Papers by Xue Li

Transition-Based Chinese AMR Parsing (N18-2)

Challenge:	Existing benchmarks rely heavily on text-based evaluation and largely ignore paralinguistic cues such as prosody, emotion, and speaker traits.
Approach:	They propose a speech-native benchmark for evaluating instruction-following S2S models with explicit assessment of both semantic understanding and paralinguistic expression.
Outcome:	The proposed system enables more natural, robust, and human-aligned speech agents.

Copied to clipboard

Chuan Wang, Bin Li, Nianwen Xue

Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities (2025.findings-acl)

Challenge:	Abstract Meaning Representation (AMR) is a semantic representation where the meaning of a sentence is encoded as a rooted, directed and acyclic graph.
Approach:	They propose a transition-based AMR parsing framework for Chinese to be used in the next generation of AMR.
Outcome:	The proposed parser is based on the Chinese AMR bank.

Copied to clipboard

Wenyue Hua, Kaijie Zhu, Lingyao Li, Lizhou Fan, Mingyu Jin, Shuhang Lin, Haochen Xue, Zelong Li, Jindong Wang, Yongfeng Zhang

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval (2026.findings-acl)

Challenge:	Using large language models, large language model models can be used to evaluate reasoning abilities in context-rich scenarios.
Approach:	They construct datasets for both propositional logic and abductive logic reasoning with four difficulty levels across 12 distinct domains based on Wikipedia categorization and those with purely abstract variables.
Outcome:	The proposed model can be used to benchmark LLMs in real-world scenarios, but not in context-rich scenarios.

Copied to clipboard

Xin Xie, Dongyun Xue, Wuguannan Yao, Mingxiao Feng, Wengang Zhou, Xiang Qi, Houqiang Li, Peng Zhang

CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending (2024.acl-long)

Challenge:	a new framework casts LLM planning as non-parametric retrieval, but high latency of inference-time search and supervised fine-tuning are limitations.
Approach:	They propose a framework that casts LLM planning as non-parametric retrieval . they leverage Monte Carlo Tree Search to explore the solution space .
Outcome:	Empirical results show that SGA-MCTS can match the performance of SOTA systems without task-specific fine-tuning.

Copied to clipboard

Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue, Qi Zhang, Yifan Wu, Jianguo Li

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models (2026.findings-acl)

Challenge:	Existing models that use self-attention and position embedding have anomalous behavior that hinder long context window extrapolation.
Approach:	They propose a collinear constraint between Q and K to integrate RoPE and self-attention.
Outcome:	The proposed model integrates self-attention and position embedding into LLMs without fine-tuning.

Copied to clipboard

Canhui Wu, Qiong Cao, Chang Li, Zhenfang Wang, Chao Xue, Yuwei Fan, Wei Xi, Xiaodong He

How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026.acl-industry)

Challenge:	Existing reinforcement learning methods for large reasoning models suffer from excessive verbosity, known as "overthinking." Existing models penalize generated tokens to promote conciseness, but these methods encounter two challenges: they may develop hacking behavior in later stages of training by discarding reasoning steps.
Approach:	They propose a framework that steers large reasoning models toward more efficient reasoning . they prioritize correctness while imposing penalties for redundant steps .
Outcome:	The proposed framework reduces token usage by 69.7% on AIME24.

Copied to clipboard

Yongqi Tong, Xiaoyun Feng, Lyuxin Xue, Jianshe Li, Xin Zhang, Jiang-Ming Yang

Challenge:	Traditional industrial agents rely on modular workflows that fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency.
Approach:	They propose a paradigm shift from external workflows to internalized knowledge representation that consolidates complex business logic and SOPs directly into the model’s parameters.
Outcome:	The proposed model breaks the impossible triangle of latency, accuracy, and complexity.

A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech (2021.acl-long)

Copied to clipboard

Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Nianwen Xue, Ji-Rong Wen

KEHRL: Learning Knowledge-Enhanced Language Representations with Hierarchical Reinforcement Learning (2024.lrec-main)

Challenge:	Existing work regards dropped pronoun recovery and conversational discourse parsing as two separate tasks and tackles them separately.
Approach:	They propose a neural model for dropped pronoun recovery and conversational discourse parsing in Chinese conversational speech.
Outcome:	The proposed model outperforms the state-of-the-art models on a new dataset . the proposed model is based on linguistic and semantic information from Chinese conversational speech .

Copied to clipboard

Dongyang Li, Taolin Zhang, Longtao Huang, Chengyu Wang, Xiaofeng He, Hui Xue

Advancing Collaborative Debates with Role Differentiation through Multi-Agent Reinforcement Learning (2025.acl-long)

Challenge:	General pre-trained language models (PLMs) leverage relation triples from knowledge graphs (KGs) and integrate external data sources into language models via self-supervised learning.
Approach:	They propose to learn Knowledge-Enhanced language representations with Hierarchical Reinforcement Learning (KEHRL) to detect positions for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge.
Outcome:	The proposed model can detect essential positions in texts for knowledge injection and integrate external knowledge into the model to avoid injecting inaccurate or irrelevant knowledge.

Copied to clipboard

Haoran Li, Ziyi Su, Yun Xue, Zhiliang Tian, Yiping Song, Minlie Huang

Representation Learning

Challenge:	Multi-agent collaborative tasks exhibit exceptional capabilities in natural language applications and generation.
Approach:	They propose a multi-LLM Cooperation framework with automatic role assignment capabilities that allows multiple agents to embed roles in turn-based speaking.
Outcome:	The proposed framework improves collaboration and expertise among agents and teams by enabling them to share roles and develop complementary strengths from the optimization level.

Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation (2025.acl-long)

Copied to clipboard

Senyu Li, Zipeng Sun, Jiayi Wang, Xue Liu, Pontus Stenetorp, Siva Reddy, David Ifeoluwa Adelani

Semantics-Aware Dual Graph Convolutional Networks for Argument Pair Extraction (2024.lrec-main)

Challenge:	Existing supervised fine-tuning (SFT) methods focus on directly generating the target output without leveraging the benefits of intermediate steps or initial guidance.
Approach:	They propose a task-agnostic framework that enables models to generate intermediate "warmup" sequences that are iteratively refined to maximize their contribution to the final output.
Outcome:	The proposed framework outperforms traditional supervised fine-tuning methods on translation, summarization, and multi-choice question answering tasks.

Copied to clipboard

Minzhao Guan, Zhixun Qiu, Fenghuan Li, Yun Xue

Structured Data in NLP

Challenge:	Argument pair extraction (APE) aims to extract interactive argument pairs from two separate passages.
Approach:	They propose to tackle the lexical and semantic relevance of arguments with a pre-trained Rouge-guided Transformer (ROT) by using a word graph and a gating mechanism to fuse two graphs.
Outcome:	The proposed approach achieves state-of-the-art on F1 score and significantly improves on existing best alternative.

Sequence Parallelism: Long Sequence Training from System Perspective (2023.acl-long)

Copied to clipboard

Shenggui Li, Fuzhao Xue, Chaitanya Baranwal, Yongbin Li, Yang You

MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation (2025.acl-long)

Challenge:	Existing work on memory-efficient parallelisms to reduce time and space complexity focuses on reducing time and complexity from system perspective.
Approach:	They propose a memory-efficient parallelism to reduce time and space complexity . they split input sequence into multiple chunks and feed each chunk into GPU .
Outcome:	The proposed approach is compatible with most existing parallelisms and makes 4D parallelismal possible.

Copied to clipboard

Haochen Xue, Feilong Tang, Ming Hu, Yexin Liu, Qidong Huang, Yulong Li, Chengzhi Liu, Zhongxing Xu, Chong Zhang, Chun-Mei Feng, Yutong Xie, Imran Razzak, Zongyuan Ge, Jionglong Su, Junjun He, Yu Qiao

Natural Language Interfaces

Challenge:	Existing multimodal large language models lack the ability to memorize, recall, and reason in sustained interactions.
Approach:	They propose a multimodal real-world conversation benchmark for evaluating open-ended abilities of multimodal large language models.
Outcome:	The proposed benchmarks show that the models perform better in open-ended conversations.

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

PACE: Improving Prompt with Actor-Critic Editing for Large Language Model (2024.findings-acl)

Challenge:	Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases.
Approach:	They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases.
Outcome:	The proposed framework synthesizes more generalized training data to address these model weaknesses.

Copied to clipboard

Yihong Dong, Kangcheng Luo, Xue Jiang, Zhi Jin, Ge Li

VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction (2025.coling-main)

Challenge:	Prompt with Actor-Critic Editing (PACE) for LLMs improves performance of different human-written prompts, resulting in significant performance discrepancies.
Approach:	They propose to use LLMs as actors and critics to enable automatic prompt editing by taking feedback from both actors performing prompt and criticizing response into account.
Outcome:	The proposed model improves the performance of human-written prompts by 98% and compares to high-quality human-writing prompts.

Copied to clipboard

Khai Phan Tran, Wen Hua, Xue Li

Information Extraction & Text Mining

Challenge:	Existing methods for Document-level Relation Extraction assume a uniform label distribution, resulting in suboptimal performance on real-world, imbalanced datasets.
Approach:	They propose a method that leverages the Variational Autoencoder architecture to capture all relation-wise distributions formed by entity pair representations and augment data for underrepresented relations.
Outcome:	The proposed method outperforms state-of-the-art models on two benchmark datasets and is available on github.

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback (2026.findings-acl)

Copied to clipboard

Yutao Mou, Zhangchi Xue, Lijun Li, Peiyang Liu, Shikun Zhang, Wei Ye, Jing Shao

From What to Why: Improving Relation Extraction with Rationale Graph (2021.findings-acl)

Challenge:	Unlike chatbots, autonomous agents act directly on external environments, making tool invocation safety critical for reliable deployment.
Approach:	They develop a benchmark for step-level tool invocation safety detection in LLM agents and a guardrail model that proactively detects unsafe tool invoking actions before execution using multi-task reinforcement learning.
Outcome:	The proposed model reduces harmful tool invocations of ReAct-style agents by 65% on average and improves benign task completion by 10% under prompt injection attacks.

Copied to clipboard

Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Xue Mengge, Tingwen Liu, Li Guo

Information Extraction & Text Mining

Challenge:	Existing neural relation extraction models are limited by entity type and textual context.
Approach:	They propose a novel RAtionale Graph to organize co-occurrence constraints among entity types, triggers and relations in a holistic graph view.
Outcome:	The proposed method outperforms baselines significantly and achieves state-of-the-art performance on document-level and sentence-level RE benchmarks.

M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis (2025.emnlp-main)

Copied to clipboard

ChengYan Wu, Bolei Ma, Yihong Liu, Zheyu Zhang, Ningyuan Deng, Yanshu Li, Baolan Chen, Yi Zhang, Yun Xue, Barbara Plank

Multilinguality

Challenge:	Existing studies focus on English-centric aspects of sentiment analysis, limiting scope for multilingual evaluation and research.
Approach:	They propose to use a multilingual dataset to analyze aspects with associated sentiment elements in text.
Outcome:	The proposed dataset is the most extensive multilingual parallel dataset for ABSA to date.

Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation (2023.emnlp-main)

Copied to clipboard

Mingfeng Xue, Dayiheng Liu, Wenqiang Lei, Jie Fu, Jian Lan, Mei Li, Baosong Yang, Jun Xie, Yidan Zhang, Dezhong Peng, Jiancheng Lv

UNIMO-G: Unified Image Generation through Multimodal Conditional Diffusion (2024.acl-long)

Challenge:	Existing unsupervised paraphrase generation methods require large-scale, manually annotated paraphrase datasets, which are labor-intensive to build.
Approach:	They propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence.
Outcome:	The proposed method generates diverse pseudo-paraphrases in distinct surface structures for a given sentence.

Copied to clipboard

Wei Li, Xue Xu, Jiachen Liu, Xinyan Xiao

SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking (2026.acl-long)

Challenge:	Existing text-to-image diffusion models generate images from text prompts due to inherent brevity of textual descriptions . however, the ability to accurately synthesize images with intricate details, such as specific entities or scenes, is limited due to the inherent bribery of text descriptions.
Approach:	They propose a multimodal conditional diffusion framework that operates on multimodal prompts with interleaved textual and visual inputs.
Outcome:	The proposed framework excels in both text-to-image generation and zero-shot subject-driven synthesis.

Copied to clipboard

Yingjie Xue, Xingyou Xia, Jun Zhang, Yunbo Cao, Dengpan Ye, Guotong Geng, Fei Li

Universally Empowering Zeroth-Order Optimization via Adaptive Layer-wise Sampling (2026.findings-acl)

Challenge:	Existing methods for jailbreak ignore the semantic differences between categories of harmful questions, leading to inconsistent success rates and reduced overall attack effectiveness.
Approach:	They propose a category-aware jailbreak framework that incorporates the semantic category of harmful questions into prompt generation.
Outcome:	The proposed framework improves attack success rates and category alignment and achieves better cross-category robustness compared to the state-of-the-art (SOTA) baselines.

Copied to clipboard

Fei Wang, Li Shen, Liang Ding, Chao Xue, Ye Liu, Changxing Ding

Green & Sustainable NLP

Challenge:	Existing methods for fine-tuning Large Language Models are slow and lack of performance.
Approach:	They propose a Zeroth-Order optimization framework that uses forward passes to fine-tune Large Language Models.
Outcome:	The proposed framework achieves 1.7 to 3.0 wall-clock acceleration on LLaMA and OPT models.

Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations (2026.acl-long)

Copied to clipboard

Wentao Hu, Yanbo Zhai, Xiaohui Hu, Mingkuan Zhao, Shanhong yu, Xue Liu, Kaidong Yu, Shuangyong Song, Xuelong Li

Attention Consistency for LLMs Explanation (2025.findings-emnlp)

Challenge:	Sparse Mixture-of-Experts models are vulnerable to hallucinations, authors say . static Top-k routing leaves "specialist experts" under-prioritized for specific tokens .
Approach:	They propose a training-free inference framework to awaken dormant experts . they propose 'counterfactual routing' to shift computational resources from syntax-dominant to knowledge-intensive layers .
Outcome:	Experiments show that CoR improves factual accuracy by 3.1% without increasing the inference budget.

Copied to clipboard

Tian Lan, Jinyuan Xu, Xue He, Jenq-Neng Hwang, Lei Li

Explainability & Interpretability in NLP

Challenge:	Existing interpretability methods face limitations such as low resolution and high computational cost.
Approach:	They propose a multi-layer attention consistency score to estimate the importance of input tokens in large language models.
Outcome:	The proposed heuristic achieves a favorable trade-off between interpretability quality and computational efficiency .

Enhancing Advanced Visual Reasoning Ability of Large Language Models (2024.emnlp-main)

Copied to clipboard

Zhiyuan Li, Dongnan Liu, Chaoyi Zhang, Heng Wang, Tengfei Xue, Weidong Cai

LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contexts (2025.findings-emnlp)

Challenge:	Recent advances in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models’ advanced reasoning ability.
Approach:	They propose a novel multi-modal in-context learning methodology to enhance LLMs’ contextual understanding and reasoning.
Outcome:	The proposed model achieves SOTA performance among all visual reasoning tasks and achieves a 'higher level of accuracy' than previous models.

Copied to clipboard

Junhao Chen, Jingbo Sun, Xiang Li, Haidong Xin, Yuhao Xue, Yibin Xu, Hao Zhao

Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)

Challenge:	Large language models (LLMs) are increasingly important for their intelligence evaluation.
Approach:	They propose a game theory-based evaluation platform that measures LLMs’ decision-making strategies and social behaviors in classic game-theoretic settings.
Outcome:	The proposed system cross-evaluates 15 leading LLMs using leaderboard rankings and scoring mechanisms.

Copied to clipboard

Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang

Multilinguality

Challenge:	Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data.
Approach:	They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants.
Outcome:	The proposed approach improves performance across benchmarks and representation space.

Aspect Based Sentiment Analysis with Gated Convolutional Networks (P18-1)

Copied to clipboard

Wei Xue, Tao Li

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis can provide more detailed information than general sentiment analysis.
Approach:	They propose a model based on convolutional neural networks and gating mechanisms which can selectively output the sentiment features according to the given aspect or entity.
Outcome:	The proposed model can selectively output sentiment features according to the given aspect or entity.

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

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning (2026.findings-acl)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Juexiang Ye, Xue Li, Yang Xinyu, Chengkai Huang, Lanshun Nie, Lina Yao, Dechen Zhan

Information Retrieval

Challenge:	Existing methods rely on unstructured retrieval or coarse abstractions, which lead to temporal conflicts, brittle reasoning, and limited traceability.
Approach:	They propose a unified memory framework that consolidates long-term agent experiences into three interconnected components that combine structured knowledge and evidence to construct compact yet information-dense contexts for reasoning.
Outcome:	The proposed framework significantly improves multi-hop and temporal reasoning accuracy while reducing input context length by over 95% compared to long-context baselines.

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Haolei Xu, Haiwen Hong, Hongxing Li, Rui Zhou, Yang Zhang, Longtao Huang, Hui Xue, Yongliang Shen, Weiming Lu, Yueting Zhuang

START: Self-taught Reasoner with Tools (2025.emnlp-main)

Challenge:	Existing multimodal Mixture-of-Experts models accurately perceive image content yet fail in subsequent reasoning . Seeing but not thinking phenomenon is a puzzling phenomenon .
Approach:	They propose a routing-guided intervention method that enhances domain expert activation.
Outcome:	The proposed method achieves consistent improvements on visual reasoning tasks.

Copied to clipboard

Chengpeng Li, Mingfeng Xue, Zhenru Zhang, Jiaxi Yang, Beichen Zhang, Bowen Yu, Binyuan Hui, Junyang Lin, Xiang Wang, Dayiheng Liu

Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields (2020.findings-emnlp)

Challenge:	Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in complex reasoning through long chain-of-thought, yet they struggle with precise computations and algorithmic operations.
Approach:	They propose a training-free approach that activates LRMs’ latent tool-use capabilities through artificial hints and a framework that enables models to learn effective tool utilization through diverse hint patterns and rejection-based data synthesis.
Outcome:	Experiments show that START significantly improves state-of-the-art LRMs across challenging benchmarks, including competition-level mathematics (AMC23: 95.0%, AIME24: 75.6%) and graduate-level science questions (GPQA: 64.6%).

Copied to clipboard

Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Ji-Rong Wen, Nianwen Xue

CodeContests-O: Powering LLMs via Feedback-Driven Iterative Test Case Generation (2026.findings-acl)

Challenge:	Existing approaches to recover dropped pronouns ignore the dependencies between pronounes in neighboring utterances.
Approach:	They propose a framework that combines Transformer network and General Conditional Random Fields to model the dependencies between pronouns in neighboring utterances.
Outcome:	The proposed framework outperforms state-of-the-art models on three Chinese conversation datasets showing that it captures the dependencies between pronouns in neighboring utterances.

Copied to clipboard

Jianfeng Cai, Jinhua Zhu, Ruopei Sun, Kangwen Zhao, Dongyun Xue, Mingxiao Feng, Wengang Zhou, Houqiang Li

Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward (2026.findings-acl)

Challenge:	Existing approaches to synthesize test cases using Large Language Models (LLMs) rely on the model’s intrinsic generation capabilities without external feedback, resulting in insufficiently diverse cases.
Approach:	They propose a feedback-driven iterative framework that leverages Large Language Models to generate initial test cases, execute them against known correct and incorrect solutions, and utilizes the failed results as feedback to guide the LLM in refining the test cases toward high fidelity and discriminability.
Outcome:	The proposed method outperforms the existing codecontests and codecontests+ models by 4.30% and 8.78%.

Copied to clipboard

Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou

Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Recent studies show that RLVR training is slow and results plateau as policy entropy collapses . low-probability regularization (Lp-Reg) reduces the number of low-quality exploratory tokens induced by RL training .
Approach:	They propose a method to reduce RLVR over-penalization by eliminating low-probability exploratory tokens . they propose 'Low-provability Regularization' to reduce the gradual elimination of low-quality exploratory entropy tokens.
Outcome:	The proposed method eliminates low-probability exploratory tokens and prevents suppression of potentially valuable low-property candidates.

Copied to clipboard

Rui Qi, Fengran Mo, Yufeng Chen, Xue Zhang, Shuo Wang, Hongliang Li, Xu Jinan, Meng Jiang, Jian-Yun Nie, Kaiyu Huang

Multilinguality

Challenge:	Existing approaches to multilingual retrieval-augmented generation (MRAG) use a single-turn retrieval and subsequent optimization to acquire and integrate beneficial external knowledge from multilingual collections.
Approach:	They propose a multilingual search-augmented reinforcement learning framework that integrates a language-coupled Group Relative Policy Optimization into the policy and reward models.
Outcome:	The proposed framework achieves competitive performance and is appropriate for various practical scenarios such as constrained training data and retrieval over collections encompassing a large number of languages.

Meaning Representations for Natural Languages: Design, Models and Applications (2022.emnlp-tutorials)

Copied to clipboard

Jeffrey Flanigan, Ishan Jindal, Yunyao Li, Tim O’Gorman, Martha Palmer, Nianwen Xue

SparkRA: A Retrieval-Augmented Knowledge Service System Based on Spark Large Language Model (2024.emnlp-demo)

Challenge:	This tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation models.
Approach:	This tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation models.
Outcome:	This tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation models . it also reviews the applications of meaning representation in downstream NLP tasks and real-world applications .

Copied to clipboard

Dayong Wu, Jiaqi Li, Baoxin Wang, Honghong Zhao, Siyuan Xue, Yanjie Yang, Zhijun Chang, Rui Zhang, Li Qian, Bo Wang, Shijin Wang, Zhixiong Zhang, Guoping Hu

Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective (2025.findings-acl)

Challenge:	Large language models (LLMs) have shown remarkable achievements across various language tasks.
Approach:	They propose a scientific literature LLM and a knowledge service system based on it . they collect scientific literature and then pre-train it using autoregressive training .
Outcome:	The proposed system provides literature investigation, paper reading, and academic writing functions.

Copied to clipboard

Yipeng Kang, Junqi Wang, Yexin Li, Mengmeng Wang, Wenming Tu, Quansen Wang, Hengli Li, Tingjun Wu, Xue Feng, Fangwei Zhong, Zilong Zheng

Structured Data in NLP

Challenge:	Current approaches to value alignment focus on a few core values, such as helpfulness, harmlessness, and honesty.
Approach:	They propose to use latent causal value graphs to guide two lightweight value-steering methods . role-based prompting and sparse autoencoder (SAE) steering are also used .
Outcome:	Experiments on Gemma-2B-IT and Llama3-8B- IT show that the proposed methods are effective and controllable.

Section-Aware Commonsense Knowledge-Grounded Dialogue Generation with Pre-trained Language Model (2022.coling-1)

Copied to clipboard

Sixing Wu, Ying Li, Ping Xue, Dawei Zhang, Zhonghai Wu

Dialogue Systems & Conversational Agents

Challenge:	Pre-trained language models can be expected to deepen the fusing of dialogue context and knowledge because of their superior ability of semantic understanding.
Approach:	They propose a two-stage framework to integrate a linearized knowledge into plan text using a ranking network PriorRanking to estimate the relevance of a retrieved knowledge fact.
Outcome:	The proposed framework improves the performance of pre-trained language models by using section-aware strategies to encode the linearized knowledge.

SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition (2025.emnlp-main)

Copied to clipboard

Zechen Li, Shohreh Deldari, Linyao Chen, Hao Xue, Flora D. Salim

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	SensorLLM is a timeseries classification framework that can perform human activity recognition tasks.
Approach:	They propose a framework that enables Large Language Models to perform human activity recognition from sensor time-series data.
Outcome:	The proposed framework can perform human activity recognition (HAR) tasks with human inputs.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

A Unified Joint Approach with Topological Context Learning and Rule Augmentation for Knowledge Graph Completion (2024.findings-acl)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Jingtao Guo, Chunxia Zhang, Lingxi Li, Xiaojun Xue, Zhendong Niu

An LLM-based Framework for Biomedical Terminology Normalization in Social Media via Multi-Agent Collaboration (2025.coling-main)

Challenge:	Existing knowledge graph completion methods perform simple linear update on relation representation, and only local neighborhood information is aggregated, making it difficult to capture logic semantic between relations and global topological context information.
Approach:	They propose a joint approach with Topological Context learning and Rule Augmentation (TCRA) it uses a topological context learning mechanism and a relation rule context learning system .
Outcome:	The proposed approach performs better on three benchmark datasets and is widely used in knowledgeintensive applications.

Copied to clipboard

Yongqi Fan, Kui Xue, Zelin Li, Xiaofan Zhang, Tong Ruan

Ambiguity-aware Multi-level Incongruity Fusion Network for Multi-Modal Sarcasm Detection (2025.coling-main)

Challenge:	Experimental results indicate that our approach exhibits competitive performance.
Approach:	They propose a tuning-free approach to normalize non-standard terms using large language models . they use a search engine and a domain knowledge base to expand the short texts into accurate descriptions .
Outcome:	The proposed approach is based on the "Recall and Re-rank" framework . it can be used to identify the standard term in a specified termbase for non-standardized mentions .

Copied to clipboard

Kuntao Li, Yifan Chen, Qiaofeng Wu, Weixing Mai, Fenghuan Li, Yun Xue

D2R: Dual-Branch Dynamic Routing Network for Multimodal Sentiment Detection (2024.emnlp-main)

Challenge:	Existing methods for sarcasm detection focus on fusing text and image information to establish cross-modal correlations, overlooking the significance of original unimodal incongruity information.
Approach:	They propose a multi-modal incongruity learning module to capture inconcluity information simultaneously at the text-level, image-level and cross-modal-level.
Outcome:	The proposed model outperforms state-of-the-art methods on a publicly available dataset.

Copied to clipboard

Yifan Chen, Kuntao Li, Weixing Mai, Qiaofeng Wu, Yun Xue, Fenghuan Li

Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design (2026.findings-acl)

Challenge:	Existing methods for multimodal sentiment detection use the same fixed framework to classify the sentiment polarity of image-text pairs.
Approach:	They propose a multimodal dynamic interaction model that uses a fixed framework to classify the sentiment polarity of a given imagetext pair.
Outcome:	The proposed model outperforms state-of-the-art models on three publicly available datasets.

Copied to clipboard

Yuchen Li, Handing Wang, Bing Xue, Mengjie Zhang, Yaochu Jin

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification (2024.emnlp-main)

Challenge:	Existing approaches to translating ambiguous design requirements into a mathematical optimization formulation are expensive and time-consuming.
Approach:	They propose a solver-independent framework that converts engineers’ natural language requirements into executable optimization models.
Outcome:	The proposed framework outperforms existing methods in the accuracy of requirement formalization and quality of resulting radiation efficiency curves on antenna design.

Copied to clipboard

Junhui He, Shangyu Wu, Weidong Wen, Chun Jason Xue, Qingan Li

Language Generation via Combinatorial Constraint Satisfaction: A Tree Search Enhanced Monte-Carlo Approach (2020.findings-emnlp)

Challenge:	Existing methods for activation sparsification do not capture the relationship between activation and model performance.
Approach:	They propose a general activation sparsification approach using channel-wise thresholding and selective sparsifying to capture the relationship between activation and model performance.
Outcome:	The proposed approach reduces the number of activated neurons during inference by 1.27x over eight downstream tasks while activating fewer parameters than existing methods.

Copied to clipboard

Maosen Zhang, Nan Jiang, Lei Li, Yexiang Xue

Domaino1s: Guiding LLM Reasoning for Explainable Answers in High-Stakes Domains (2025.findings-acl)

Challenge:	Generating natural language under complex constraints is a principled formulation towards controllable text generation.
Approach:	They propose a method to specify combinatorial constraints for sentence generation . they use a tree search algorithm embedded into the proposal process of the Markov Chain Monte Carlo .
Outcome:	The proposed method achieves consistent and significant improvement on multiple language generation tasks.

Copied to clipboard

Xu Chu, Zhijie Tan, Hanlin Xue, Guanyu Wang, Tong Mo, Weiping Li

Breakthrough from Nuance and Inconsistency: Enhancing Multimodal Sarcasm Detection with Context-Aware Self-Attention Fusion and Word Weight Calculation. (2024.lrec-main)

Challenge:	Existing Large Language Models (LLMs) generate brief answers without reasoning processes and explanations.
Approach:	They propose supervised fine-tuning and tree search to enhance LLMs’ reasoning capabilities on domain tasks.
Outcome:	The proposed model improves on stock investment recommendation and legal reasoning QA tasks.

Copied to clipboard

Hongfei Xue, Linyan Xu, Yu Tong, Rui Li, Jiali Lin, Dazhi Jiang

Sentiment Analysis

Challenge:	Existing methods for sarcasm detection rely on feature concatenation to fuse different modalities or model inconsistencies among modalités.
Approach:	They propose to use Context-Aware Self-Attention Fusion to integrate local and momentary multimodal information into specific words to illustrate the inconsistencies between connotation and denotation.
Outcome:	The proposed method achieves an accuracy of 76.9 and an F1 score of 76.1 on the MUStARD dataset, surpassing the current state-of-the-art IWAN model by 1.7 and 1.6 respectively.

Event-Content-Oriented Dialogue Generation in Short Video (2024.naacl-long)

Copied to clipboard

Fenghua Cheng, Xue Li, Zi Huang, Jinxiang Wang, Sen Wang

Dialogue Systems & Conversational Agents

Challenge:	Existing multi-modal dialogue models are limited to incapacity of reading visual information and multi-dimensional interactions.
Approach:	They propose a novel event-oriented video-dialogue dataset called SportsVD to overcome these challenges by generating human-like response according to event contents in the video and related external knowledge.
Outcome:	The proposed method outperforms existing methods on SportsVD and other baselines under several automatic metrics.

A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization (2025.findings-acl)

Copied to clipboard

Junhui He, Junna Xing, Nan Wang, Rui Xu, Shangyu Wu, Peng Zhou, Qiang Liu, Chun Jason Xue, Qingan Li

Enhancing Reinforcement Learning with Label-Sensitive Reward for Natural Language Understanding (2024.acl-long)

Challenge:	Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache.
Approach:	They propose a retrieval-based method to reduce the memory footprint of LLMs . they propose Windowed Rotary Position Embedding and query-aware vector quantization .
Outcome:	The proposed method can achieve lower performance degradation with lower overhead compared to existing methods . it can reduce the memory footprint and access overhead of long context large language models .

Copied to clipboard

Kuo Liao, Shuang Li, Meng Zhao, Liqun Liu, Mengge Xue, Zhenyu Hu, Honglin Han, Chengguo Yin

Challenge:	Recent advances in large language models (LLMs) have yielded remarkable performance, but objective mismatch issues hinder RLHF learning.
Approach:	They propose a Reinforcement Learning framework enhanced with Label-sensitive reward to enhance LLMs' alignment and generation capabilities.
Outcome:	The proposed framework improves performance on five diverse models across eight tasks.

Empowering Backbone Models for Visual Text Generation with Input Granularity Control and Glyph-Aware Training (2024.emnlp-main)

Copied to clipboard

Wenbo Li, Guohao Li, Zhibin Lan, Xue Xu, Wanru Zhuang, Jiachen Liu, Xinyan Xiao, Jinsong Su

Visual Data in NLP

Challenge:	Existing text-to-image models struggle to generate images with legible visual texts . current models lack support for Chinese texts, misspelling, and lack of diversity .
Approach:	They propose to empower backbone models to generate visual texts in Chinese and English . they propose to augment conventional training objective with glyph-aware training losses .
Outcome:	The proposed methods can generate visual texts in English and Chinese while maintaining image generation quality.

Disco-RAG: Discourse-Aware Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang

Information Retrieval

Challenge:	Existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents.
Approach:	They propose a framework that explicitly injects discourse signals into the generation process.
Outcome:	Experiments on question answering and long-document summarization benchmarks show the efficacy of the proposed framework.

Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering (2025.findings-emnlp)

Copied to clipboard

Bolei He, Xinran He, Run Shao, Shanfu Shu, Xianwei Xue, MingQuan Cheng, Haifeng Li, Zhen-Hua Ling

Knowledge Representation

Challenge:	Large Language Models (LLMs) perform well in general QA but often struggle in domain-specific scenarios.
Approach:	They propose a framework that internalizes domain knowledge through internal-external knowledge self-selection and selective supervised fine-tuning.
Outcome:	The proposed framework outperforms existing methods and matches domain-pretrained LLMs with significantly lower cost.

Saber: Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model in Code Generation (2026.acl-long)

Copied to clipboard

Yihong Dong, Zhaoyu Ma, Xue Jiang, Zhiyuan Fan, Jiaru Qian, Yongmin Li, Jianha Xiao, Zhi Jin, Ge Li

Programming Languages in NLP

Challenge:	Diffusion language models (DLMs) offer advantages in parallel generation and bidirectional context modeling, but they face a critical trade-off between inference speed and output quality for tasks with strict structural constraints such as code generation.
Approach:	They propose an efficient sampling algorithm that reduces the number of tokens unmasked per step based on the model’s evolving confidence.
Outcome:	The proposed method improves Pass@1 accuracy by 1.9% while achieving 251.4% inference speedup.

Recovering dropped pronouns in Chinese conversations via modeling their referents (N19-1)

Copied to clipboard

Jingxuan Yang, Jianzhuo Tong, Si Li, Sheng Gao, Jun Guo, Nianwen Xue

Dialogue Systems & Conversational Agents

Challenge:	Pronouns are often dropped in conversational genres as their referents can be easily understood from context.
Approach:	They propose an end-to-end neural network model to recover dropped pronouns in conversational data.
Outcome:	The proposed model improves on three different conversational genres.

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Copied to clipboard

Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

Rethinking Repetition Problems of LLMs in Code Generation (2025.acl-long)

Challenge:	supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach:	They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome:	The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.

Copied to clipboard

Yihong Dong, Yuchen Liu, Xue Jiang, Bin Gu, Zhi Jin, Ge Li

Programming Languages in NLP

Challenge:	Recent studies have focused on content repetition, but structural repetition is a more prevalent problem in code generation.
Approach:	They propose a decoding approach that eliminates repetition problems in code generation by identifying grammar rules and strategically decaying the likelihood of critical tokens that contribute to repetitions.
Outcome:	The proposed approach outperforms baselines and humanEval benchmarks on CodeRepetEval dataset and MBPP benchmarks, effectively reducing repetitions and enhancing the quality of generated code.

We Need to Talk About Reproducibility in NLP Model Comparison (2023.emnlp-main)

Copied to clipboard

Yan Xue, Xuefei Cao, Xingli Yang, Yu Wang, Ruibo Wang, Jihong Li

BERT-ATTACK: Adversarial Attack Against BERT Using BERT (2020.emnlp-main)

Challenge:	Existing studies show that standard splits produce low reproducible and unreliable conclusions . reproducibility of empirical experimental conclusions is a problem in NLP domain .
Approach:	They propose to transform the reproducibility of a model comparison into a probabilistic function . they propose to use a regularized corpus splitting strategy to estimate the model's performance .
Outcome:	The proposed estimator achieves a high SNR and significantly increases reproducibility.

Copied to clipboard

Linyang Li, Ruotian Ma, Qipeng Guo, Xiangyang Xue, Xipeng Qiu

Robustness in NLP

Challenge:	Current approaches to generate adversarial samples for discrete data are heuristic replacement strategies that are difficult to implement in continuous data.
Approach:	They propose a method to generate adversarial samples using pre-trained masked language models using BERT.
Outcome:	The proposed method outperforms state-of-the-art methods in success rate and perturb percentage while remaining fluent and semantically preserved.

BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores (2026.acl-long)

Copied to clipboard

Jiajia Li, Weizhi Xue, Yao Yao, Qiwei Li, null Chenchong, Zuchao Li, Ping Wang, Hai Zhao

ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks (2025.emnlp-main)

Challenge:	Multimodal Large Language Models excel in general tasks but struggle with specialized, structured cultural symbols.
Approach:	They evaluate 21 leading MLLMs and compare their performance to a benchmark for Ancient Chinese musical notation.
Outcome:	The benchmark evaluates 21 leading MLLMs on five types of ancient Chinese music notation systems.

Copied to clipboard

Heng Zhou, Hejia Geng, Xiangyuan Xue, Li Kang, Yiran Qin, Zhiyong Wang, Zhenfei Yin, Lei Bai

Red Teaming Large Reasoning Models (2026.acl-long)

Challenge:	Multi-agent systems (MAS) are limited by poor flexibility and scalability, with underdeveloped optimization strategies.
Approach:	They propose a task graph generation and a reward-driven two-stage agent selection process to integrate multi-agent systems to improve their reasoning capabilities.
Outcome:	The proposed model outperforms existing methods on Math-MAS and SciBench-MAS SciBech, while other methods completely fail.

Copied to clipboard

Jiawei Chen, Yang Yang, Chao Yu, Yu Tian, Zhi Cao, Xue Yang, Linghao Li, Hang Su, Zhaoxia Yin

AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Challenge:	Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, but they introduce safety and reliability risks, such as CoT-hijacking and prompt-induced inefficiencies.
Approach:	They propose a unified benchmark to assess the trustworthiness of Large Reasoning Models.
Outcome:	The proposed benchmark evaluates truthfulness, safety and efficiency on 26 models.

Copied to clipboard

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Challenge:	Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach:	They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome:	The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.

PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning (2024.findings-acl)

Copied to clipboard

Tianci Xue, Ziqi Wang, Yixia Li, Yun Chen, Guanhua Chen

Bias Fitting to Mitigate Length Bias of Reward Model in RLHF (2026.acl-long)

Challenge:	In-context instruction tuning is a method that fine tunes with supervised instruction data to enhance the instruction following ability of large language models.
Approach:	They propose an in-context instruction tuning method that incorporates positive and negative examples into the prompt for better performance.
Outcome:	The proposed method outperforms baseline instruction tuning methods on in-domain and out-domain tasks up to 9.16 and 3.14 average ROUGE-L scores.

Copied to clipboard

Kangwen Zhao, Jianfeng Cai, Jinhua Zhu, Ruopei Sun, Dongyun Xue, Wengang Zhou, Li Li, Houqiang Li

Challenge:	Existing approaches to tackling length bias are limited by their complexity or lack of a linear length-reward relation.
Approach:	They propose a framework that learns and corrects underlying bias patterns by fitting a length-reward relationship into a reward model.
Outcome:	The proposed framework improves length-controlled win rate and reduces verbosity without compromising performance.

Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models (2024.findings-acl)

Copied to clipboard

Yihong Dong, Xue Jiang, Huanyu Liu, Zhi Jin, Bin Gu, Mengfei Yang, Ge Li

V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me (2025.acl-long)

Challenge:	Considering the vast size and wide-ranging sources of LLMs’ training data, it could explicitly or implicitly include test data.
Approach:	They propose a Contamination Detection via output Distribution (CDD) which detects data contamination only by identifying the peakedness of LLM's output distribution.
Outcome:	The proposed method improves performance by 21.8%-30.2% on humanEval and TED: trustworthy evaluation via output distribution.

Copied to clipboard

Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Jiapeng Wang, YiFan Zhang, Zhuoma GongQue, Chong Sun, Yida Xu, Yadong Xue, Ye Tian, Zhimin Bao, Lan Yang, Chen Li, Honggang Zhang

EmoPrompt-ECPE: Emotion Knowledge-aware Prompt-tuning for Emotion-Cause Pair Extraction (2024.lrec-main)

Challenge:	Deciphering oracle bone scripts using AI technology is not an overnight task due to the evolution of written language over millennia.
Approach:	They propose a framework that utilizes Large Multi-modal Models (LMMs) for interpreting Oracle Bone Script (OBS).
Outcome:	The proposed framework provides quantitative analyses and superior deciphering capability.

Copied to clipboard

Xue Gu, Zhihan Zhou, Ziyao Meng, Jian Li, Tiago Gomes, Adriano Tavares, Hao Xu

Verifiable LLM-Generated Text Detection via Projected Semantic-Structural Distributions (2026.acl-long)

Challenge:	Existing methods for Emotion-cause pair extraction (ECPE) do not distinguish between the emotion-caused pairs that belong to different types of emotions, limiting their applicability.
Approach:	They propose an Emotion-cause pair extraction method which integrates the implicit knowledge of cause clauses into a prompt template and extends the emotion labels to categories with an external emotion word base.
Outcome:	The proposed method extracts all potential emotion clauses and corresponding cause clauses from unannotated documents.

Copied to clipboard

Ruochong Xiong, Qien Li, Wangwang Lian, Yulong Wan, Hanlin Xue, Zhouxing Tan, Han Yang, Fengyu Lu, Junfei Liu

Meaning Representations for Natural Languages: Design, Models and Applications (2024.lrec-tutorials)

Challenge:	Existing methods for detecting LLM-Generated text suffer from distribution misalignment and limited interpretability.
Approach:	They propose a statistical framework utilizing supervised subspace learning to extract compact features and construct conditional semantic distributions based on syntactic structures.
Outcome:	The proposed framework is superior in cross-domain, cross-model, and adversarial scenarios.

Copied to clipboard

Julia Bonn, Jeffrey Flanigan, Jan Hajič, Ishan Jindal, Yunyao Li, Nianwen Xue

Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors (2024.acl-long)

Challenge:	a tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation.
Approach:	This tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation. authors propose a cutting-edge, full-day tutorial for all stakeholders in the AI community.
Outcome:	This tutorial reviews the design of common meaning representations and SoTA models for predicting meaning representation models . it also reviews the applications of meaning representation in downstream NLP tasks and real-world applications .

Copied to clipboard

Mengge Xue, Zhenyu Hu, Liqun Liu, Kuo Liao, Shuang Li, Honglin Han, Meng Zhao, Chengguo Yin

Co-Eval: Augmenting LLM-based Evaluation with Machine Metrics (2025.emnlp-main)

Challenge:	Multiple-Choice Questions (MCQs) are a critical area of research in the study of Large Language models (LLMs).
Approach:	They propose an efficient SFT algorithm for MCQs, termed Point-wise Intelligent Feedback, which constructs negative instances by randomly combing the incorrect option contents with all candidate symbols.
Outcome:	The proposed algorithm significantly reduces the model’s selection bias by improving its MCSB capability.

Copied to clipboard

Ling-I Wu, Weijie Wu, Minyu Chen, Jianxin Xue, Guoqiang Li

Challenge:	Existing LLMs suffer from biases and misalignment due to limited functional understanding and knowledge gaps.
Approach:	They introduce a framework that leverages a criteria planner model and optimized machine metrics to enhance the scalability and fairness of LLM-based evaluation.
Outcome:	The proposed framework reduces biases and improves alignment with human preferences, with gains of up to 0.324 in Spearman correlation.

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

Copied to clipboard

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

RCTEA: Richness-guided Co-training for Temporal Entity Alignment (2026.findings-acl)

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

Copied to clipboard

Jiayun Li, Wen Hua, Shiqi Fan, Fengmei Jin, Haiyang Jiang, Xue Li

Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention (2020.acl-main)

Challenge:	Existing TEA models fail to capture the orthogonal yet complementary effect between structural and temporal features.
Approach:	They propose a framework that jointly models structural and temporal aspects of Temporal Knowledge Graphs for entity alignment.
Outcome:	The proposed framework achieves state-of-the-art on public TEA benchmarks.

Copied to clipboard

Yanzeng Li, Bowen Yu, Xue Mengge, Tingwen Liu

Parameter-Efficient Prompt Tuning Makes Generalized and Calibrated Neural Text Retrievers (2023.findings-emnlp)

Challenge:	Pre-trained Chinese language models take character as the basic unit and learn representation according to character’s external contexts, ignoring the semantics expressed in the word, which is the smallest meaningful utterance in Chinese.
Approach:	They propose to pool character-level attention to the word level and propose to alleviate the potential issue of segmentation error propagation by multi-source information fusion.
Outcome:	The proposed approach improves on five Chinese NLP benchmark tasks against BERT, ERNIE and BERT-wwm.

Copied to clipboard

Weng Tam, Xiao Liu, Kaixuan Ji, Lilong Xue, Jiahua Liu, Tao Li, Yuxiao Dong, Jie Tang

KoCo-Bench: Can Large Language Models Leverage Domain Knowledge in Software Development? (2026.acl-long)

Challenge:	Prompt tuning is a technique that updates few parameters in pre-trained models for language understanding and generation tasks.
Approach:	They propose to leverage prompt tuning for neural text retrieval to improve generalization and cross-domain generalization.
Outcome:	The proposed approach can mitigate the two issues faced by fine-tuning retrieval methods and improve the out-of-domain zero-shot generalization of the retrieval models.

Copied to clipboard

Xue Jiang, Ge Li, Jiaru Qian, Xianjie Shi, Chenjie Li, Hao Zhu, Ziyu Wang, Jielun Zhang, Zeyu Zhao, Kechi Zhang, Jia Li, Wenpin Jiao, Zhi Jin, Yihong Dong

TAGS: A Test-Time Generalist–Specialist Framework with Retrieval-Augmented Reasoning and Verification (2026.findings-acl)

Challenge:	Existing domain-specific code benchmarks focus on assessing what knowledge LLMs possess rather than how they acquire and apply new knowledge.
Approach:	They propose a benchmark to evaluate domain specialization methods in real-world software development.
Outcome:	KOCO-bench is a new benchmark for evaluating domain specialization methods in real-world software development.

Copied to clipboard

Jianghao Wu, Feilong Tang, Yulong Li, Ming Hu, Haochen Xue, Shoaib Jameel, Zongyuan Ge, Yutong Xie, Imran Razzak

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation (2025.findings-acl)

Challenge:	Existing efforts to improve medical question answering performance follow two directions.
Approach:	They propose a framework that combines a generalist with a domain-specific specialist without any model fine-tuning or parameter updates.
Outcome:	The proposed framework boosts GPT-4o accuracy by 13.8%, deepseek-R1 by 16.8%, and improves a vanilla 7B model from 14.1% to 23.9%.

Copied to clipboard

Sreyan Ghosh, Mohammad Sadegh Rasooli, Michael Levit, Peidong Wang, Jian Xue, Dinesh Manocha, Jinyu Li

Information Retrieval

Challenge:	Generative Error Correction (GEC) is a powerful post-processing method to boost the performance of Automatic Speech Recognition systems.
Approach:	They propose a method to augment GEC models with retrieved entities to improve accuracy in out-of-domain and out-od scenarios.
Outcome:	The proposed method outperforms baseline models on multiple datasets and settings.

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

Copied to clipboard

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

AtTGen: Attribute Tree Generation for Real-World Attribute Joint Extraction (2023.acl-long)

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

Copied to clipboard

Yanzeng Li, Bingcong Xue, Ruoyu Zhang, Lei Zou

Information Extraction & Text Mining

Challenge:	Attribute extraction aims to identify attribute names and the corresponding attribute values from descriptive texts.
Approach:	They propose a unified formulation for real-world attribute extraction application, where closed-world, open-world and semi-open attribute extraction tasks are modeled uniformly.
Outcome:	The proposed model outperforms existing methods on three datasets and outperformed existing methods by a large margin.

DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)

Copied to clipboard

Shaokai He, Kaiwen Wei, Xinyi Zeng, Xiang Chen, Xue Yang, Zhenyang Li, Jiang Zhong, Yu Tian

BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios (2025.findings-acl)

Challenge:	Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs .
Approach:	They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations .
Outcome:	The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation .

Copied to clipboard

Wei Li, Lujun Li, Mark G. Lee, Shengjie Sun, Lei Zhang, Wei Xue, Yike Guo

Self-Sum: Teaching an Agent to Decide Itself When and What to Summarize (2026.findings-acl)

Challenge:	Large language models (LLMs) have revolutionized various domains with their remarkable capabilities, but their massive parameter sizes pose significant challenges for fine-tuning and inference.
Approach:	They propose a Bayesian Knowledge Distillation framework for compact Large Language Models in resource-constrained fine-tuning scenarios that employs Logits Dual-Scaling, Knowledge Alignment Module, and Bayes Distillations Optimization.
Outcome:	The proposed framework outperforms baseline methods on various state-of-the-art LLMs, including LLaMA, Qwen2, Bloom, and Vicuna.

Copied to clipboard

Hongru Wang, Rui Wang, Jushi Kai, Boyang Xue, Yongqi Li, Shijue Huang, Xiaoteng Ma, Jeff Z. Pan, Amos Storkey

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (D19-1)

Challenge:	Existing methods for summarizing long-horizon agents rely on fixed, rule-based summarization strategies.
Approach:	They propose a framework that empowers agents to autonomously decide when and what to summarize by modeling it as an internal cognitive action unified with environmental actions.
Outcome:	The proposed framework outperforms no-summarization and rule-based training methods on long-horizon benchmarks and shows strong generalization gains.

Copied to clipboard

Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, Vincent Zhang, Caiming Xiong, Richard Socher, Walter Lasecki, Dragomir Radev

Programming Languages in NLP

Challenge:	CoSQL is a corpus for building cross-domain, general-purpose database querying dialogue systems.
Approach:	They present a corpus for building cross-domain, general-purpose database querying dialogue systems . they use a Wizard-of-Oz collection of 3k turns plus 10k+ annotated SQL queries .
Outcome:	The proposed corpus is based on a Wizard-of-Oz dataset of 3k dialogues querying 200 complex DBs spanning 138 domains.

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Zelin Tan, Hejia Geng, Xiaohang Yu, Mulei Zhang, Guancheng Wan, Yifan Zhou, Qiang He, Xiangyuan Xue, Heng Zhou, Yutao Fan, Zhong-Zhi Li, Zaibin Zhang, Guibin Zhang, Chen Zhang, Zhenfei Yin, Philip Torr, Lei Bai

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs (2026.findings-acl)

Challenge:	elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach:	They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome:	The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.

Copied to clipboard

Hongyuan Yuan, Xinran He, Run Shao, Bolei He, Xianwei Xue, Mengke Chen, Qiutong Pan, Haiwei Wang, Haifeng Li

Structured Data in NLP

Challenge:	Extending CoT through RL can induce undesirable thinking patterns such as overthinking . prior work has focused on inefficient reflection, which manifests in two problematic patterns: Indiscriminate Reflection and Repetitive Reflectione .
Approach:	They propose a graph-based approach to optimize CoT by pruning each linear CoT into a directed acyclic graph with explicit dependency edges.
Outcome:	The proposed approach reduces the average reasoning tokens by 42% while maintaining or improving accuracy.

Unified Hallucination Detection for Multimodal Large Language Models (2024.acl-long)

Copied to clipboard

Xiang Chen, Chenxi Wang, Yida Xue, Ningyu Zhang, Xiaoyan Yang, Qiang Li, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen

Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language Models (2025.acl-long)

Challenge:	despite significant strides in multimodal tasks, MLLMs are plagued by the critical issue of hallucination.
Approach:	They propose a meta-evaluation benchmark to facilitate evaluation of advancements in hallucination detection methods.
Outcome:	The proposed framework validates hallucinations robustly and provides strategic insights . MHaluBench is a meta-evaluation benchmark designed to facilitate evaluation .

Copied to clipboard

Chengao Li, Hanyu Zhang, Yunkun Xu, Hongyan Xue, Xiang Ao, Qing He

RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization (2026.acl-long)

Challenge:	Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences.
Approach:	They propose a novel algorithm that uses multiple-gradient descent to optimize LLMs with diverse preferences to maximize trade-offs between objectives.
Outcome:	The proposed approach incorporates user preferences across different objectives and achieves Pareto solutions that better align with the user’s specific needs.

Copied to clipboard

Yihong Dong, Xue Jiang, Yongding Tao, Huanyu Liu, Kechi Zhang, Lili Mou, Rongyu Cao, Yingwei MA, Jue Chen, Binhua Li, Zhi Jin, Fei Huang, Yongbin Li, Ge Li

Escaping the Echo Trap: On Credit Assignment Failure in Multi-turn LLM Self-Reflection (2026.acl-long)

Challenge:	Reinforcement Learning with Verifiable Reward (RLVR) has significantly advanced the complex reasoning abilities of Large Language Models (LLMs).
Approach:	They propose a hybrid-policy optimization approach that synergizes internal exploitation with external data to achieve stronger reasoning capabilities.
Outcome:	The proposed approach achieves state-of-the-art performance on six math reasoning benchmarks and superior performance on out-of distribution reasoning tasks.

Copied to clipboard

Linxuan Du, Guangquan Xue, Xiaobo Liang, Qipeng Huang, Yuyang Ding, Xinyu Shi, Zhang Yijun, Ji Qi, Wenpeng Zhu, Juntao Li, Min Zhang

Challenge:	Existing methods for multi-turn self-reflection are limited by the Echo Trap problem . the model is limited by its inherent capabilities and repeats earlier reflections to preserve reward signals .
Approach:	They propose a tree-structured extension of GRPO for multi-turn self-reflection which enables more accurate advantage estimation.
Outcome:	The proposed method mitigates behavior collapse and improves performance across benchmarks.

ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents (2026.acl-long)

Copied to clipboard

Zechen Li, Baiyu Chen, Hao Xue, Flora D. Salim

MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantization (2025.emnlp-main)

Challenge:	Existing approaches to human activity recognition are constrained to fixed activity sets . lack of training-free adaptation to new behavior leads to hallucinations and weak grounding .
Approach:	They propose a knowledge- and retrieval-augmented agentic framework for motion time-series reasoning in a training-free inference setting.
Outcome:	The proposed framework generalizes robustly to unseen subjects and across datasets . it can be used to train-free inference in a training-free environment .

Copied to clipboard

Chun Hu, Junhui He, Shangyu Wu, Yuxin He, Chun Jason Xue, Qingan Li

UniPSDA: Unsupervised Pseudo Semantic Data Augmentation for Zero-Shot Cross-Lingual Natural Language Understanding (2024.lrec-main)

Challenge:	Existing methods for efficient deployment of small language models face inefficient bit-width allocation and insufficient fine-grained quantization adjustments.
Approach:	They propose a weight quantization technique that facilitates efficient deployment of SLMs . they propose to combine inter-layer loss and intra-layer salience to achieve better allocation .
Outcome:	Experimental results show that multi-level weight quantization achieves competitive performance compared to state-of-the-art methods.

Copied to clipboard

Dongyang Li, Taolin Zhang, Jiali Deng, Longtao Huang, Chengyu Wang, Xiaofeng He, Hui Xue

The Emperor’s New Reasoning: Format Imitation Overshadows Genuine Mathematical Understanding in SFT (2025.emnlp-main)

Challenge:	Existing studies rely on shallow unsupervised data generated by token surface matching regardless of global context-aware semantics of the surrounding text tokens.
Approach:	They propose an Unsupervised Pseudo Semantic Data Augmentation mechanism to enrich training data without human intervention.
Outcome:	The proposed model improves on general zero-shot cross-lingual understanding tasks on different languages without human intervention.

Copied to clipboard

Linyao Yang, Jian-Tao Huang, Yafei Lu, Zhenhui Jessie Li, Guirong Xue

Rhombus: Incentivizing Coordination in Parallel Thinking through Reinforcement Learning (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have yielded impressive gains on mathematical reasoning benchmarks via supervised fine-tuning (SFT).
Approach:	They investigate the mechanisms behind SFT improvements in small-scale large language models by examining four key questions: (1) Are performance gains primarily due to format alignment rather than reasoning? (2) Can high-quality supervision encourage genuine reasoning? (4) Are format alignment gains consistent across model sizes and architectures?
Outcome:	The proposed models outperform the proprietary models on OlympiadBench and Omni-Math, but lack the brittleness of the models under perturbations to test their reasoning abilities.

Copied to clipboard

Ziyuan Nan, Qi Yi, Di Huang, Yutong Wu, Guanhua Huang, Xue Gong, Kejiao Li, Yuhao Jiang, Chenchen Zhang, Zenan Xu, Xing Hu, Bo Zhou

Semi-supervised Domain Adaptation for Dependency Parsing (P19-1)

Challenge:	Parallel thinking is a promising avenue for scaling test-time compute in Large Language Models . however, coordinating the exploration and aggregation stages remains challenging .
Approach:	They propose a parallel thinking framework that explicitly incentivizes coordination between components via end-to-end reinforcement learning.
Outcome:	The proposed framework improves accuracy by 6.0% over long chain-of-thought baselines while reducing wall-clock latency by 39.4% under matched token budgets.

Copied to clipboard

Zhenghua Li, Xue Peng, Min Zhang, Rui Wang, Luo Si