Papers by Xu Jia

Towards Self-Evolving Agents: Enabling Autonomy through Interactive Experience Refinement (2026.findings-acl)

Challenge:	Existing methods for identifying student misconceptions overlook students' reasoning processes, authors report .
Approach:	They propose a knowledge distillation framework that mines high-value samples from existing data.
Outcome:	The proposed framework outperforms sota LLM and standard fine-tuned 72B models on cross-topic tests.

Copied to clipboard

Cheng Yang, Xuemeng Yang, Licheng Wen, Daocheng Fu, Jianbiao Mei, Rong Wu, Pinlong Cai, Yufan Shen, Nianchen Deng, Jia Xu, Botian Shi, Yu Qiao, Haifeng Li

Challenge:	Large Language Models struggle with complex, multi-step operational tasks because they remain static during inference and cannot learn from past experience.
Approach:	They propose a framework that organizes cross-domain insights to facilitate orchestration of long-horizon workflows.
Outcome:	The proposed framework outperforms existing methods on the TAC productivity benchmark and shows strong cross-task transferability.

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

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

ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue (2026.findings-acl)

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

Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Qingyu Niu, Guoqing Ma, Jingjiang Liu, Yidan Liang, Yilin Wang, Shimin Di, Jiajie Xu

Dialogue Systems & Conversational Agents

Challenge:	Existing approaches to multi-turn dialogues lack contextual consistency and dependencies, and models struggle to maintain factual faithfulness as interaction turns increase.
Approach:	They propose an adaptive context refactoring framework that monitors and reshapes the interaction history to mitigate contextual inertia and state drift.
Outcome:	The proposed model outperforms baselines while reducing token consumption.

Contrastive Preference Learning for Neural Machine Translation (2024.findings-naacl)

Copied to clipboard

Jianfei He, Shichao Sun, Sen Peng, Jie Xu, Xiaohua Jia, Wenjie Li

Machine Translation

Challenge:	Existing discrepancies between token-level objective and overall sequence-level quality of a model are causing exposure bias and other issues in NMT.
Approach:	They propose a contrastive preference model that integrates an indicator function to fine-tune a pre-trained model in Neural Machine Translation.
Outcome:	The proposed model outperforms the traditional Plackett-Luce model on three language pairs and also outperFORMs token-level and sequence-level baseline models.

Retrieval and Reasoning on KGs: Integrate Knowledge Graphs into Large Language Models for Complex Question Answering (2024.findings-emnlp)

Copied to clipboard

Yixin Ji, Kaixin Wu, Juntao Li, Wei Chen, Mingjie Zhong, Xu Jia, Min Zhang

One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments (2025.acl-long)

Challenge:	Large Language Models (LLMs) have performed impressively in various NLP tasks, but their inherent hallucination phenomena severely challenge their credibility in complex reasoning.
Approach:	They propose to integrate explainable Knowledge Graphs (KGs) with LLMs to alleviate hallucinations . they construct subgraphs to enhance the retrieval capabilities of KGs via CoT reasoning.
Outcome:	Extensive experiments on two KGQA datasets show that the proposed model achieves convincing performance compared to strong baselines.

Copied to clipboard

Ke Yi, Yuhui Xu, Heng Chang, Yuan Meng, Tong Zhang, Jia Li

Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting (2025.coling-industry)

Challenge:	Quantization has shown promise for Large Language Models, but current methods require lengthy training to alleviate quantization loss.
Approach:	They propose to decouple weights and incorporate Low-Rank adapters to reduce weight sharing . they validate the approach on LLaMA2 families and Mistral on downstream evaluation .
Outcome:	The proposed approach shows high performance while reducing deployment time faced with multiple scenarios.

Copied to clipboard

Zeyuan Chen, Haiyan Wu, Kaixin Wu, Wei Chen, Mingjie Zhong, Jia Xu, Zhongyi Liu, Wei Zhang

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Existing approaches to relevance modeling have lacked generalization and accuracy . recent studies have focused on capturing the semantic relationships between queries and items .
Approach:	They propose a framework that integrates world knowledge stored in LLMs with specialized domain knowledge represented by user behavior data for promising performance.
Outcome:	The proposed framework can handle full-scale search traffics of Alipay with acceptable cost and latency.

Copied to clipboard

Pengyue Jia, Derong Xu, Xiaopeng Li, Zhaocheng Du, Xiangyang Li, Yichao Wang, Yuhao Wang, Qidong Liu, Maolin Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

ReTRE: Benchmarking LLM Transfer Robustness with Structure-Preserving Variants (2026.acl-long)

Challenge:	Existing approaches to rerank and align documents based on reasoning capabilities of large language models (LLMs) . prior work shows that LLMs have exceptional reasoning and text generation capabilities .
Approach:	They propose a rationale extraction method that leverages reasoning capabilities of large language models to extract the rationales necessary for answering a query.
Outcome:	The proposed method is compared with baseline methods on two tasks across three datasets.

Copied to clipboard

ZhongDong Li, Weijie Shi, Yue Cui, Haolun MA, Yuanjun Liu, Jiawei Li, An Liu, Jia Zhu, Jiajie Xu

How to Ask Good Questions? Try to Leverage Paraphrases (2020.acl-main)

Challenge:	Learning transfer theory emphasizes that applying acquired knowledge to novel manifestations is a key signal of deep understanding
Approach:	They propose a benchmark that probes transfer robustness along two rewrite levels: Near Transfer and Far Transfer.
Outcome:	The proposed benchmark demonstrates that large language models are robust when faced with novel manifestations of the same problem.

Copied to clipboard

Xin Jia, Wenjie Zhou, Xu Sun, Yunfang Wu

Text Generation

Challenge:	Existing methods to generate human-like questions rely on paraphrases to generate good questions.
Approach:	They propose to integrate paraphrase knowledge into question generation to generate human-like questions by combining paraphrases with a back-translation method.
Outcome:	The proposed model achieves obvious performance gain over several strong baselines and human evaluation validates that it can ask questions of high quality by leveraging paraphrase knowledge.

Table-as-Search: Agentic Information Seeking is Table Completion (2026.findings-acl)

Copied to clipboard

Tian Lan, Felix Henry, Bin Zhu, Qianghuai Jia, Junyang Ren, Qihang PU, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo

Can Data Diversity Enhance Learning Generalization? (2022.coling-1)

Challenge:	Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states within one plain-text context is inherently fragile.
Approach:	They propose a structured planning framework that reformulates the InfoSeeking task as a Table Completion task.
Outcome:	The proposed framework outperforms state-of-the-art frameworks across three kinds of benchmarks, including multi-agent framework and commercial systems.

Copied to clipboard

Yu Yu, Shahram Khadivi, Jia Xu

Challenge:	a diversity advanced actor-critical reinforcement learning framework is used to improve NLP generalization and accuracy.
Approach:	They introduce Diversity Advanced Actor-Critic reinforcement learning framework to improve NLP generalization and accuracy.
Outcome:	The proposed framework outperforms domain adaptation and generalization baselines without using any target domain knowledge.

DIDS: Domain Impact-aware Data Sampling for Large Language Model Training (2025.emnlp-main)

Copied to clipboard

Weijie Shi, Jipeng Zhang, Yaguang Wu, Jingzhi Fang, Shibo Zhang, Yao Zhao, Hao Chen, Ruiyuan Zhang, Yue Cui, Jia Zhu, Sirui Han, Jiajie Xu, Xiaofang Zhou

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026.acl-long)

Challenge:	Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact.
Approach:	They propose to use a Fisher-Information Matrix-guided metric to measure domain impact to ensure intra-domain consistency and accuracy.
Outcome:	The proposed model achieves 3.4% higher average performance while maintaining comparable training efficiency.

Copied to clipboard

Zhiyuan Peng, Xin Yin, Pu Zhao, Fangkai Yang, Lu Wang, Ran Jia, Xu Chen, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Challenge:	Existing benchmarks focus on isolated function/class-level generation, neglecting complete microservice repository generation.
Approach:	They propose a multilingual benchmark for repository-level end-to-end web microservice generation that reflects real-world development workflows.
Outcome:	The benchmark compared 106 repositories across 18 domains and 11 frameworks and 1,258 API endpoints and 2,335 test cases.

Modularized Interaction Network for Named Entity Recognition (2021.acl-long)

Copied to clipboard

Fei Li, Zheng Wang, Siu Cheung Hui, Lejian Liao, Dandan Song, Jing Xu, Guoxiu He, Meihuizi Jia

Measuring Robustness for NLP (2022.coling-1)

Challenge:	Named Entity Recognition (NER) models focus on word-level information, while segment-based models focus only on word level information.
Approach:	They propose a Modularized Interaction Network (MIN) model which utilizes both word-level information and segment-level dependencies.
Outcome:	The proposed model outperforms the current state-of-the-art models on three NER benchmark datasets.

Copied to clipboard

Yu Yu, Abdul Rafae Khan, Jia Xu

Neural Gibbs Sampling for Joint Event Argument Extraction (2020.aacl-main)

Challenge:	Existing methods to evaluate NLP models are limited to news domains and cannot be generalized to other domains.
Approach:	They propose a measure of NLP quality based on robustness . they measure consistency of cross-domain accuracy and introduce coefficient of variation and gamma-Robustness based upon human evaluation .
Outcome:	The proposed approach shows higher agreement with human evaluation than accuracy scores on ranking machine translation systems.

Copied to clipboard

Xiaozhi Wang, Shengyu Jia, Xu Han, Zhiyuan Liu, Juanzi Li, Peng Li, Jie Zhou

Instance-Guided Prompt Learning for Few-Shot Text Matching (2022.findings-emnlp)

Challenge:	Existing methods for event argument extraction cannot adequately model the correlation between event arguments and their roles.
Approach:	They propose a Bayesian model to jointly extract event arguments using Gibbs sampling . they train two neural networks to model prior distribution and conditional distribution over event arguments .
Outcome:	The proposed model can achieve comparable results to existing methods on two widely-used datasets.

Copied to clipboard

Jia Du, Xuanyu Zhang, Siyi Wang, Kai Wang, Yanquan Zhou, Lei Li, Qing Yang, Dongliang Xu

GenTKG: Generative Forecasting on Temporal Knowledge Graph with Large Language Models (2024.findings-naacl)

Challenge:	Few-shot text matching is a more practical technique to determine whether two texts are semantically identical.
Approach:	They propose a pluggable prompt learning method for few-shot text matching . they use the semantics of instances to regulate the effects of the gate on the prompt tokens .
Outcome:	The proposed method outperforms baselines on MRPC and QQP.

Copied to clipboard

Ruotong Liao, Xu Jia, Yangzhe Li, Yunpu Ma, Volker Tresp

RelEdit: Evaluating Conceptual Knowledge Editing in Language Models via Relational Reasoning (2025.findings-acl)

Challenge:	Existing methods for temporal relational forecasting are limited and require limited training data.
Approach:	They propose a retrieval-augmented generation framework that uses temporal logical rule-based retrieval and parameter-efficient instruction tuning to solve temporal knowledge forecasting challenges.
Outcome:	The proposed framework outperforms conventional methods in the temporal knowledge graph domain with low computation resources.

Copied to clipboard

Yifan Niu, Miao Peng, Nuo Chen, Yatao Bian, Tingyang Xu, Jia Li

Separation and Fusion: A Novel Multiple Token Linking Model for Event Argument Extraction (2024.naacl-long)

Challenge:	Existing knowledge editing methods struggle to reason about related conceptual knowledge effectively, despite a lack of model-level relational reasoning.
Approach:	They propose a benchmark to assess concept-level and instance-level relational reasoning abilities of edited models.
Outcome:	The proposed model obtains the best scores on the memory-based in-context editing baseline, MICE, suggesting a promising direction for model editing.

Copied to clipboard

Jing Xu, Dandan Song, Siu Hui, Zhijing Wu, Meihuizi Jia, Hao Wang, Yanru Zhou, Changzhi Zhou, Ziyi Yang

Logits-Based Finetuning (2025.emnlp-main)

Challenge:	Existing methods for event argument extraction (EAE) lack cross-event information and require longer role sequences . et al. (2017): outperforms state-of-the-art methods for EE.
Approach:	They propose a separation-and-fusion paradigm to separate the acquisition of cross-event information and fuse it into the argument extraction of a target event.
Outcome:	The proposed model outperforms the state-of-the-art models on four widely used datasets.

Copied to clipboard

Jingyao Li, Senqiao Yang, Sitong Wu, Han Shi, Chuanyang Zheng, Hong Xu, Jiaya Jia

Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory (2026.acl-long)

Challenge:	Existing methods for developing compact and efficient large language models lack token-level dependencies and linguistic diversity.
Approach:	They propose a logits-based fine-tuning framework that integrates supervised learning and knowledge distillation to build enriched training targets using teacher logits and ground truth labels.
Outcome:	The proposed method outperforms existing methods on a large-scale logits dataset and a series of science-focused models.

Copied to clipboard

Derong Xu, Shuochen Liu, Pengfei Luo, Pengyue Jia, Yingyi Zhang, Yi Wen, Yimin Deng, Wenlin Zhang, Enhong Chen, Xiangyu Zhao, Tong Xu

Challenge:	Existing memory systems rely on static, hand-crafted update rules for personalization, but sparse outcome rewards provide weak supervision, resulting in unstable long-horizon optimization.
Approach:	They propose a memory guideline optimization framework that learns how memory should be organized and what information to update.
Outcome:	The proposed framework learns how memory should be organized and what information to update.

Assessing Quality Estimation Models for Sentence-Level Prediction (C18-1)

Copied to clipboard

Hoang Cuong, Jia Xu

Challenge:	Using a relevant QE model is also very important in QE.
Approach:	They evaluate a wide range of advanced sentence-level Quality Estimation models including Support Vector Regression, Ride Regression and Bayesian Neural Networks.
Outcome:	The proposed models behave differently in evaluation settings depending on whether test data come from the same domain as the training data or not.

Estimating Large Language Model Capabilities without Labeled Test Data (2023.findings-emnlp)

Copied to clipboard

Harvey Fu, Qinyuan Ye, Albert Xu, Xiang Ren, Robin Jia

EmByte: Decomposition and Compression Learning for Small yet Private NLP (2025.findings-emnlp)

Challenge:	Large Language Models have shown impressive ability to perform in-context learning from only a few examples, but their accuracy varies widely from task to task.
Approach:	They propose a method that trains a meta-model using LLM confidence scores as features to perform ICL accuracy estimation.
Outcome:	The proposed method improves over baselines across 7 out of 12 settings and achieves the same accuracy as evaluating on 40 sampled examples per task.

Copied to clipboard

Shenglan Li, Jia Xu, Mengjiao Zhang

QuickLLaMA: Query-aware Inference Acceleration for Large Language Models (2025.coling-main)

Challenge:	EMBYTE is a byte-level tokenization model that reduces embedding parameters by up to 94% . it is also resilient to privacy threats such as gradient inversion attacks .
Approach:	EMBYTE is a byte-level tokenization model that decomposes subwords into fine-grained byte embeddings and then compresses them via neural projection.
Outcome:	EMBYTE achieves substantial embedding compression while preserving accuracy and enhancing privacy.

Copied to clipboard

Jingyao Li, Han Shi, Sitong Wu, Chuanyang Zheng, Zhenguo Li, Xin Jiang, Hong Xu, Jiaya Jia

BMInf: An Efficient Toolkit for Big Model Inference and Tuning (2022.acl-demo)

Challenge:	Large Language Models (LLMs) struggle with capturing long-distance dependencies within sequences to deeply understand semantics.
Approach:	They propose a system that captures relevant information within a fixed window size and provides precise answers to queries.
Outcome:	The proposed system can read Harry Potter within 30s and accurately answer the questions.

Copied to clipboard

Xu Han, Guoyang Zeng, Weilin Zhao, Zhiyuan Liu, Zhengyan Zhang, Jie Zhou, Jun Zhang, Jia Chao, Maosong Sun

Green & Sustainable NLP

Challenge:	Recent years, pre-trained language models (PLMs) have achieved promising results on various NLP tasks.
Approach:	They propose an open-source toolkit for big model inference and tuning which can support big model tuning at extremely low computation cost.
Outcome:	The proposed toolkit can support big model inference and tuning at extremely low computation cost.

Using Review Combination and Pseudo-Tokens for Aspect Sentiment Quad Prediction (2025.findings-naacl)

Copied to clipboard

Jiazhou Chen, Xu Jia, RuiQiang Guo

Sentiment Analysis

Challenge:	Existing models confuse implicit and explicit sentiment, making it difficult to extract quadruples effectively.
Approach:	They propose a framework that leverages distinct labeled features from diverse reviews and incorporates pseudo-token prompts to harness the semantic knowledge of pre-trained models.
Outcome:	The proposed framework improves over four public datasets, averaging 1.99% F1 improvement, particularly in instances involving implicit sentiment.

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

Copied to clipboard

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

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

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

Copied to clipboard

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

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation (2025.acl-long)

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

Haoran Jin, Meng Li, Xiting Wang, Zhihao Xu, Minlie Huang, Yantao Jia, Defu Lian

Probabilistic Robustness for Data Filtering (2023.eacl-main)

Challenge:	Existing LLMs do not possess consistent values, but many have been developed to align them at the behavioral level, including supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF).
Approach:	They propose a Controlled Value Vector Activation method that directly aligns the internal values of Large Language Models by interpreting how a value is encoded in their latent representations.
Outcome:	The proposed method achieves highest success rate across 10 basic values without hurting model performance and fluency, and ensures target values even with opposite and potentially malicious input prompts.

Copied to clipboard

Yu Yu, Abdul Rafae Khan, Shahram Khadivi, Jia Xu

MMDAG: Multimodal Directed Acyclic Graph Network for Emotion Recognition in Conversation (2022.lrec-1)

Challenge:	Modern machine learning works with massive amounts of data on a range of tasks like language modeling, object detection, and data mining.
Approach:	They propose a probabilistic robustness rewarded data optimization approach to enhance the model's generalization power by selecting training data that optimizes probabilistic metrics.
Outcome:	The proposed approach achieves +17.2% increase of accuracy and -28.05 decrease of perplexity on unknown-domain test sets.

Copied to clipboard

Shuo Xu, Yuxiang Jia, Changyong Niu, Hongying Zan

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Challenge:	Emotion recognition in conversation is important for an empathetic dialogue system to understand the user’s emotion and then generate appropriate emotional responses.
Approach:	They propose to use multimodal directed acyclic graphs to integrate multimodal information and contextual information into a DAG architecture to exploit multimodal contexts.
Outcome:	Comparative studies on IEMOCAP and MELD show that the proposed model outperforms state-of-the-art models.

Copied to clipboard

Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)

Challenge:	Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach:	They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome:	The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.

Copied to clipboard

Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen

The Agent’s First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios (2026.findings-acl)

Challenge:	Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks.
Approach:	They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings.
Outcome:	The proposed framework achieves the strongest overall performance across all models.

Copied to clipboard

Daocheng Fu, Jianbiao Mei, Rong Wu, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi

Challenge:	Existing research mainly focuses on performance upper bounds in static environments, overlooking stochastic real-world deployment.
Approach:	They propose a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.
Outcome:	The proposed model evaluates agents in a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding (2024.acl-long)

Copied to clipboard

Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Bill Yuchen Lin, Radha Poovendran

A Self-Evolving LLM Agent Framework for Role-Based Norm Compliance in Healthcare (2026.findings-acl)

Challenge:	Despite advances in large language models, they face substantial challenges in terms of safety.
Approach:	They develop a safety-aware decoding strategy for large language models to defend against jailbreak attacks.
Outcome:	The proposed strategy outperforms six defense methods against jailbreak attacks on five LLMs.

Copied to clipboard

Haijie Ruan, Xiaowu Jiang, Zhanpeng LI, Wei Jia, Xuanwu Xu, Xiao-Fen Shan, Shujie Chen, Xindong Ye

Neural Topic Model with Reinforcement Learning (D19-1)

Challenge:	Existing systems treat roles as static prompts and rely on one-shot safety filters . a self-evolving LLM agent is proposed that learns from role-based social experience .
Approach:	They propose a self-evolving LLM agent that learns from role-based social experience and explicitly models communicator-level individual traits informed by prior communication questionnaires and clinical literature.
Outcome:	The proposed agent learns from role-based social experience and models communicator-level individual traits informed by prior communication questionnaires and clinical literature.

Copied to clipboard

Lin Gui, Jia Leng, Gabriele Pergola, Yu Zhou, Ruifeng Xu, Yulan He

RSDA: Restoring Stale Data Affinity via Dynamic Renovation Strategy for Mitigating Data Scarcity (2026.acl-long)

Challenge:	Experimental results show superior performance on perplexity and topic coherence measures compared to state-of-the-art topic models.
Approach:	They propose to incorporate topic coherence measures as reward signals to guide the learning of a VAE-based topic model.
Outcome:	The proposed model is able to separating background words dynamically from topic words eliminating the pre-processing step of filtering infrequent and/or top frequent words, typically required for learning traditional topic models.

Copied to clipboard

Yidan Liang, Jia Zhu, Weijie Shi, Hanghui Guo, Yue Cui, Jiawei Shen, Guoqing Ma, Jingjiang Liu, Qingyu Niu, Yilin Wang, Shimin Di, Jiajie Xu

R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning (2026.findings-acl)

Challenge:	High-quality data is the cornerstone of advancing large language models, but the supply of premium data is nearing depletion, while vast stale corpora remain underutilized.
Approach:	They propose a framework to restore stale data affinity by quantifying the latent value of samples and employing a dynamic renovation strategy selection mechanism to determine the optimal component-level strategy.
Outcome:	The proposed framework achieves performance improvements using less than 10% of the data volume, underscoring that the latent potential of stale corpora remains largely untapped.

Copied to clipboard

Qingfei Zhao, Ruobing Wang, Dingling Xu, Daren Zha, Ma Bowen, Zhichun Wang, Shijie Jia, Limin Liu, Xin Wang

KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning (2026.acl-long)

Challenge:	Large language models (LLMs) have demonstrated impressive capabilities in multi-step and long-chain reasoning, but extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge.
Approach:	They propose a framework for Reasoning–Search integration that integrates multi-reward signals to optimize the reasoning–search interaction trajectories.
Outcome:	Experiments on seven datasets show that R-Search significantly outperforms mainstream RAG baselines.

Copied to clipboard

Jingjiang Liu, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Xiaokang Jin, Yilin Wang, Qingyu Niu, Jiawei Shen, Guoqing Ma, Yidan Liang, Shimin Di, Jiajie Xu

LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning (2025.acl-long)

Challenge:	Existing summarization methods compress content for gist browsing, but they break prerequisite logic in instructional videos.
Approach:	They propose a framework that decouples epistemic planning from content generation.
Outcome:	The proposed framework outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage.

Copied to clipboard

Weijie Shi, Han Zhu, Jiaming Ji, Mengze Li, Jipeng Zhang, Ruiyuan Zhang, Jia Zhu, Jiajie Xu, Sirui Han, Yike Guo

Coding Textual Inputs Boosts the Accuracy of Neural Networks (2020.emnlp-main)

Challenge:	Existing legal judgment prediction methods struggle with logical errors when conducting complex legal reasoning.
Approach:	They propose a method which enhances LJP reliability through step-wise verification and correction of the reasoning process.
Outcome:	The proposed model significantly improves concordance with court decisions from 72.37 to 80.27 on LLAMA-3.1-70B.

Copied to clipboard

Abdul Rafae Khan, Jia Xu, Weiwei Sun

Challenge:	a new approach to natural language processing uses arbitrary symbols to represent meaning . Soundex, MetaPhone, NYSIIS, logogram are used as inputs for NLP .
Approach:	They propose to use arbitrary symbols to represent linguistic meaning of a word . they propose to integrate codewords with text to provide more reliable inputs .
Outcome:	The proposed approach outperforms state-of-the-art models on machine translation, language modeling, and part-of speech tagging.

MultiDx: A Multi-Source Knowledge Integration Framework towards Diagnostic Reasoning (2026.findings-acl)

Copied to clipboard

Yimin Deng, Zhenxi Lin, Yejing Wang, Guoshuai Zhao, Pengyue Jia, Zichuan Fu, Derong Xu, Yefeng Zheng, Xiangyu Zhao, Li Zhu, Xian Wu, Xueming Qian

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

Challenge:	Existing approaches focus on diagnostic reasoning based on internal model knowledge or static knowledge bases.
Approach:	They propose a two-stage diagnostic reasoning framework that integrates multi-perspective evidence to generate a diagnostic prediction.
Outcome:	The proposed method generates suspected diagnoses and reasoning traces from web search, SOAP-formatted case, and clinical case database.

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 .

KG-FLIP: Knowledge-guided Fashion-domain Language-Image Pre-training for E-commerce (2023.acl-industry)

Copied to clipboard

Qinjin Jia, Yang Liu, Daoping Wu, Shaoyuan Xu, Huidong Liu, Jinmiao Fu, Roland Vollgraf, Bryan Wang

Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation (2020.emnlp-main)

Challenge:	Various visionlanguage pre-training (VLP) models learn cross-modal alignment from large-scale well-aligned image-text datasets without leveraging external knowledge.
Approach:	They propose a knowledge-guided fashion-domain language-image pre-training framework that learns fine-grained representations in e-commerce domain and utilizes external knowledge to improve the pre-train efficiency.
Outcome:	The proposed framework outperforms state-of-the-art models on Amazon and Fashion-Gen datasets by large margins.

Copied to clipboard

Ruibo Liu, Guangxuan Xu, Chenyan Jia, Weicheng Ma, Lili Wang, Soroush Vosoughi

Evian: Towards Explainable Visual Instruction-tuning Data Auditing (2026.findings-acl)

Challenge:	Existing methods for data augmentation produce low readability or semantic consistency.
Approach:	They propose a framework which augments data through reinforcement learning guided conditional generation.
Outcome:	The proposed framework improves F1 performance on three different classification tasks by 8.7% on average when given only 10% of the whole data for training.

Copied to clipboard

Zimu Jia, Mingjie Xu, Andrew Estornell, Jiaheng Wei

RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game (2026.findings-acl)

Challenge:	Existing data filtering methods rely on coarse-grained scores that lack granularity to identify nuanced semantic flaws.
Approach:	They propose a "Decomposition-then-Evaluation" paradigm that breaks model responses into constituent cognitive components.
Outcome:	The proposed model outperforms models trained on larger datasets in three key areas . the authors show that Logical Coherence is the most critical factor in data quality evaluation .

Copied to clipboard

Shijia Xu, Yu Wang, Xiaolong Jia, Zhou Wu, Kai Liu, April Xiaowen Dong

Challenge:	despite the adoption of Large Language Models (LLMs), contract revision remains impeded because generic models treat strict legal constraints as mere suggestions.
Approach:	They propose a risk-constrained bilevel Stackelberg framework that models high-stakes revision as a strategic interaction rather than an open-ended conversation.
Outcome:	The proposed framework achieves state-of-the-art performance with an average RRR of 84.21% and enhanced token efficiency.

Reinforcement Learning with Supervised Alignment (2025.findings-emnlp)

Copied to clipboard

João Luís Lins, Jia Xu

Pre-trained Language Model with Prompts for Temporal Knowledge Graph Completion (2023.findings-acl)

Challenge:	Supervised fine-tuning (SFT) is a widely used method for adapting Large Language Models to specific tasks.
Approach:	They propose a method that uses supervised fine-tuning to train a reward model for reinforcement learning.
Outcome:	The proposed method outperforms existing methods on in-domain benchmarks but surpasses them 50 times on out-of-domain and cross-task evaluations.

Copied to clipboard

Wenjie Xu, Ben Liu, Miao Peng, Xu Jia, Min Peng

DioR: Adaptive Cognitive Detection and Contextual Retrieval Optimization for Dynamic Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Existing methods for temporal knowledge graph completion (TKGC) focus on extracting information from timestamps and insufficiently utilizing implied information in relations.
Approach:	They propose a temporal knowledge graph completion model with prompts that converts quadruples into pre-trained language inputs and prompts to make coherent sentences with implicit semantic information.
Outcome:	The proposed model can make coherent sentences with implicit semantic information.

Copied to clipboard

Hanghui Guo, Jia Zhu, Shimin Di, Weijie Shi, Zhangze Chen, Jiajie Xu

Analyzing Encoded Concepts in Transformer Language Models (2022.naacl-main)

Challenge:	Existing methods for generating large language models face limitations in key aspects such as retrieval triggers and contextual scrutiny of retrieval content.
Approach:	They propose a dynamic RAG method that uses cognitive detection and contextual retrieval optimization to determine when retrieval is needed and what to retrieve for LLMs.
Outcome:	The proposed method achieves superior performance on all tasks, demonstrating the effectiveness of the proposed method.

Copied to clipboard

Hassan Sajjad, Nadir Durrani, Fahim Dalvi, Firoj Alam, Abdul Khan, Jia Xu

Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning (2024.findings-naacl)

Challenge:	a new framework to analyze how latent concepts are encoded in representations learned in pre-trained lan-guage models is proposed . conceptX uses clustering to discover the encoded concepts and align them with a large set of human-defined concepts.
Approach:	They propose a framework to analyze how latent concepts are encoded in representations learned within pre-trained lan-guage models.
Outcome:	The proposed framework explains encoded concepts by aligning with human-defined concepts.

Copied to clipboard

Yanhui Guo, Shaoyuan Xu, Jinmiao Fu, Jia Liu, Chaosheng Dong, Bryan Wang

Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS (2026.findings-acl)

Challenge:	Existing methods for continual prompt tuning are limited by the ever-growing parameter scale of modern language models (e.g., GPT-4 that may have 1.76 trillion parameters).
Approach:	They propose a method for continual prompt tuning that enables the lifelong learning of a pre-trained language model by adding a task-specific prompt to a queue of older tasks.
Outcome:	The proposed method outperforms the state-of-the-art methods substantially on continual prompt tuning benchmarks.

Copied to clipboard

Shijia Xu, Zhou Wu, Xiaolong Jia, Yu Wang, Kai Liu, April Xiaowen Dong

Grouping Words with Semantic Diversity (2021.naacl-main)

Challenge:	Existing approaches to retrieval-augmented generation still face problems with low context utilization and frequent hallucinations.
Approach:	They propose a framework that reformulates retrieval and generation as constrained optimization and path planning.
Outcome:	The proposed framework significantly improves reasoning accuracy on complex queries while reducing hallucinations.

Copied to clipboard

Karine Chubarian, Abdul Rafae Khan, Anastasios Sidiropoulos, Jia Xu

Challenge:	a new approach to grouping input words based on their semantic diversity is proposed . high-dimensional inputs and learning complexity hinders deep learning generalization, authors say .
Approach:	They propose a way to group input words based on their semantic diversity to simplify input language representation with low ambiguity.
Outcome:	The proposed methods generalize NLP models and demonstrate improvements on medium-scale machine translation tasks.

ResFormer: All-Time Reservoir Memory for Long Sequence Classification (2025.emnlp-main)

Copied to clipboard

Hongbo Liu, Jia Xu

Byte-based Multilingual NMT for Endangered Languages (2022.coling-1)

Challenge:	Existing models with quadratic time and memory complexity restrict input length . however, analyzing extensive sequential contexts is challenging .
Approach:	They propose a neural network architecture that captures contextual dependencies in linear time and a nonlinear readout to model short-term dependencies within sentences.
Outcome:	The proposed model outperforms baseline models on EmoryNLP datasets and on IEMOCAP and MultiWOZ datasets.

Copied to clipboard

Mengjiao Zhang, Jia Xu

Multilinguality

Challenge:	Existing work has not studied how byte encoding can benefit endangered languages . multilingual neural machine translation (MNMT) models suffer from out-of-vocabulary issues and representation bottleneck .
Approach:	They propose a multilingual multilingual neural machine translation system to alleviate the representation bottleneck and improve translation performance in endangered languages.
Outcome:	The proposed system outperforms subword-based models on twelve languages up to +18.5 BLEU points, an 840% relative improvement over baseline models.

Making RALM Robust to Irrelevant Contexts via Layer Knowledge Guided Attention (2025.findings-acl)

Copied to clipboard

Weijie Shi, Hao Chen, Jiaming Li, Yao Zhao, Yazhong Zhang, Qijin Chen, Jipeng Zhang, Ruiyuan Zhang, Jia Zhu, Jiajie Xu, Xiaofang Zhou

AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant (2025.findings-acl)

Challenge:	Large language models (LLMs) face factual hallucination and knowledge obsolescence when tackling knowledge-intensive tasks.
Approach:	They propose a layer-knowledge guided attention method which harnesses the layer-wise knowledge of large language models to optimize per-layer attention on useful passages.
Outcome:	The proposed method outperforms existing methods on RALM benchmarks.

Copied to clipboard

Chengyou Jia, Minnan Luo, Zhuohang Dang, Qiushi Sun, Fangzhi Xu, Junlin Hu, Tianbao Xie, Zhiyong Wu

Challenge:	Existing agents lack generalization and specialization capabilities for open-ended tasks . specialized generalists are often underdeveloped in real-world environments .
Approach:	They propose a platform to dynamically integrate heterogeneous agents for automating computer tasks . they propose specialized generalist agent MetaAgent with the AgentToken strategy .
Outcome:	The proposed platform expands capabilities of existing agents in generalization and specialization . it can be used to automate open-ended tasks in real-world environments .

Dialect-SQL: An Adaptive Framework for Bridging the Dialect Gap in Text-to-SQL (2025.emnlp-main)

Copied to clipboard

Jie Shi, Xi Cao, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Peng Wang, Wei Wang

Programming Languages in NLP

Challenge:	Existing Text-to-SQL research focuses on specific database systems, limiting adaptability to different dialects.
Approach:	They propose a framework that employs Object Relational Mapping (ORM) code as an intermediate language to bridge this gap.
Outcome:	The proposed framework outperforms existing methods that generate SQL queries directly.

Generative Input: Towards Next-Generation Input Methods Paradigm (2024.findings-acl)

Copied to clipboard

Keyu Ding, Yongcan Wang, Zihang Xu, Zhenzhen Jia, Enhong Chen

Contrastive Novelty-Augmented Learning: Anticipating Outliers with Large Language Models (2023.acl-long)

Challenge:	generative models have been used for various NLP tasks but their application in the field of input methods remains under-explored.
Approach:	They propose a novel Generative Input paradigm that uses prompts to handle all input scenarios and other intelligent auxiliary input functions, optimizing the model with user feedback.
Outcome:	The proposed paradigm achieves state-of-the-art in the Full-mode Key-sequence to Characters task and surpasses GPT-4 in the other input methods.

Copied to clipboard

Albert Xu, Xiang Ren, Robin Jia

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

Challenge:	Existing methods for classification are overly confident on unseen examples . despite recent advances in NLP, some categories of distribution shift still pose serious challenges.
Approach:	They propose a method that generates OOD examples representative of novel classes and trains to decrease confidence on them.
Outcome:	The proposed method improves classifiers' ability to detect and abstain on novel class examples over previous methods by 2.3% and 5.5% over previous approaches.

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

CPRM: A LLM-based Continual Pre-training Framework for Relevance Modeling in Commercial Search (2025.naacl-industry)

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

Kaixin Wu, Yixin Ji, Zeyuan Chen, Qiang Wang, Cunxiang Wang, Hong Liu, Baijun Ji, Xu Jia, Zhongyi Liu, Jinjie Gu, Yuan Zhou, Linjian Mo

Revealing Procedural Reasoning Structures in Chain-of-Thought Training via Span-Level Gradient Organization (2026.acl-long)

Challenge:	Relevance modeling between queries and items is a key component of commercial search engines.
Approach:	They propose a framework for continual pre-training of LLMs to enhance domain knowledge . they employ queries and multi-field item to jointly pre-train for enhancing domain knowledge.
Outcome:	The proposed model achieves convincing performance compared to strong baselines.

Copied to clipboard

Jia Liu, Jiaxin Luo, Weiwen Xu, Jonathan M. Garibaldi, Xiao-Kun Wu, Yixue Hao, Min Chen

PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning (2025.acl-long)

Challenge:	Chain-of-Thought (CoT) prompts elicit multi-step reasoning, yet how reasoning related structure is expressed during training remains poorly understood.
Approach:	They propose a framework that tracks span-level gradients during fine-tuning on reasoning benchmarks to understand how models develop structured, step-by-step reasoning capabilities.
Outcome:	The proposed framework tracks span-level gradients during fine-tuning on reasoning benchmarks to understand how models develop structured, step-by-step reasoning capabilities.

Copied to clipboard

Zhicong Lu, Changyuan Tian, PeiguangLi PeiguangLi, Li Jin, Sirui Wang, Wei Jia, Ying Shen, Guangluan Xu

MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution (2026.acl-long)

Challenge:	Existing studies on Large Language Models (LLMs) have failed to evaluate their performance in event reasoning with a single event relational type or reasoning format.
Approach:	They propose a benchmark to evaluate LLMs' event reasoning capability using a single event relational type or reasoning format.
Outcome:	The proposed model improves on 10K diverse instruction-tuning demonstrations to alleviate event reasoning-oriented data scarcity.

Copied to clipboard

Zihan Wu, Jie Xu, Yun Peng, Chun Yong Chong, Xiaohua Jia

Seek-and-Solve: Benchmarking MLLMs for Visual Clue-Driven Reasoning in Daily Scenarios (2026.findings-acl)

Challenge:	Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to the heterogeneity of vulnerability patterns and manual prompt engineering for massive weakness categories is unscalable.
Approach:	They propose a retrieval-augmented multi-agent framework for precise and broad-coverage vulnerability detection using a coarse-to-fine strategy.
Outcome:	The proposed framework outperforms the baseline model on 130 CWE types and achieves 34.79% Macro-F1 performance.

Copied to clipboard

Xiaomin Li, Tala Wang, Zichen Zhong, Ying Zhang, Zirui Zheng, Takashi Isobe, Dezhuang Li, Huchuan Lu, You He, Xu Jia