Language Models (2024.emnlp-main)

Challenge:	Existing hierarchical recurrent encoder-decoder models treat all contexts indiscriminately, which may hurt the following response generation process.
Approach:	They propose a hierarchical recurrent encoder-decoder model that treats all contexts indiscriminately and uses a word level LSTM encoder to obtain the initial representation of each context.
Outcome:	The proposed model outperforms baseline models on Chinese customer services and English Ubuntu dialogue datasets in terms of both metric-based and human evaluations.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Xueqi Cheng

Prompt Tuning with Contradictory Intentions for Sarcasm Recognition (2023.eacl-main)

Challenge:	Dynamic nature of language limits the adaptability of Large Language Models (LLMs) Traditionally, LLMs are trained on static data, which limits their adaptability .
Approach:	They propose a benchmark to integrate novel data and assess LLMs’ ability to comprehend emerging concepts, alongside a causal inference-based approach to enhance LLM comprehension of new phrases and their colloquial context.
Outcome:	The proposed model outperforms baseline models in terms of precision and relevance in the comprehension of Internet slang and memes.

Copied to clipboard

Yiyi Liu, Ruqing Zhang, Yixing Fan, Jiafeng Guo, Xueqi Cheng

Sentiment Analysis

Challenge:	Recent advances have shown that Pre-trained Language Models (PLMs) can achieve promising performance in many downstream Natural Language Processing (NLP) tasks.
Approach:	They propose to incorporate prior knowledge about contradictory intentions into prompt tuning for sarcasm recognition by mimicking the actual intention by verbalizer engineering.
Outcome:	The proposed model mimics the actual intention by prompt construction and indicates whether the actual intent contradicts the literal content by verbalizer engineering.

Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings (2020.coling-main)

Copied to clipboard

Yutao Zeng, Xiaolong Jin, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Few-shot Link Prediction on Hyper-relational Facts (2024.lrec-main)

Challenge:	Existing methods for event coreference resolution do not identify paraphrase relations between events.
Approach:	They propose a new event-specific paraphrase and argument-aware semantic Embedding model for event coreference resolution based on event-related paraphrases and argument embeddings . EPASE recognizes deep paraphrase relations in an event- specific context of sentences and can cover event paraphrase of more situations .
Outcome:	Experiments on within- and cross-document event coreference show it is superior compared to existing methods.

Copied to clipboard

Jiyao Wei, Saiping Guan, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs (2026.findings-acl)

Challenge:	Existing methods to predict missing elements in hyper-relational facts require high-quality data.
Approach:	They propose a task to predict a missing entity in a hyper-relational fact with limited support instances.
Outcome:	The proposed model outperforms existing models on three datasets.

Copied to clipboard

Hengran Zhang, Keping Bi, Jiafeng Guo, Xueqi Cheng

Natural Language Interfaces

Challenge:	Relevance emphasizes the aboutness of a result to a query, while utility refers to the result’s usefulness or value to an information seeker.
Approach:	They propose an Iterative utiliTy judgmEnt fraMework to promote each step in Retrieval-Augmented Generation (RAG) they propose to use relevance ranking, utility judgments, and answer generation to prioritize high-utility results over low-utilitity results.
Outcome:	The proposed framework improves relevance, ranking, and answer generation on retrieval (TREC DL, WebAP), utility judgment task (GTI-NQ), and factoid question-answering (NQ) datasets.

Can Graph Descriptive Order Affect Solving Graph Problems with LLMs? (2025.acl-long)

Copied to clipboard

Yuyao Ge, Shenghua Liu, Baolong Bi, Yiwei Wang, Lingrui Mei, Wenjie Feng, Lizhe Chen, Xueqi Cheng

Nested Event Extraction upon Pivot Element Recognition (2024.lrec-main)

Challenge:	Large language models (LLMs) have achieved significant success in reasoning tasks, including mathematical reasoning and logical deduction.
Approach:	They conduct the first comprehensive analysis of how the order of graph descriptions impacts LLM performance.
Outcome:	The results show that graph descriptions significantly improve LLMs’ comprehension of graph structures, and the robustness of LLM models to graph description order varies across different tasks.

Copied to clipboard

Weicheng Ren, Zixuan Li, Xiaolong Jin, Long Bai, Miao Su, Yantao Liu, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Text2Sql: Pure Fine-Tuning and Pure Knowledge Distillation (2025.naacl-industry)

Challenge:	Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively.
Approach:	They propose a new model that extracts nested events mainly based on recognizing PEs.
Outcome:	The proposed model can extract nested events based on recognizing PEs . it incorporates information from both event types and argument roles to improve performance .

Copied to clipboard

Gao yu Zhu, Wei Shao, Xichou Zhu, Lei Yu, Jiafeng Guo, Xueqi Cheng

A Generative Framework for Personalized Sticker Retrieval (2025.findings-emnlp)

Challenge:	Text2Sql is a task that translates natural language questions and database schemas into SQL queries.
Approach:	They employ pure fine-tuning strategy to reduce redundancy by using only 53% of the baseline prompt length to fine- tune the model.
Outcome:	The model outperforms the baseline model by 8.2% and 8.6% in Test-suite accuracy (TS) and exact-set-match accuracy (EM) under the most refined Spider dev set of prompts, the model achieves 73.5% and 75.4%, respectively, approaching state-of-the-art (SOTA) levels.

Copied to clipboard

Changjiang Zhou, Ruqing Zhang, Jiafeng Guo, Yu-An Liu, Fan Zhang, Ganyuan Luo, Xueqi Cheng

Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases (2022.coling-1)

Challenge:	Existing relevance-based generative retrieval methods lack personalization, leading to a mismatch between diverse user expectations and the retrieved results.
Approach:	They propose a representation learning model that learns discriminative user representations to encode user-specific sticker preferences.
Outcome:	The proposed framework outperforms state-of-the-art methods in generating relevant stickers for queries.

Copied to clipboard

Kun Zhang, Yunqi Qiu, Yuanzhuo Wang, Long Bai, Wei Li, Xuhui Jiang, Huawei Shen, Xueqi Cheng

Jailbreak LLMs through Internal Stance Manipulation (2025.emnlp-main)

Challenge:	Existing methods train one encoder-decoder-based model to fit all questions . however, such a one-size-fits-all strategy may not perform well for complex questions involving multiple KB relations or functional constraints.
Approach:	They propose a meta-learning framework for complex question generation over knowledge bases . they propose he meta-trained generator can acquire universal meta-knowledge .
Outcome:	The proposed framework can acquire universal and transferable meta-knowledge and quickly adapt to long-tailed samples under different dimensions.

Copied to clipboard

Shuangjie Fu, Du Su, Beining Huang, Fei Sun, Jingang Wang, Wei Chen, Huawei Shen, Xueqi Cheng

Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration (2024.emnlp-main)

Challenge:	Existing approaches to exploit LLMs' inherent safety mechanism, including GCG and AutoDAN, are ineffective for certain malicious requests.
Approach:	They propose a method that generates jailbreak prompts to suppress a refusal stance and induce affirmative responses by modifying adversarial prompts.
Outcome:	The proposed method outperforms the best baseline approach in Llama-2-7b-chat and achieves a 92.2% success rate across all models.

Copied to clipboard

Kangxi Wu, Liang Pang, Huawei Shen, Xueqi Cheng

“Not Aligned” is Not “Malicious”: Being Careful about Hallucinations of Large Language Models’ Jailbreak (2025.coling-main)

Challenge:	Large language models (LLMs) are difficult to interpret due to their black-box nature and randomness.
Approach:	They propose a new method which enhances influence functions by addressing fitting errors by eliminating knowledge bias present in the base model before fine-tuning.
Outcome:	The proposed method outperforms existing methods and achieves an average AUC of 91.64%.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Jiayi Mao, Xueqi Cheng

Semantic Structure Enhanced Event Causality Identification (2023.acl-long)

Challenge:	“Jailbreak” is a major safety concern of Large Language Models (LLMs).
Approach:	They propose a benchmarking framework to evaluate "jailbreak" outputs . they propose specialized validation framework to ensure outputs are useful malicious instructions .
Outcome:	The proposed framework enhances existing benchmarks to ensure outputs are useful . it also aims to evaluate the true potential of jailbroken outputs to cause harm to human society.

Copied to clipboard

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Challenge:	Existing methods for Event Causality Identification (ECI) capture implicit associations between events, which are difficult because they lack the ability to understand the associations between two events.
Approach:	They propose a model that captures the implicit associations between two events and integrates the event-centric structure information into a GNN-based event aggregator.
Outcome:	The proposed model improves on three widely used datasets showing that it integrates event-centric and event-associated semantic elements and captures event associations.

Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation (2025.coling-main)

Copied to clipboard

Jia Gu, Liang Pang, Huawei Shen, Xueqi Cheng

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction (2025.emnlp-main)

Challenge:	LLMs are used to emulate sequential decision-making processes of humans . however, their ability to perform probabilistic sampling is limited .
Approach:	They propose to use large language models (LLMs) as agents to emulate the sequential decision-making processes of humans represented as Markov decision-makers (MDPs).
Outcome:	The proposed models can understand probabilities, but struggle with sampling precision . integrating coding tools can improve sampling precision, but this level of sampling precision still makes it difficult to simulate human behavior as agents.

Copied to clipboard

Wenxuan Liu, Zixuan Li, Long Bai, Yuxin Zuo, Daozhu Xu, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Speculative Safety-Aware Decoding (2025.emnlp-main)

Challenge:	Event Extraction (EE) is a long-standing target, but lacks an efficient and effective annotation framework to construct the corresponding datasets.
Approach:	They propose an LLM-based collaborative annotation framework that refines annotations of triggers from distant supervision and carries out argument annotation.
Outcome:	The proposed framework outperforms state-of-the-art methods on the largest EE dataset to date . it achieves the F1 scores of 90% and 85.3% on the human-annotated test set .

Copied to clipboard

Xuekang Wang, Shengyu Zhu, Xueqi Cheng

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

Challenge:	Speculative Safety-Aware Decoding (SSD) equips large language models with desired safety property while accelerating inference.
Approach:	They propose a lightweight decoding-time approach that equips large models with the desired safety property while accelerating inference.
Outcome:	Experimental results show that a small language model has the desired safety property while accelerating inference.

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.

Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical Reasoning (2026.acl-long)

Copied to clipboard

Zhaodan Zhang, Jin Zhang, Jiafeng Guo, Xueqi Cheng

Linguistics & Cognitive NLP

Challenge:	Recent advances in large language models (LLMs) have revolutionized stance detection, enabling complex reasoning strategies such as chain-of-thought prompting.
Approach:	They propose Cognitive-Driven Stance Detection (CDSD) that integrates fast intuitive judgment and analytical reasoning enhanced by three key modules: attention-based cognitive alignment to compare system focus, uncertainty-aware belief update using Bayesian inference, and self-doubt-triggered counterfactual reasoning for re-evaluation under low consistency or high uncertainty.
Outcome:	The proposed method outperforms state-of-the-art methods on SEM16, P-Stance, and VAST.

Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? (2024.acl-long)

Copied to clipboard

Hexiang Tan, Fei Sun, Wanli Yang, Yuanzhuo Wang, Qi Cao, Xueqi Cheng

G2S: A General-to-Specific Learning Framework for Temporal Knowledge Graph Forecasting with Large Language Models (2025.findings-acl)

Challenge:	Recent advances in augmenting Large Language Models (LLMs) with auxiliary information have significantly revolutionized their efficacy in knowledge-intensive tasks.
Approach:	They propose a systematic framework to identify whether LLMs’ responses are attributed to either generated or retrieved contexts.
Outcome:	The proposed framework identifies whether LLMs’ responses are attributed to either generated or retrieved contexts.

Copied to clipboard

Long Bai, Zixuan Li, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng, Tat-Seng Chua

Stop Hardening Everything: A Training-Free Neuron-Level Defense for Neural Ranking Models (2026.acl-long)

Challenge:	Recent studies have introduced Large Language Models (LLMs) for this task to enhance the models’ generalization abilities.
Approach:	They propose a General-to-Specific learning framework that disentangles the learning processes of two kinds of knowledge in a temporal temporal structure.
Outcome:	The proposed framework disentangles the learning processes of the above two kinds of knowledge and improves their generalization abilities.

Copied to clipboard

Yu-An Liu, Ruqing Zhang, Hongru Song, Jiafeng Guo, Yixing Fan, Xueqi Cheng

Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention (P18-2)

Challenge:	Existing defenses for neural ranking models are data-centric and require retraining and adversarial data generation.
Approach:	They propose a model-centric defense that addresses vulnerability at its architectural source without costly retraining or adversarial data generation.
Outcome:	The proposed approach outperforms state-of-the-art models on MS MARCO and TREC 19 while maintaining strong performance on clean data.

Copied to clipboard

Yue Zhao, Xiaolong Jin, Yuanzhuo Wang, Xueqi Cheng

Representation Learning

Challenge:	Existing methods for event detection use sentence-level contextual information.
Approach:	They propose a document embedding enhanced bi-RNN model to detect events in sentences . they use hierarchical and supervised attention based RNN to learn document embeds .
Outcome:	The proposed model compares with state-of-the-art models on a ACE-2005 dataset.

Learning to Control the Specificity in Neural Response Generation (P18-1)

Copied to clipboard

Ruqing Zhang, Jiafeng Guo, Yixing Fan, Yanyan Lan, Jun Xu, Xueqi Cheng

Text Generation

Challenge:	Existing generative conversational models tend to favor general and trivial responses which appear frequently.
Approach:	They propose a controlled response generation mechanism to handle different utterance-response relationships in terms of specificity.
Outcome:	The proposed model outperforms state-of-the-art models under automatic and human evaluations.

The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse (2024.findings-acl)

Copied to clipboard

Wanli Yang, Fei Sun, Xinyu Ma, Xun Liu, Dawei Yin, Xueqi Cheng

LLMDet: A Third Party Large Language Models Generated Text Detection Tool (2023.findings-emnlp)

Challenge:	Even a single edit can trigger model collapse, manifesting as significant performance degradation in various benchmark tasks.
Approach:	They propose to use perplexity as a surrogate metric to determine whether an edited model's performance is affected by a single edit.
Outcome:	The proposed method shows that even a single edit can cause model collapse, manifesting as significant performance degradation in various benchmark tasks.

Copied to clipboard

Kangxi Wu, Liang Pang, Huawei Shen, Xueqi Cheng, Tat-Seng Chua

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Challenge:	Existing detection tools rely on access to LLMs and can only distinguish between machine-generated and human-authored text.
Approach:	They propose a model-specific, secure, efficient, and extendable detection tool that can source text from specific LLMs.
Outcome:	The proposed tool can source text from specific LLMs, such as GPT-2, OPT, LLaMA, and others.

Copied to clipboard

Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Integrating Deep Event-Level and Script-Level Information for Script Event Prediction (2021.emnlp-main)

Challenge:	Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach:	They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome:	Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.

Copied to clipboard

Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, Xueqi Cheng

Class-Incremental Few-Shot Event Detection (2024.lrec-main)

Challenge:	Existing studies only consider a single event sequence corresponding to one common protagonist.
Approach:	They propose a Transformer-based model which integrates deep event-level and script-level information for script event prediction.
Outcome:	The proposed model is superior to existing models on the New York Times corpus . it utilizes rich information in the text to obtain more comprehensive representations .

Copied to clipboard

Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

Large Language Model-Based Event Relation Extraction with Rationales (2025.coling-main)

Challenge:	Existing methods to deal with new class of events with only a few labeled instances are challenging . old knowledge forgetting and new class overfitting are two problems in this task.
Approach:	They propose a task called class-incremental few-shot event detection to solve old knowledge forgetting and new class overfitting problems.
Outcome:	The proposed method reduces old knowledge forgetting and new class overfitting problems on two benchmark datasets.

Copied to clipboard

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

MacLaSa: Multi-Aspect Controllable Text Generation via Efficient Sampling from Compact Latent Space (2023.findings-emnlp)

Challenge:	Existing methods for ERE rely on large language models, but they face limitations.
Approach:	They propose an LLM-based approach with rationales for the ERE task . LLMERE transforms ERE into a question-and-answer task that may have multiple answers .
Outcome:	Experimental results show that LLMERE improves over existing methods.

Copied to clipboard

Hanxing Ding, Liang Pang, Zihao Wei, Huawei Shen, Xueqi Cheng, Tat-Seng Chua

Green & Sustainable NLP

Challenge:	Existing approaches to multi-aspect controllable text generation require expensive iteration / searching within the discrete text space during the decoding stage, resulting in a degradation of text quality due to the domain discrepancies between different aspects.
Approach:	They propose a framework that estimates compact latent space for multiple aspects and performs efficient Sampling with a fast sampler to eliminate domain discrepancies.
Outcome:	The proposed framework outperforms baselines on attribute relevance and textual quality while maintaining a high inference speed.

SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation (2023.acl-long)

Copied to clipboard

Junkai Zhou, Liang Pang, Huawei Shen, Xueqi Cheng

Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification (2026.acl-long)

Challenge:	Existing work on large-scale corpora-based language models is limited and hard to generalize to all types of pre-trained language models.
Approach:	They propose a two-stage SimOAP strategy that over-samples and post-evaluates large-scale responses from existing models and selects a good response based on multiple evaluation metrics.
Outcome:	The proposed strategy outperforms baseline and automatic evaluation strategies in both automatic and human evaluations.

Copied to clipboard

Zenghao Duan, Zhiyi Yin, Zhichao Shi, Liang Pang, Shaoling Jing, Zihe Huang, Jiayi Wu, Yu Yan, Jingcheng Deng, Huawei Shen, Xueqi Cheng

Challenge:	Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content.
Approach:	They propose a method that removes toxic subspaces from FFN parameters . they propose to use a lightweight method to eliminate toxic subespaces .
Outcome:	The proposed method achieves SOTA detoxification while preserving general capabilities without large-scale retraining.

Visual Named Entity Linking: A New Dataset and A Baseline (2022.findings-emnlp)

Copied to clipboard

Wen Sun, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng

Visual Data in NLP

Challenge:	Existing tasks in Visual Entity Linking (VEL) rely on textual data to complement multi-modal linking or only link objects with general entities.
Approach:	They propose a task to link regions of images with corresponding entities in Knowledge Bases . they propose three sub-tasks, based on a human-annotated visual person dataset .
Outcome:	The proposed task is based on a human-annotated visual person linking dataset . the proposed sub-tasks are validated on the WIKIPerson dataset based upon the proposed methods .

Copied to clipboard

Zenghao Duan, Wenbin Duan, Zhiyi Yin, Yinghan Shen, Shaoling Jing, Jie Zhang, Huawei Shen, Xueqi Cheng

Beyond Language: Learning Commonsense from Images for Reasoning (2020.findings-emnlp)

Challenge:	Existing knowledge editing methods struggle when tasked with editing multiple related knowledge pieces for the same subject.
Approach:	They propose a benchmark to assess the effectiveness of knowledge editing methods . they use same-subject edits to ensure comprehensive updates to entity-centric knowledge .
Outcome:	The proposed method over-relys on subject information, neglecting other critical factors, resulting in reduced editing effectiveness.

Copied to clipboard

Wanqing Cui, Yanyan Lan, Liang Pang, Jiafeng Guo, Xueqi Cheng

Inductive Link Prediction in N-ary Knowledge Graphs (2025.coling-main)

Challenge:	Existing commonsense reasoning methods use raw texts to perform data representation and answer prediction tasks.
Approach:	They propose a novel approach to learn commonsense from images instead of limited raw texts or costly knowledge bases.
Outcome:	The proposed approach outperforms language-based methods on commonsense reasoning problems on two commonsence reasoning problems.

Copied to clipboard

Jiyao Wei, Saiping Guan, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Low-Entropy Watermark Detection via Bayes’ Rule Derived Detector (2025.findings-acl)

Challenge:	Existing methods to predict missing elements in NKGs are fixed and therefore cannot be used in real-world situations.
Approach:	They propose a task to predict missing elements in unseen facts involving unseent entities and roles in emerging NKGs by embedding unseense entities and role-encoding neural networks.
Outcome:	The proposed task outperforms representative models across all datasets.

Copied to clipboard

Beining Huang, Du Su, Fei Sun, Qi Cao, Huawei Shen, Xueqi Cheng

Numerical Reasoning

Challenge:	Existing methods for text watermarking ignore strong evidences embedded in low-entropy tokens, causing statistical measures to falsely indicate the absence of a watermark.
Approach:	They propose a Bayes' Rule derived watermark Detector which exploits watermark information from every token by leveraging the posterior probability of watermark’s presence.
Outcome:	The proposed method achieves 50% and 70% relative improvements over baselines in code generation and math problem-solving tasks.

Bootstrapped Pre-training with Dynamic Identifier Prediction for Generative Retrieval (2024.findings-acl)

Copied to clipboard

Yubao Tang, Ruqing Zhang, Jiafeng Guo, Maarten Rijke, Yixing Fan, Xueqi Cheng

MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification (2022.coling-1)

Challenge:	Existing methods for document retrieval rely on static document identifiers . experimental results show that generative retrieval is outperforms dense retrieval in document retrievals.
Approach:	They propose a bootstrapped pre-training method that dynamically adjusts document identifiers during pre-train to accommodate the continuing memorization of the corpus.
Outcome:	The proposed method significantly outperforms existing pre-training generative retrieval baselines and performs well even in zero-shot settings.

Copied to clipboard

Kailin Zhao, Xiaolong Jin, Saiping Guan, Jiafeng Guo, Xueqi Cheng

MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective Verification (2025.acl-long)

Challenge:	Existing few-shot text classification methods lack labeled data in many scenarios.
Approach:	They propose a meta learning framework that obtains different learning rates for different tasks and neural network layers to enable the meta learner to quickly adapt to new training data.
Outcome:	The proposed framework can obtain different learning rates for different tasks and neural network layers so as to enable the meta learner to quickly adapt to new tasks.

Copied to clipboard

ZhaoDan Zhang, Zhao Zhang, Jin Zhang, Hui Xu, Xueqi Cheng

Sentiment Analysis

Challenge:	despite advances in large language models, challenges persist due to hallucination-models generating inaccurate content.
Approach:	They propose a framework that integrates multi-perspective verification with Retrieval-Augmented Generation to address these challenges.
Outcome:	The proposed method outperforms existing models on the SemEval-2016 and VAST datasets.

RoCEL: Advancing Table Entity Linking through Distinctive Row and Column Contexts (2024.emnlp-main)

Copied to clipboard

Yuanzheng Wang, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng

Multimodality

Challenge:	Existing methods for table entity linking ignore row and column contexts . existing methods for TEL focus on understanding sequential text contexts, making it difficult to adapt to the row and columns structure of tables.
Approach:	They propose to leverage row and column contexts to enhance the semantics of mentions in entity disambiguation.
Outcome:	The proposed method outperforms the state-of-the-art (SOTA) baseline by 1.5% on the in-domain dataset and 3.7% on average across three out-of domain datasets.

Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities (2024.findings-emnlp)

Copied to clipboard

Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei, Hongcheng Gao, Yilong Xu, Xueqi Cheng

Challenge:	Existing methods to update parametric knowledge of large language models (LLMs) are outdated and incontext editing (KE) is not effective due to the substantial cost associated with retraining.
Approach:	They propose a new decoding technique that enhances in-context editing (ICE) they propose to use parametric knowledge to update the models' knowledge .
Outcome:	The proposed technique improves ICE performance while incurring only half the latency.

The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)

Copied to clipboard

Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng

Adaptive Information Seeking for Open-Domain Question Answering (2021.emnlp-main)

Challenge:	Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome .
Approach:	They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens.
Outcome:	The proposed method reduces token usage by up to 44% while preserving accuracy.

Copied to clipboard

Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, Xueqi Cheng

Natural Language Interfaces

Challenge:	Existing iterative approaches to open-domain question answering use predefined strategies . e.g., BM25, DPR, and hyperlink are defined as actions .
Approach:	They propose a novel adaptive information-seeking strategy for open-domain question answering . they propose to use a partially observed Markov decision process to select a proper retrieval action .
Outcome:	Experiments on SQuAD Open and HotpotQA fullwiki show that AISO outperforms baseline methods with predefined strategies in retrieval and answer evaluations.

Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation (2025.emnlp-main)

Copied to clipboard

Jiayu Yao, Shenghua Liu, Yiwei Wang, Lingrui Mei, Baolong Bi, Yuyao Ge, Zhecheng Li, Xueqi Cheng

When Do LLMs Need Retrieval Augmentation? Mitigating LLMs’ Overconfidence Helps Retrieval Augmentation (2024.findings-acl)

Challenge:	Existing RAG models are sensitive to the order in which evidence is presented, resulting in unstable performance and biased reasoning.
Approach:	They propose to quantify position bias in multimodal RAG systems by using position sensitivity index . they also develop a visualization framework to trace attention allocation patterns across decoder layers .
Outcome:	The proposed framework shows that multimodal interactions intensify position bias compared to unimodal settings and that this bias increases logarithmically with retrieval range.

Copied to clipboard

Shiyu Ni, Keping Bi, Jiafeng Guo, Xueqi Cheng

Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have difficulty knowing they do not possess certain knowledge and tend to provide specious answers in such cases.
Approach:	They propose to use Retrieval Augmentation to enhance LLMs' ability to perceive their knowledge boundaries to reduce overconfidence.
Outcome:	The proposed methods reduce overconfidence and improve accuracy in large language models with fewer retrieval calls.

Copied to clipboard

Jingcheng Deng, Zhongtao Jiang, Liang Pang, Zihao Wei, Liwei Chen, Kun Xu, Yang Song, Huawei Shen, Xueqi Cheng

Soft Contextual Data Augmentation for Neural Machine Translation (P19-1)

Challenge:	Experimental results demonstrate that our method significantly outperforms traditional contrastive learning approaches when using the same amount of data.
Approach:	They propose a new contrastive learning method built on embedding conditional probability distributions that integrates two tasks: information compression and conditional distribution alignment.
Outcome:	The proposed method outperforms traditional contrastive learning approaches and achieves comparable performance to state-of-the-art models when using the same amount of data.

Copied to clipboard

Fei Gao, Jinhua Zhu, Lijun Wu, Yingce Xia, Tao Qin, Xueqi Cheng, Wengang Zhou, Tie-Yan Liu

Machine Translation

Challenge:	Existing methods for enhancing training data are limited in natural language tasks due to text characteristics.
Approach:	They propose a data augmentation method that softly augments a randomly chosen word in a sentence by its contextual mixture of multiple related words.
Outcome:	The proposed method outperforms baseline methods on small and large scale machine translation datasets.

Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method (2024.emnlp-main)

Copied to clipboard

Weichao Zhang, Ruqing Zhang, Jiafeng Guo, Maarten Rijke, Yixing Fan, Xueqi Cheng

Plot Retrieval as an Assessment of Abstract Semantic Association (2024.acl-srw)

Challenge:	Existing methods to detect text in training corpus are limited due to their low token probabilities.
Approach:	They propose a method to calibrate token probabilities for pretraining data detection by using a divergence-based calibration method.
Outcome:	The proposed method significantly outperforms existing methods on Chinese text on English-language benchmarks and patents.

Copied to clipboard

Shicheng Xu, Liang Pang, Jiangnan Li, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou

HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router (2026.acl-long)

Challenge:	Existing information retrieval datasets cannot capture abstract semantic associations well.
Approach:	They propose a task that retrieves relevant plots from the book for a query using a labeled dataset.
Outcome:	The proposed task can be used to evaluate the performance of IR models on the novel task Plot Retrieval.

Copied to clipboard

Lingrui Mei, Shenghua Liu, Yiwei Wang, Baolong Bi, Ruibin Yuan, Xueqi Cheng

A Survey of Link Prediction in N-ary Knowledge Graphs (2025.emnlp-main)

Challenge:	Current alignment approaches rely on refusal alignment to avoid harmful content . large language models are often overly cautious or overlook subtle harmful content.
Approach:	They propose a framework for fine-grained safe generation in Large Language Models that enables real-time, token-level harmfulness detection and redaction without loss in capability.
Outcome:	The proposed framework achieves over 90% in F1 score for detecting and redacting harmful content while preserving overall utility and informativeness of the model’s responses.

Copied to clipboard

Jiyao Wei, Saiping Guan, Da Li, Zhongni Hou, Miao Su, Yucan Guo, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026.acl-long)

Challenge:	N-ary Knowledge Graphs (NKGs) capture n-ary facts containing more than two entities.
Approach:	They present the first comprehensive survey of link prediction in NKGs . they provide an overview of the field and analyze their performance and application scenarios .
Outcome:	The proposed methods provide an overview of the field and analyze performance and application scenarios.

Copied to clipboard

Hexiang Tan, Wanli Yang, Junwei Zhang, Xin Chen, Rui Tang, Du Su, Jingang Wang, Yuanzhuo Wang, Fei Sun, Xueqi Cheng

RegaVAE: A Retrieval-Augmented Gaussian Mixture Variational Auto-Encoder for Language Modeling (2023.findings-emnlp)

Challenge:	Post-trained LLMs typically compromise reliability with severe overconfidence, resulting in inaccurate responses.
Approach:	They propose a solution that feeds PoLLMs into the base LLM to get confidence.
Outcome:	The proposed solution reduces expected calibration error (ECE) by 42.90% compared to the best unsupervised baselines.

Copied to clipboard

Jingcheng Deng, Liang Pang, Huawei Shen, Xueqi Cheng

MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning (2024.findings-acl)

Challenge:	Existing research on retrieval-augmented language models has two main problems: determining what information to retrieve and effectively combining retrieved information during generation.
Approach:	They propose a retrieval-augmented language model that captures current and future information from source and target text into a latent space.
Outcome:	The proposed model is more efficient than explicit raw text, but limited by context length and noise.

Copied to clipboard

Wanqing Cui, Keping Bi, Jiafeng Guo, Xueqi Cheng

Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation (2025.emnlp-main)

Challenge:	Language Models (LLMs) have gained increasing prominence in artificial intelligence, especially Large Language Model (LLm) due to the well-recognized reporting bias, the recording of commonsense information is significantly less than its existence in reality.
Approach:	They propose a Multi-mOdal REtrieval framework to leverage both text and images to enhance commonsense ability of language models.
Outcome:	The proposed framework can leverage both text and images to enhance commonsense ability of language models.

Copied to clipboard

Hengran Zhang, Minghao Tang, Keping Bi, Jiafeng Guo, Shihao Liu, Daiting Shi, Dawei Yin, Xueqi Cheng