Papers by Liang Xie

MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows (2026.acl-long)

Challenge:	Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks.
Approach:	They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams.
Outcome:	The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models.

Copied to clipboard

Xiquan Li, Junxi Liu, Yuzhe Liang, Zhikang Niu, Wenxi Chen, Xie Chen

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models (2024.findings-acl)

Challenge:	Recent advances in Text-to-Audio Generation (TTA) systems suffer from slow inference speed, authors report . authors demonstrate that MeanAudia achieves state-of-the-art performance in single-step audio generation .
Approach:	They propose a text-to-audio generator capable of rendering realistic sound with only one function evaluation.
Outcome:	The proposed system achieves state-of-the-art performance in single-step audio generation.

Copied to clipboard

Qian Lou, Xin Liang, Jiaqi Xue, Yancheng Zhang, Rui Xie, Mengxin Zheng

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

Challenge:	Existing certified robustness methods for certifying input-specific text perturbations have shown promise in certifyling UTPs, but masking only adversarial words can eliminate the attack.
Approach:	They propose a method to certify a language model’s robustness against UTPs by using random smoothing.
Outcome:	The proposed method achieves high certified accuracy under extensive masking and achieves state-of-the-art results in multiple settings.

Copied to clipboard

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

Explainability & Interpretability in NLP

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

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)

Copied to clipboard

Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li

Programming Languages in NLP

Challenge:	In-context learning of large-language models has achieved remarkable success in the field of natural language processing . however, the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL.
Approach:	They propose a workflow paradigm method to enhance the attention and problem-solving scope of large-language models through decomposition.
Outcome:	The proposed method outperforms existing methods on three datasets and improves the upper limit of LLM-based approaches.

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

Copied to clipboard

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

Low-Hallucination and Efficient Coreference Resolution with LLMs (2025.findings-emnlp)

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

Copied to clipboard

Yujian Gan, Yuan Liang, Jinxia Xie, Yanni Lin, Juntao Yu, Massimo Poesio

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models (2024.acl-long)

Challenge:	Large Language Models have shown promising results in coreference resolution, but they face a critical issue: hallucinations.
Approach:	They propose a low-hallucination and efficient solution to the problem of hallucinations . they propose efficient constrained decoding for coreference resolution .
Outcome:	The proposed approach achieves better performance on the English OntoNotes development set.

Copied to clipboard

Damai Dai, Chengqi Deng, Chenggang Zhao, R.x. Xu, Huazuo Gao, Deli Chen, Jiashi Li, Wangding Zeng, Xingkai Yu, Y. Wu, Zhenda Xie, Y.k. Li, Panpan Huang, Fuli Luo, Chong Ruan, Zhifang Sui, Wenfeng Liang

Why Multi-Interest Fairness Matters: Hypergraph Contrastive Multi-Interest Learning for Fair Conversational Recommender System (2025.findings-acl)

Challenge:	Mixture-of-Experts (MoE) architectures face challenges in ensuring expert specialization . despite the promising performance, scaling language models to an extremely large scale is associated with exceedingly high computational costs.
Approach:	They propose an architecture that allows for ultimate expert specialization by segmenting experts into mN ones and activating mK from them.
Outcome:	The proposed architecture achieves comparable performance with GShard with 2B parameters and computation.

Copied to clipboard

Yongsen Zheng, Zongxuan Xie, Guohua Wang, Ziyao Liu, Liang Lin, Kwok-Yan Lam

Retrieval Augmented Instruction Tuning for Open NER with Large Language Models (2025.coling-main)

Challenge:	Unfairness is a well-known challenge in Recommender Systems (RSs) some approaches have started to improve fairness in offline or static contexts, but it often exacerbates over time, leading to significant problems like the Matthew effect, filter bubbles, and echo chambers.
Approach:	They propose a framework to promote multi-interest diversity fairness in RSs by establishing diverse hypergraphs through contrastive learning.
Outcome:	The proposed framework achieves state-of-the-art performance while effectively alleviating unfairness in two CRS-based datasets.

Copied to clipboard

Tingyu Xie, Jian Zhang, Yan Zhang, Yuanyuan Liang, Qi Li, Hongwei Wang

EmoS: A High-Fidelity Multimodal Benchmark for Fine-grained Streaming Emotional Understanding (2026.acl-long)

Challenge:	Existing studies have focused on integrating large language models (LLMs) with information extraction (IE) however, the best approach to incorporate information with LLMs for IE remains an open question.
Approach:	They propose to use a Chinese IT dataset to perform RA-IT for IE . they use semantically similar examples from the training dataset as the context .
Outcome:	The proposed approach is evaluated in English and Chinese scenarios.

Copied to clipboard

Pengze Guo, Jingxi Liang, Zhiwen Xie, Qifeng Wang, Derek F. Wong

Memp: Exploring Agent Procedural Memory (2026.findings-acl)

Challenge:	Existing benchmarks fail to achieve ecological validity, signal clarity, and reliable fine-grained labeling in multimodal Emotion Recognition (MER) Existing datasets lack spontaneity of real-life interactions, resulting in poor quality and inconsistent data quality.
Approach:	They propose a bilingual benchmark to resolve limitations of ecological validity and noise in existing datasets by combining strictly filtered static slices with a dynamic Streaming Monologue subset.
Outcome:	EmoS provides trusted ground truth that captures continuous emotional evolution.

Copied to clipboard

Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Challenge:	Large Language Models (LLMs) based agents suffer from brittle procedural memory that is manually engineered or entangled in static parameters.
Approach:	They propose a procedural-memory repository that distills past agent trajectories into fine-grained, step-by-step instructions and higher-level, script-like abstractions.
Outcome:	The proposed repository can be used to improve agents' performance on travelplanner and Alfworld.

MaCSC: Towards Multimodal-augmented Pre-trained Language Models via Conceptual Prototypes and Self-balancing Calibration (2024.naacl-long)

Copied to clipboard

Xianwei Zhuang, Zhichang Wang, Xuxin Cheng, Yuxin Xie, Liming Liang, Yuexian Zou

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)

Challenge:	Existing approaches to training pre-trained language models (PLMs) focus on static image modality; inevitably encounter modality gaps and noise; and treat all modalities.
Approach:	They propose a multimodal-augmented framework that can infuse multimodal semantics into PLMs and facilitate a self-balancing calibration of information allocation.
Outcome:	The proposed framework outperforms baselines on multiple NLP tasks and outperformed existing frameworks.

Copied to clipboard

Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen

Speech & Audio in NLP

Challenge:	a new spoken dialogue system with single-stage training is demonstrating its low latency and high quality . SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens .
Approach:	They propose a timbre-controllable, end-to-end voice interaction system with single-stage training.
Outcome:	The proposed system outperforms previous models on 4 GPUs with limited data.

LLM Agents for Education: Advances and Applications (2025.findings-emnlp)

Copied to clipboard

Zhendong Chu, Shen Wang, Jian Xie, Tinghui Zhu, Yibo Yan, Jingheng Ye, Aoxiao Zhong, Xuming Hu, Jing Liang, Philip S. Yu, Qingsong Wen

VulLibGen: Generating Names of Vulnerability-Affected Packages via a Large Language Model (2024.acl-long)

Challenge:	Large Language Model (LLM) agents are transforming education by automating complex tasks and enhancing both teaching and learning processes.
Approach:	This survey analyzes recent advances in applying Large Language Model agents to educational settings . it highlights ethical issues, hallucination and overreliance, and integration with existing ecosystems .
Outcome:	The authors analyze the technologies enabling LLM agents and highlight key challenges in deploying them in educational settings.

Copied to clipboard

Tianyu Chen, Lin Li, ZhuLiuchuan ZhuLiuchuan, Zongyang Li, Xueqing Liu, Guangtai Liang, Qianxiang Wang, Tao Xie

From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks (2025.naacl-long)

Challenge:	Existing work on affected package identification is limited by large language models . a recent study shows that 84% third-party packages contain security vulnerabilities .
Approach:	They propose a method to use LLM to generate the affected package . they propose supervised fine-tuning, retrieval augmented generation and a local search algorithm .
Outcome:	The proposed method has an average precision of 0.806 for identifying vulnerable packages in four most popular ecosystems in GitHub Advisory.

Copied to clipboard

Xiaofeng Zhang, Yihao Quan, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye

CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Challenge:	Large visionlanguage models (LVLMs) are a powerful visual-language reasoning tool.
Approach:	They propose to integrate attention analysis with LLaVA-CAM to determine interactions between visual representations.
Outcome:	The proposed approach can be used to determine interactions between visual representations.

Copied to clipboard

Liang Xu, Hai Hu, Xuanwei Zhang, Lu Li, Chenjie Cao, Yudong Li, Yechen Xu, Kai Sun, Dian Yu, Cong Yu, Yin Tian, Qianqian Dong, Weitang Liu, Bo Shi, Yiming Cui, Junyi Li, Jun Zeng, Rongzhao Wang, Weijian Xie, Yanting Li, Yina Patterson, Zuoyu Tian, Yiwen Zhang, He Zhou, Shaoweihua Liu, Zhe Zhao, Qipeng Zhao, Cong Yue, Xinrui Zhang, Zhengliang Yang, Kyle Richardson, Zhenzhong Lan

Challenge:	Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach:	They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome:	The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .

Unsupervised Preference-Aware Language Identification (2022.findings-acl)

Copied to clipboard

Xingzhang Ren, Baosong Yang, Dayiheng Liu, Haibo Zhang, Xiaoyu Lv, Liang Yao, Jun Xie

Information Extraction & Text Mining

Challenge:	Existing studies do not consider inter-personal variations due to the lack of user annotated training data.
Approach:	They propose to use user preferences to identify ambiguous texts in multilingual applications without user annotated training data to build a preference-aware LID model.
Outcome:	The proposed model significantly outperforms existing LID systems on handling ambiguous texts.

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

Copied to clipboard

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

Revisiting the Negative Data of Distantly Supervised Relation Extraction (2021.acl-long)

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

Copied to clipboard

Chenhao Xie, Jiaqing Liang, Jingping Liu, Chengsong Huang, Wenhao Huang, Yanghua Xiao

Information Extraction & Text Mining

Challenge:	Existing methods for relation extraction with distant supervision generate plenty of training samples but noisy labels and imbalanced training data cause problems.
Approach:	They propose a method that automatically labels a sentence with relational triples from a knowledge base.
Outcome:	The proposed method outperforms existing methods even with false positive samples.

Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization (2024.lrec-main)

Copied to clipboard

Linzhi Wu, Xingyu Zhang, Yakun Zhang, Changyan Zheng, Tiejun Liu, Liang Xie, Ye Yan, Erwei Yin

Agent Trading Arena: A Study on Numerical Understanding in LLM-Based Agents (2025.findings-emnlp)

Challenge:	Lip reading is a process of interpreting silent speech from visual lip movements . but lip reading in cross-speaker scenarios poses a challenging problem due to inter-speech variability .
Approach:	They propose to exploit lip landmark-guided visual clues instead of mouth-cropped images as input features.
Outcome:	Experimental results show that the proposed approach reduces speaker-specific appearance characteristics in cross-speaker scenarios.

Copied to clipboard

Tianmi Ma, Jiawei Du, Wenxin Huang, Wenjie Wang, Liang Xie, Xian Zhong, Joey Tianyi Zhou

SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling (2020.emnlp-main)

Challenge:	Existing approaches to large language models are limited to historical backtesting and static data.
Approach:	a new large-language model is developed to simulate real-time trading in a virtual stock market . the agent trading arena simulates real-world bid-ask interactions and provides real-life trading scenarios .
Outcome:	The Agent Trading Arena simulates real-world market conditions and directly impacts price dynamics.

Copied to clipboard

Di Wu, Liang Ding, Fan Lu, Jian Xie

Sentiment Analysis

Challenge:	Slot filling and intent detection are two main tasks in spoken language understanding systems.
Approach:	They propose a non-autoregressive slot filling model with two-pass iteration mechanism to handle uncoordinated slots problem.
Outcome:	The proposed model significantly outperforms previous models in slot filling task while speeding up decoding.

Toward Human-Like Evaluation for Natural Language Generation with Error Analysis (2023.acl-long)

Copied to clipboard

Qingyu Lu, Liang Ding, Liping Xie, Kanjian Zhang, Derek F. Wong, Dacheng Tao

DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)

Challenge:	Pre-trained language models (PLMs) have been used to evaluate language generation tasks . pretrained error analysis can be used to refine the generated sentence toward higher confidence .
Approach:	They propose to combine pretrained language model based metrics with human-like error analysis to improve sentence confidence.
Outcome:	The proposed method outperforms top-scoring metrics in 19/25 settings.

Copied to clipboard

Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang

PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling (2024.acl-long)

Challenge:	Recent advances in neural theorem-proving resort to large language models and tree searches.
Approach:	They propose a Dynamic-Tree Driven Theorem Solver to accommodate general theoremes by guiding the search procedure with state confidence and proof-level values.
Outcome:	The proposed method outperforms state-of-the-art methods on two popular theorem-proving datasets with a 6.65% improvement on average in terms of success rate.

Copied to clipboard

Xianwei Zhuang, Xuxin Cheng, Liming Liang, Yuxin Xie, Zhichang Wang, Zhiqi Huang, Yuexian Zou

Robustness in NLP

Challenge:	Spoken language understanding (SLU) suffers from error propagation from automatic speech recognition (ASR) in actual scenarios.
Approach:	They propose a framework which calibrates bias and errors and achieves adaptive-balanced decoupling training by a prototype-based loss model.
Outcome:	The proposed framework outperforms existing approaches and achieves state-of-the-art performance on three datasets.

Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)

Copied to clipboard

Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu

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

Challenge:	Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations.
Approach:	They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability.
Outcome:	The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants .

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Information Retrieval

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

Green & Sustainable NLP

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation (2022.findings-naacl)

Copied to clipboard

Huan Lin, Baosong Yang, Liang Yao, Dayiheng Liu, Haibo Zhang, Jun Xie, Min Zhang, Jinsong Su

Multilinguality

Challenge:	Existing diverse NMT models lack translation diversity due to a discrepancy between training and inference . despite the success of diverse NTM, there is still a lack of translation diversity .
Approach:	They propose a multi-candidate optimization framework for diverse NMT to deal with this defect.
Outcome:	The proposed framework is transparent to basic diverse NMT models, and universally makes better trade-off between diversity and quality.

Causality-aware Concept Extraction based on Knowledge-guided Prompting (2023.acl-long)

Copied to clipboard

Siyu Yuan, Deqing Yang, Jinxi Liu, Shuyu Tian, Jiaqing Liang, Yanghua Xiao, Rui Xie

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning (2025.acl-long)

Challenge:	Concepts in knowledge graphs (KGs) are far from complete in existing knowledge graph models.
Approach:	They propose to equip a PLM-based extractor with a knowledge-guided prompt to alleviate concept bias by removing spurious co-occurrence correlations from existing knowledge.
Outcome:	The proposed prompt can alleviate concept bias and improve the performance of existing models.

Copied to clipboard

Chenxi Huang, Shaotian Yan, Liang Xie, Binbin Lin, Sinan Fan, Yue Xin, Deng Cai, Chen Shen, Jieping Ye

Tool learning via Inference-time Scaling and Cycle Verifier (2025.findings-acl)

Challenge:	Representation Fine-tuning (ReFT) is a proposed method for improving parameter efficiency . however, it yields suboptimal performance, as fixed-position representations have uncertain impact on outputs .
Approach:	They propose a method that fine-tunes critical representations in a low-rank linear subspace while freezing the base model.
Outcome:	The proposed method improves accuracy of LLaMA-2-7B and ReFT by 18.2 and 3.8 on GSM8K.

Copied to clipboard

Xiaobo Liang, Wenjin Xie, Juntao Li, Wanfu Wang, Yibin Chen, Kehai Chen, Min Zhang

Challenge:	In inference-time scaling, Chain-of-Thought (CoT) data is scarce or even unavailable.
Approach:	They propose a method which establishes an inference cycle to synthesize user queries and CoT data.
Outcome:	The proposed method achieves a 75.4% pass rate and a 79.6% win rate using small models in StableToolBench.

Game on Tree: Visual Hallucination Mitigation via Coarse-to-Fine View Tree and Game Theory (2024.emnlp-main)

Copied to clipboard

Xianwei Zhuang, Zhihong Zhu, Zhanpeng Chen, Yuxin Xie, Liming Liang, Yuexian Zou

Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning (2026.findings-acl)

Challenge:	Large vision-language models produce unfaithful visual hallucinations, also known as visual halluinations, which hinders their application in multimodal understanding and decision-making.
Approach:	They propose a plug-and-play train-free decoding algorithm for mitigating visual hallucinations . they leverage visual information to construct a coarse-to-fine visual view tree .
Outcome:	The proposed algorithm reduces visual hallucinations (VH) by leveraging visual information to construct a coarse-to-fine visual view tree (CFTree)

Copied to clipboard

Yongcan Yu, Lingxiao He, Jian Liang, Kuangpu Guo, Meng Wang, Qianlong Xie, Xingxing Wang, Ran He

ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors (2025.acl-long)

Challenge:	a framework to mitigate spurious optimization signals is proposed for test-time reinforcement learning (TTRL) Reinforcement learning with verifiable rewards (RLVR) is an effective paradigm for improving large language models on structured challenging reasoning tasks.
Approach:	They propose a framework to mitigate spurious optimization signals from label noise . they propose to use a frequency-based sampling strategy to exclude ambiguous samples .
Outcome:	The proposed framework outperforms existing TTRL baselines on three large language models across multiple mathematical reasoning benchmarks.

Copied to clipboard

Yuguo Yin, Yuxin Xie, Wenyuan Yang, Dongchao Yang, Jinghan Ru, Xianwei Zhuang, Liming Liang, Yuexian Zou

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)

Challenge:	Existing multilingual audio-text retrieval schemes suffer from inconsistencies for instance similarity matching across languages.
Approach:	They propose a multilingual audio-text retrieval scheme that mitigates the impact of data distribution error on recall and consistency.
Outcome:	The proposed scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English.

Copied to clipboard

Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang

Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation (2026.acl-long)

Challenge:	Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive.
Approach:	They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory .
Outcome:	The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient.

Copied to clipboard

Hengyuan Zhang, Shiping Yang, Xiao Liang, Chenming Shang, Yuxuan Jiang, Chaofan Tao, Jing Xiong, Hayden Kwok-Hay So, Ruobing Xie, Angel X. Chang, Ngai Wong

APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation (2026.findings-acl)

Challenge:	Existing studies show that stronger models are not always optimal teachers, suggesting a mismatch between the teacher’s output and the student’s learning ability.
Approach:	They propose a method that routes each prompt to its optimal teacher via a query-level router that jointly considers the student models’ learnability and teacher models’ response quality.
Outcome:	The proposed method outperforms baselines on six benchmarks including instruct tuning and math reasoning settings.

Copied to clipboard

Dongliang Chen, Xinlin Zhuang, Junjie Xu, Luojian Xie, Zehui Wang, Jiaxi Zhuang, Haolin Yang, Liang Dou, Xiao He, Xingjiao Wu, Ying Qian

Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers (2024.acl-long)

Challenge:	APEX optimizes for text-to-image generation by combining learning potential, conflict penalty, and progress need.
Approach:	They propose an algorithm that stabilizes heterogeneous rewards and dynamically schedules objectives . they propose a method that achieves better Pareto trade-offs across four heterogenous objectives based on P3 Adaptive Priorities .
Outcome:	The proposed algorithm achieves better pareto trade-offs across four heterogeneous objectives while maintaining competitive OCR accuracy.

Copied to clipboard

Jiawen Xie, Pengyu Cheng, Xiao Liang, Yong Dai, Nan Du

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Challenge:	Existing transformer-based models struggle with long-sequence processing due to computational costs . a framework to enhance long-content processing of transformers is proposed .
Approach:	They propose a framework to enhance long-sequence processing of transformers by three steps . they demonstrate that the framework significantly outperforms prior long-quence processors .
Outcome:	The proposed framework outperforms baseline models on long-sequence summarization and reading comprehension tasks.

Copied to clipboard

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen

Challenge:	a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach:	They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome:	The proposed benchmarks show that the current models perform worse than the human ceiling.

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement (2025.acl-short)

Copied to clipboard

Runnan Fang, Xiaobin Wang, Yuan Liang, Shuofei Qiao, Jialong Wu, Zekun Xi, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

Challenge:	Using Large Language Models (LLMs)-based agents can enhance their understanding of environments and tasks.
Approach:	They propose a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search exploration to refine their action knowledge in the current environment.
Outcome:	The proposed framework synthesizes possible scenarios with multi-step action invocation within the action space and performs Monte Carlo Tree Search exploration to refine action knowledge in the current environment.

Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG (2025.acl-long)

Copied to clipboard

Xin Sun, Jianan Xie, Zhongqi Chen, Qiang Liu, Shu Wu, Yuehe Chen, Bowen Song, Zilei Wang, Weiqiang Wang, Liang Wang

Information Retrieval

Challenge:	Large language models (LLMs) augmented with retrieval systems have significantly advanced natural language processing tasks by integrating external knowledge sources.
Approach:	They propose a method that conditions large language models to generate answers even in the absence of reliable knowledge.
Outcome:	The proposed approach balances accuracy with appropriate abstention, enhancing the reliability and trustworthiness of retrieval-augmented systems.

Better Pre-Training by Reducing Representation Confusion (2023.findings-eacl)

Copied to clipboard

Haojie Zhang, Mingfei Liang, Ruobing Xie, Zhenlong Sun, Bo Zhang, Leyu Lin

Concise and Organized Perception Facilitates Reasoning in Large Language Models (2025.findings-naacl)

Challenge:	Existing methods to improve pre-trained language models address information confusion in position encoding and model representations.
Approach:	They propose two techniques to improve pre-trained language models by decoupling directions and auxiliary regularizers.
Outcome:	The proposed techniques can improve pre-trained language models on GLUE benchmarks.

Copied to clipboard

Junjie Liu, Shaotian Yan, Chen Shen, Zhengdong Xiao, Liang Xie, Wenxiao Wang, Jieping Ye

From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning (2025.findings-acl)

Challenge:	Extensive experimental results on several popular logical benchmarks (ProofWriter, PrOntoQA, PrONtoQA-OOD, and FOLIO) and mathematical benchmark (DI-GSM) show that COP significantly outperforms previous state-of-the-art methods.
Approach:	They propose a reasoning approach called Concise and Organized Perception (COP) that carefully analyzes the given statements to identify the most pertinent information while eliminating redundancy efficiently.
Outcome:	The proposed approach outperforms state-of-the-art methods on several popular logical benchmarks and mathematical benchmarks.

Copied to clipboard

Wenjing Xie, Xiaobo Liang, Juntao Li, Wanfu Wang, Kehai Chen, Qiaoming Zhu, Min Zhang

BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning (2024.findings-acl)

Challenge:	Existing approaches enhance reasoning through Chain-of-Thought, Program-ofThough, and Tool-Integration.
Approach:	They propose a tool-awareness training method that leverages both forward and backward data generation strategies to strengthen the model’s conscious and selective tool utilization in multi-step reasoning tasks.
Outcome:	The proposed method improves the model's tool utilization capabilities, including proactivity and execution success rates.

Copied to clipboard

Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, Rui Yan

Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema (2025.coling-main)

Challenge:	BioT5+ is an extension of the BioT5, but lacked a nuanced understanding of molecular structures.
Approach:	They propose a new bio-entity modeling framework, BioT5+, which integrates IUPAC names and molecule data.
Outcome:	The proposed model bridges the gap between molecular representations and textual descriptions and improves the grounded reasoning of bio-text and bio-sequences.

Copied to clipboard

Jie Shi, Bo Xu, Jiaqing Liang, Yanghua Xiao, Jia Chen, Chenhao Xie, Peng Wang, Wei Wang

Programming Languages in NLP

Challenge:	Recent studies have shifted paradigms and leveraged Large Language Models (LLMs) to tackle the challenging task of Text-to-SQL.
Approach:	They propose a framework that leverages large language models to generate SQL queries . they exploit prior knowledge from the LLM to enhance embedding-based retriever .
Outcome:	The proposed method improves embedding-based retriever and reduces cost.

Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues (2026.acl-long)

Copied to clipboard

Muhammad Dehan Al Kautsar, Saeed Almheiri, Momina Ahsan, Bilal Elbouardi, Younes Samih, Sarfraz Ahmad, Amr Keleg, Omar El Herraoui, Kareem Elzeky, Abed Alhakim Freihat, Mohamed Anwar, Zhuohan Xie, Junhong Liang, Mohammad Rustom Al Nasar, Preslav Nakov, Fajri Koto

Dialogue Systems & Conversational Agents

Challenge:	Most benchmarks focus on short text snippets in Modern Standard Arabic (MSA), overlooking cultural nuances that naturally arise in dialogues.
Approach:	They propose a culturally grounded conversational dataset covering 13 Arabic-speaking countries, in both Modern Standard Arabic (MSA) and each country’s respective dialect, spanning 12 daily-life topics and 54 fine-grained subtopics.
Outcome:	The proposed model performs worse on all three tasks than the MSA benchmark.

LLEOT: A Privacy-Enhancing Offsite Tuning Framework via Loss Landscape Elevation (2026.findings-acl)

Copied to clipboard

Jin Zhong, Jinglin Liang, Tongtong Yang, Zijian Xie, Shuangping Huang, Hanlin Gu

Generalizable and Stable Finetuning of Pretrained Language Models on Low-Resource Texts (2024.naacl-long)

Challenge:	Existing approaches to fine-tune large language models are infeasible due to privacy regulations.
Approach:	They propose an offsite tuning framework that secures data privacy and model parameter and capability privacy.
Outcome:	The proposed framework secures data privacy and model parameter and capability privacy while preserving gradient alignment.

Copied to clipboard

Sai Ashish Somayajula, Youwei Liang, Li Zhang, Abhishek Singh, Pengtao Xie