Papers by Lu Xiao

Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026.acl-long)

Challenge:	Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples.
Approach:	They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies.
Outcome:	The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models.

Copied to clipboard

Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang

Challenge:	GUI agents have demonstrated remarkable progress in automating complex user interface interactions . training such agents for long-horizon tasks remains challenging due to limited rewards and prohibitive costs.
Approach:	They propose a method that leverages expert trajectories as environment experiences for on-policy multi-turn training.
Outcome:	The proposed method achieves significant gains over the base model with 1K public trajectories as RL experiences . it achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o .

Immediate Inference: The Missing Foundation in Large Language Model Logical Reasoning (2026.acl-long)

Copied to clipboard

Sihang Jiang, Zhiyu Lu, Keyi Wang, Jiaqing Liang, Yanghua Xiao, Xiaojun Meng, Jiansheng Wei

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning (2025.findings-acl)

Challenge:	Recent work on LLMs has focused on fine-grained skill decomposition and consistency probing at the propositional level.
Approach:	They propose a benchmark evaluating immediate inference that evaluates elemental operations over categorical propositions and proposes a model that uses immediate inferential reasoning.
Outcome:	The proposed benchmark demonstrates that models lack robust operator grounding, oscillating between structural reasoning and surface pattern matching, inconsistent handling of quantifiers and negation.

Copied to clipboard

Ke Wang, Junting Pan, Linda Wei, Aojun Zhou, Weikang Shi, Zimu Lu, Han Xiao, Yunqiao Yang, Houxing Ren, Mingjie Zhan, Hongsheng Li

Unified Structure Generation for Universal Information Extraction (2022.acl-long)

Challenge:	Large Language Models (LMMs) struggle with simple tasks such as geometry, e.g., arithmetic, and reasoning.
Approach:	They propose to leverage code as supervision for cross-modal alignment . they propose to use FigCodifier and ImgCode-8.6M to synthesize novel mathematical figures .
Outcome:	The proposed model surpasses GPT-4o and Claude 3.5 Sonnet in the geometry problem-solving subset of MathVista, achieving improvements of 8.9% and 9.2%.

Copied to clipboard

Yaojie Lu, Qing Liu, Dai Dai, Xinyan Xiao, Hongyu Lin, Xianpei Han, Le Sun, Hua Wu

Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Challenge:	Information extraction suffers from its varying targets, heterogeneous structures, and demand-specific schemas.
Approach:	They propose a unified text-to-structure generation framework, namely UIE, which can universally model different IE tasks, adaptively generate targeted structures, and collaboratively learn general IE abilities from different knowledge sources.
Outcome:	The proposed framework can model different IE tasks, generate targeted structures, and learn general IE abilities from different knowledge sources.

Copied to clipboard

Yiwen Qiu, Linjuan Wu, Yizhou Liu, Yuchen Yan, Jin Ma, Xu Tan, Yao Hu, Daoxin Zhang, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)

Challenge:	Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach:	They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome:	The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .

Copied to clipboard

Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2024.findings-naacl)

Challenge:	Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects.
Approach:	They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt.
Outcome:	The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks.

Copied to clipboard

Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang

AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies (2024.emnlp-main)

Challenge:	i-Code V2 is one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data.
Approach:	They propose to create a model that can generate natural language from any combination of Vision, Language, and Speech data.
Outcome:	i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks.

Copied to clipboard

Xiao Ye, Andrew Wang, Jacob Choi, Yining Lu, Shreya Sharma, Lingfeng Shen, Vijay Murari Tiyyala, Nicholas Andrews, Daniel Khashabi

AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models (2024.findings-emnlp)

Challenge:	Analogical reasoning is an important part of human communication, says a new study . a benchmark to determine analogical reasoning ability in language models is needed .
Approach:	They propose to benchmark analogical reasoning ability in language models by collecting 340 analogies from human writings.
Outcome:	The proposed benchmark aims to determine analogical reasoning ability in language models.

Copied to clipboard

Jiale Cheng, Yida Lu, Xiaotao Gu, Pei Ke, Xiao Liu, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback (2025.findings-acl)

Challenge:	Large Language Models (LLMs) exhibit significant but subtle weaknesses, such as mistakes in instruction-following or coding tasks.
Approach:	They propose a framework to automatically expose weaknesses in Large Language Models (LLMs) they use three LLM-powered agents to perform comprehensive weakness identification .
Outcome:	The proposed framework shows that it is more effective than untargeted data augmentation methods like Self-Instruct to identify weaknesses in LLMs.

Copied to clipboard

Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang

Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Existing mathematical verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions.
Approach:	They propose a natural language feedback-enhanced verifier that can validate the correctness of response generated by policy models by constructing automatically generated training data and a two-stage training paradigm.
Outcome:	The proposed verifier significantly improves in verification and reinforcement learning and alleviates data-demanding problems of the reward model.

Copied to clipboard

Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun

Syntactic Text Processing

Challenge:	Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence.
Approach:	They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary.
Outcome:	Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training.

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement (2025.findings-acl)

Copied to clipboard

Junyu Lu, Kai Ma, Kaichun Wang, Kelaiti Xiao, Roy Ka-Wei Lee, Bo Xu, Liang Yang, Hongfei Lin

Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator (2024.lrec-main)

Challenge:	Existing studies focus on evaluating large language models' ability to handle disagreement cases.
Approach:	They evaluate the performance of large language models in detecting offensive language at varying levels of agreement.
Outcome:	The proposed model improves detection accuracy and model alignment with human judgment by using disagreement samples in training.

Copied to clipboard

Ziqian Zeng, Runyu Wu, Yuxiang Xiao, Xiaoda Zhong, Hanlin Wang, Zhengdong Lu, Huiping Zhuang

GhostBERT: Generate More Features with Cheap Operations for BERT (2021.acl-long)

Challenge:	Recent work proposed to use a pre-trained textual entailment model for event detection . but, those methods treated the TE model as a frozen annotator .
Approach:	They propose to use TE models to annotate large-scale unlabeled text and annotated data to fine-tune the TE model.
Outcome:	The proposed method outperforms baseline methods by 15% on the ACE05 dataset.

Copied to clipboard

Zhiqi Huang, Lu Hou, Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu

AgentTuning: Enabling Generalized Agent Abilities for LLMs (2024.findings-acl)

Challenge:	Existing studies show that some parameters in pre-trained language models can be pruned away without severe accuracy degradation.
Approach:	They propose a method which generates more features with very cheap operations from the remaining features and can be applied to unpruned BERT models to enhance their performance.
Outcome:	Empirical results on the GLUE benchmark on three backbone models (i.e., BERT, RoBERTa and ELECTRA) verify the efficacy of the proposed method.

Copied to clipboard

Aohan Zeng, Mingdao Liu, Rui Lu, Bowen Wang, Xiao Liu, Yuxiao Dong, Jie Tang

EXCEEDS: Extracting Complex Events via Nugget-based Grid Modeling in Scientific Domain (2026.acl-long)

Challenge:	Open large language models (LLMs) with great performance in various tasks are far inferior to commercial models such as ChatGPT and GPT-4 when acting as agents to tackle complex tasks in the real world.
Approach:	They propose a method to enhance the agent capabilities of LLMs while maintaining their general abilities.
Outcome:	The AgentLM-70B is comparable to GPT-3.5-turbo on unseen agent tasks, demonstrating generalized agent capabilities.

Copied to clipboard

Yi-Fan Lu, Xian-Ling Mao, Bo Wang, Xiao Liu, Heyan Huang

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Challenge:	Extensive event extraction research has been conducted in many domains, including news, finance, and biology.
Approach:	They propose an end-to-end scientific event extraction framework for encoding nuggets into a grid matrix and simplifying complex event extraction as a nuggot-based grid modeling task.
Outcome:	The proposed framework performs well in scientific domain, demonstrating state-of-the-art performance.

Copied to clipboard

Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach:	They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome:	Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

Modeling Content Importance for Summarization with Pre-trained Language Models (2020.emnlp-main)

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Copied to clipboard

Liqiang Xiao, Lu Wang, Hao He, Yaohui Jin

Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queries (2025.findings-acl)

Challenge:	Existing studies on content importance do not consider semantics and context when evaluating importance.
Approach:	They apply information theory to pre-trained language models to define the concept of importance from the perspective of information amount.
Outcome:	Experiments on CNN/Daily Mail and New York Times show that the proposed model can model the importance of content better than previous methods based on F1 and ROUGE scores.

Copied to clipboard

Ganlin Xu, Zhoujia Zhang, Wangyi Mei, Jiaqing Liang, Weijia Lu, Xiaodong Zhang, Zhifei Yang, Xiaofeng Ma, Yanghua Xiao, Deqing Yang

Semantic Text Processing

Challenge:	Current dense retrieval methods compute similarities between dense vectors but overlook the real query intents.
Approach:	They propose a neuro-symbolic information retrieval method that leverages first-order logic to optimize the embeddings of naive natural language by considering the logical consistency between queries and documents.
Outcome:	The proposed method outperforms existing methods on negative-constraint queries under zero-shot and low-resource retrieval tasks.

RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysis (2025.findings-acl)

Copied to clipboard

Pengzuo Wu, Yuhang Yang, Guangcheng Zhu, Chao Ye, Hong Gu, Xu Lu, Ruixuan Xiao, Bowen Bao, Yijing He, Liangyu Zha, Wentao Ye, Junbo Zhao, Haobo Wang

TV-AfD: An Imperative-Annotated Corpus from The Big Bang Theory and Wikipedia’s Articles for Deletion Discussions (2020.lrec-1)

Challenge:	Existing benchmarks for large language models focus on simple, flat table structures.
Approach:	They propose a benchmark to evaluate the performance of both Large Language Models and Multimodal LLMs across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.
Outcome:	The proposed benchmark evaluates the performance of LLMs and Multimodal LLM models across a variety of input formats for complex tabular data, including LaTeX, HTML, and PNG.

Copied to clipboard

Yimin Xiao, Zong-Ying Slaton, Lu Xiao

Dialogue Systems & Conversational Agents

Challenge:	Detecting imperatives in oral and written communication is difficult when the user doesn't use the expected forms.
Approach:	They created an imperative corpus with dialogues from The Big Bang Theory and Wikipedia comments from Wikipedia . they manually annotated imperatives and used a syntax-based classifier to extract 10,624 statements that may be imperative.
Outcome:	The proposed model performs better in the written data compared to speech data, but has a low precision and recall for speech data.

A Lexicon-Based Approach for Detecting Hedges in Informal Text (2020.lrec-1)

Copied to clipboard

Jumayel Islam, Lu Xiao, Robert E. Mercer

Dialogue Systems & Conversational Agents

Challenge:	Existing studies on hedging detection have focused on structured texts and formal communications.
Approach:	They propose to use hedging words and phrases to identify tensions between interviewees during a survivor interview to help researchers understand the dynamics of the interview.
Outcome:	The proposed algorithm detects sentence-level hedges in informal conversations such as survivor interviews.

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval (2022.emnlp-industry)

Copied to clipboard

Kun Zhou, Yeyun Gong, Xiao Liu, Wayne Xin Zhao, Yelong Shen, Anlei Dong, Jingwen Lu, Rangan Majumder, Ji-rong Wen, Nan Duan

FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs (2025.findings-emnlp)

Challenge:	Existing methods for sapping negatives from large document pool suffer from the uninformative or false negative problem.
Approach:	They propose a method to sample negatives from a large document pool using a new sampling probability distribution.
Outcome:	The proposed method can be used to sample more ambiguous negatives on four public and one industry datasets.

Copied to clipboard

Yingjia Wan, Haochen Tan, Xiao Zhu, Xinyu Zhou, Zhiwei Li, Qingsong Lv, Changxuan Sun, Jiaqi Zeng, Yi Xu, Jianqiao Lu, Yinhong Liu, Zhijiang Guo

Syntactic and Semantic-driven Learning for Open Information Extraction (2020.findings-emnlp)

Challenge:	Prior evaluation pipelines fail to evaluate factuality of long-form LLMs due to inefficiency and costly human assessment.
Approach:	They propose a fast and strong evaluation pipeline that can evaluate factuality of long-form LLMs . they propose 'faStFact' to reduce cost of web searching and inference calling .
Outcome:	The proposed evaluation pipeline achieves highest alignment with human evaluation and efficiency among existing baselines.

Copied to clipboard

Jialong Tang, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Xinyan Xiao, Hua Wu

Identifying Tension in Holocaust Survivors’ Interview: Code-switching/Code-mixing as Cues (2022.lrec-1)

Challenge:	Experimental results show that our approach significantly outperforms the supervised counterparts, and can even achieve competitive performance to supervised state-of-the-art (SoA) model.
Approach:	They propose a syntactic and semantic-driven learning approach that can learn open IE models without human-labelled data by leveraging syntakic and semantic knowledge as noisier, higher-level supervision.
Outcome:	The proposed approach outperforms supervised counterparts and can achieve competitive performance to supervised state-of-the-art models.

Copied to clipboard

Xinyuan Xia, Lu Xiao, Kun Yang, Yueyue Wang

Multilinguality

Challenge:	Using CS/CM as a linguistic phenomenon could be a sign of tension in Holocaust survivors’ interviews.
Approach:	They annotated CS/CM codes and annotate silence situations in an open corpus . they found that most annotations were captured in the tension places .
Outcome:	The proposed method shows that annotations are captured in the tension places . the study calls for more research endeavors on tension detection .

UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization (2026.acl-long)

Copied to clipboard

Zhengxi Lu, Fei Tang, Guangyi Liu, Jin Ma, Kaitao Song, Xu Tan, Wenqi Zhang, Weiming Lu, Jun Xiao, Yueting Zhuang, Yongliang Shen

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)

Challenge:	Experimental results show that UI-Copilot-7B achieves state-of-the-art performance on challenging MemGUI-Bench, outperforming strong 7B-scale GUI agents such as GUI-Owl-7B and UITARS-1.5-7B.
Approach:	They propose a collaborative framework where the GUI agent focuses on task execution while a lightweight copilot provides on-demand assistance for memory retrieval and numerical computation.
Outcome:	The proposed framework outperforms GUI-Owl-7B and UI-TARS-1.5-7B on MemGUI-Bench and delivers 17.1% improvement on AndroidWorld over the base Qwen model.

Copied to clipboard

Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection (2022.findings-emnlp)

Challenge:	Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks.
Approach:	They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically.
Outcome:	The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios.

Copied to clipboard

Chenglong Wang, Yi Lu, Yongyu Mu, Yimin Hu, Tong Xiao, Jingbo Zhu

Semantic Text Processing

Challenge:	Existing studies on knowledge distillation have shown that not all knowledge is necessary for learning a good student model.
Approach:	They propose an actor-critic approach to selecting appropriate knowledge to transfer during the process of knowledge distillation.
Outcome:	The proposed method outperforms several strong knowledge distillation baselines significantly on the GLUE datasets.

Multi-Channel Convolutional Neural Network for Twitter Emotion and Sentiment Recognition (N19-1)

Copied to clipboard

Jumayel Islam, Robert E. Mercer, Lu Xiao

Sentiment Analysis

Challenge:	Existing methods to analyze tweets are based on lexical features and a multi-channel convolutional neural architecture.
Approach:	They propose a neural network which can use different emotion and sentiment indicators such as hashtags, emoticons and emojis present in tweets to improve the performance of emotion and feelings identification.
Outcome:	The proposed model can use hashtags, emoticons and emojis present in tweets and improves emotion and sentiment identification.

Metaphor Reasoning is Meta-reasoning (2026.acl-long)

Copied to clipboard

Qianyu He, Junting Lu, Yikai Zhang, Siyu Yuan, Xiaojun Meng, Jiansheng Wei, Jiaqing Liang, Yanghua Xiao

Detection of Propaganda Using Logistic Regression (D19-50)

Challenge:	Existing work on metaphor reasoning's impact on reasoning abilities is limited.
Approach:	They propose a system for synthesizing metaphorical riddles that satisfy five quality dimensions: diverse, balanced, reasoning-oriented, challenging, and verifiable.
Outcome:	The proposed system improves reasoning abilities across six domains using only thousands of metaphorical riddles.

Copied to clipboard

Jinfen Li, Zhihao Ye, Lu Xiao

Challenge:	Various propaganda techniques are used to manipulate peoples perspectives to foster a predetermined agenda.
Approach:	They propose a Logistic Regression-based tool that automatically classifies whether a sentence is propagandistic or not.
Outcome:	The proposed tool outperforms the baseline on linguistic and semantic features.

Task-Agnostic Detector for Insertion-Based Backdoor Attacks (2024.findings-naacl)

Copied to clipboard

Weimin Lyu, Xiao Lin, Songzhu Zheng, Lu Pang, Haibin Ling, Susmit Jha, Chao Chen

Robustness in NLP

Challenge:	Existing methods for textual backdoor detection are task-specific and less effective beyond sentence classification.
Approach:	They propose a task-agnostic method for backdoor detection that leverages final layer logits and an efficient pooling technique.
Outcome:	TABDet can jointly learn from diverse task-specific models, demonstrating superior detection efficacy over traditional methods.

Copied to clipboard

Wenqiang Wang, Peng Chen, Yan Xiao, Yangshijie Zhang, Xiaoyue Lu, Jianjie Huang, Xiaochun Cao

ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning (2025.emnlp-demos)

Challenge:	Standard in-context learning assumes identical output spaces between test and retrieval datasets . however, in practice, these datasets can be fully aligned, partially alignes, or fully disjoint in label space .
Approach:	They propose a framework for in-context learning under output-space mismatch . they identify demonstrations relevant to the test label space via a Bayesian probabilistic criterion .
Outcome:	The proposed framework achieves state-of-the-art results across three LLMs, three task types, and four datasets.

Copied to clipboard

Yichen Lu, Wei Dai, Jiaen Liu, Ching Wing Kwok, Zongheng Wu, Xudong Xiao, Ao Sun, Sheng Fu, Jianyuan Zhan, Yian Wang, Takatomo Saito, Sicheng Lai

Machine Translation

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable capabilities in Machine Translation (MT) tasks.
Approach:	They propose a translation agent system designed for multimodal input that leverages visual and contextual background information to enhance the translation process.
Outcome:	The proposed translation agent achieves significantly higher translation quality in subtitle generation and general translation tasks compared to previous state-of-the-art systems.

Word-Conditioned 3D American Sign Language Motion Generation (2024.findings-emnlp)

Copied to clipboard

Lu Dong, Xiao Wang, Ifeoma Nwogu

Challenge:	Sign words are the building blocks of any sign language.
Approach:	They propose a word-conditioned 3D American Sign Language (ASL) generation model that synthesizes real-time motion sequences for sign words.
Outcome:	The proposed model outperforms the baseline model in the task of sign word generation.

Tree Representations in Transition System for RST Parsing (2020.coling-main)

Copied to clipboard

Jinfen Li, Lu Xiao

Representation Learning

Challenge:	Existing studies have proposed a series of actions to build a right-heavy binarized tree for RST parsing, but the nodes of the binary-nuclear relations have the same nuclear type as those of the multi-nullar relations.
Approach:	They propose a nuclear type for multi-nuclear relations and a new action to construct a multi-branch tree.
Outcome:	The proposed nuclear type and action are more capable of capturing multi-nuclear relation and the joint action is more suitable than the separate one.

ToW: Thoughts of Words Improve Reasoning in Large Language Models (2025.naacl-long)

Copied to clipboard

Zhikun Xu, Ming Shen, Jacob Dineen, Zhaonan Li, Xiao Ye, Shijie Lu, Aswin Rrv, Chitta Baral, Ben Zhou

Parsing Natural Language into Propositional and First-Order Logic with Dual Reinforcement Learning (2022.coling-1)

Challenge:	Unlike other data augmentation methods, thoughts of words (TOW) views next-word prediction as a core reasoning task and injects fine-grained thoughts into pre-training texts.
Approach:	They propose a training-time data-augmentation method called thoughts of words (TOW) that injects fine-grained thoughts directly into a next-word prediction task and teaches the model to understand how the observed next word is related to previous contexts.
Outcome:	The proposed method reduces model hallucination by 10% and improves reasoning performance by 7% to 9% on average.

Copied to clipboard

Xuantao Lu, Jingping Liu, Zhouhong Gu, Hanwen Tong, Chenhao Xie, Junyang Huang, Yanghua Xiao, Wenguang Wang

Challenge:	Existing methods to parse natural language into structured logical expressions have limitations due to paucity of labeled data.
Approach:	They propose a scoring model to automatically learn a model-based reward . they also propose introducing a Chinese-PL/FOL dataset to compensate for paucity of labeled data .
Outcome:	The proposed model outperforms competitors on several datasets.

TernaryBERT: Distillation-aware Ultra-low Bit BERT (2020.emnlp-main)

Copied to clipboard

Wei Zhang, Lu Hou, Yichun Yin, Lifeng Shang, Xiao Chen, Xin Jiang, Qun Liu

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

Challenge:	Transformer-based pre-training models like BERT are computationally expensive and limited to resource-constrained devices.
Approach:	They propose a method which ternarizes the weights in a fine-tuned BERT model.
Outcome:	The proposed method outperforms the other methods on the GLUE and SQUAD benchmarks while being 14.9x smaller.

Copied to clipboard

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

Multilinguality

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

Protein Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Copied to clipboard

Yijia Xiao, Wanjia Zhao, Junkai Zhang, Yiqiao Jin, Han Zhang, Zhicheng Ren, Renliang Sun, Haixin Wang, Guancheng Wan, Pan Lu, Xiao Luo, Yu Zhang, James Zou, Yizhou Sun, Wei Wang

Language Model Adaption for Reinforcement Learning with Natural Language Action Space (2024.acl-long)

Challenge:	Existing studies focus on specific aspects or applications, but this study provides a comprehensive overview of Protein-specific large language models.
Approach:	This paper proposes a structured taxonomy of state-of-the-art ProteinLLMs . they analyze how they leverage large-scale protein sequence data for improved accuracy .
Outcome:	The proposed model covers their architectures, training datasets, evaluation metrics, and diverse applications.

Copied to clipboard

Jiangxing Wang, Jiachen Li, Xiao Han, Deheng Ye, Zongqing Lu

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs? (2025.findings-acl)

Challenge:	Previous research has focused on reducing the size of the natural language action space due to the combinatorial nature of the language.
Approach:	They propose mutual-information regularized policy optimization to reduce the action space by dynamically adjusting the prior provided by the pretrained model.
Outcome:	The proposed method improves monotonically on the mutual-information regularized RL objective.

Copied to clipboard

Qingyuan Liang, Zhao Zhang, Zeyu Sun, Zheng Lin, Qi Luo, Xiao Yueyi, Yizhou Chen, Yuqun Zhang, Haotian Zhang, Lu Zhang, Chenbin Chenbin, Yingfei Xiong

Chain-of-Quizzes: Pedagogy-inspired Example Selection in In-Context-Learning (2024.findings-acl)

Challenge:	Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance.
Approach:	They develop a series of billion-scale grammar-based code representations that incorporate grammar rules into the code generation process.
Outcome:	Experiments on HumanEval and MBPP show that grammar-based representations reduce syntax errors and improve performance even in billion-scale models.

Copied to clipboard

Yiquan Wu, Anlai Zhou, Yuhang Liu, Yifei Liu, Adam Jatowt, Weiming Lu, Jun Xiao, Kun Kuang

Low-Resource NLP

Challenge:	In-context learning (ICL) is a powerful tool for enhancing large language models (LLMs) by mimicking the human learning process.
Approach:	They propose a Chain-of-Quizzes framework that uses LLMs to answer a quiz to sift 'good' examples, combine them iteratively with the increasing complexity, and utilize a final exam to gauge the combined example chains.
Outcome:	The proposed framework outperforms baseline models on diverse reasoning datasets and shows that it is scalable and can be used in future research.

Decomposed Prompt Tuning via Low-Rank Reparameterization (2023.findings-emnlp)

Copied to clipboard

Yao Xiao, Lu Xu, Jiaxi Li, Wei Lu, Xiaoli Li

LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems (2024.acl-demos)

Challenge:	Pre-trained language models have achieved remarkable performance on various tasks.
Approach:	They propose a decomposed prompt tuning approach that utilizes low-rank matrices to initialize the soft prompt.
Outcome:	The proposed method significantly reduces the number of trainable parameters while maintaining effectiveness.

Copied to clipboard

Xiao Yu, Yunan Lu, Zhou Yu

Thermometer of Thoughts: Enhancing LLM’s Exploration via Attention Temperature Modulation (2026.acl-long)

Challenge:	Existing tools for augmented question-answering do not support researchers and developers to customize the training, testing, and deployment process.
Approach:	They propose an open-source toolkit that features a wide selection of model training algorithms, evaluation methods, and deployment tools curated from the latest research.
Outcome:	The proposed framework trains and deploys 7B-models with the same performance as OpenAI’s text-ada-002 and GPT-4-turbo.

Copied to clipboard

Zhiyuan Yu, Shijian Xiao, Cam-Tu Nguyen, Zhangyue Yin, Lekai Xing, Wenzhong Li, Sanglu Lu

AIGT: AI Generative Table Based on Prompt (2025.coling-main)

Challenge:	Recent advances in the reasoning capabilities of large language models have enabled them to tackle complex tasks such as mathematics reasoning.
Approach:	They propose a method that modulates attention temperature dynamically to shift LLM's internal focus during reasoning, enabling a dynamic shift between exploratory and focused modes.
Outcome:	The proposed method improves Pass@10 by 6.78–14.20% and aggregation accuracy by 9.74% across 7 reasoning benchmarks.

Copied to clipboard

Mingming Zhang, Zhiqing Xiao, Guoshan Lu, Sai Wu, Weiqiang Wang, Xing Fu, Can Yi, Junbo Zhao

Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions (2026.acl-long)

Challenge:	Tabular data is an essential resource for many fields, but current methods do not fully utilize the rich information available in tables.
Approach:	They propose a method that utilizes metadata information to generate tabular data . they propose long-token partitioning algorithms that enable AIGT to model tables of any scale .
Outcome:	The proposed approach achieves state-of-the-art on 14 out of 20 public datasets and two real industry datasets within the Alipay risk control system.

Copied to clipboard

Boyan Duan, Xiao Liang, Shuai Lu, Yaoxiang Wang, Yelong Shen, Kai-Wei Chang, Ying Nian Wu, Mao Yang, Weizhu Chen, Yeyun Gong

Green & Sustainable NLP

Challenge:	Existing methods for geometry theorem proving in Euclidean geometry are challenging and require a neural network to perform.
Approach:	They propose a method for adding auxiliary points in geometry that runs on CPUs without relying on neural network-based inference.
Outcome:	The proposed method achieves silver-medal-level human performance on IMO-30 benchmark.

MedCite: Can Language Models Generate Verifiable Text for Medicine? (2025.findings-acl)

Copied to clipboard

Xiao Wang, Mengjue Tan, Qiao Jin, Guangzhi Xiong, Yu Hu, Aidong Zhang, Zhiyong Lu, Minjia Zhang

Semantic Text Processing

Challenge:	Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice.
Approach:	They propose a framework that facilitates the design and evaluation of LLM citations for medical tasks and a retrieval-citation method that generates high-quality citation.
Outcome:	The proposed method achieves superior citation precision and recall improvements compared to strong baseline methods and correlates well with annotation results from professional experts.

QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QA (2025.findings-emnlp)

Copied to clipboard

Jacob Dineen, Aswin Rrv, Qin Liu, Zhikun Xu, Xiao Ye, Ming Shen, Zhaonan Li, Shijie Lu, Chitta Baral, Muhao Chen, Ben Zhou

Explainability & Interpretability in NLP

Challenge:	QA-LIGN decomposes monolithic rewards into interpretable principle-specific evaluations . scalar rewards obscure which objectives drive the training signal .
Approach:	a new method decomposes monolithic rewards into interpretable principle-specific evaluations . QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate .
Outcome:	QA-LIGN reduces attack success rates by up to 68.7% while maintaining a 0.67% false refusal rate . the results outperform DPO and GRPO with state-of-the-art reward models given equivalent training .

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective (2023.eacl-main)

Copied to clipboard

Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Youxin Chen, Jing Xiao, Jey Han Lau, Qian Zhang, Zheng Lu

Visual Data in NLP

Challenge:	Recent VSE models combine simple pooling methods with hard triplet loss to improve performance.
Approach:	They propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods.
Outcome:	The proposed strategy outperforms current state-of-the-art systems on image-to-text and text-toimage retrieval.

Towards More Accurate Uncertainty Estimation In Text Classification (2020.emnlp-main)

Copied to clipboard

Jianfeng He, Xuchao Zhang, Shuo Lei, Zhiqian Chen, Fanglan Chen, Abdulaziz Alhamadani, Bei Xiao, ChangTien Lu

Why Can Distillation Work with Limited Resources? A Systematic Study (2026.findings-acl)

Challenge:	Existing models of uncertainty score depend on winning score, which is the maximum probability in a semantic vector.
Approach:	They propose to generate accurate uncertainty score by improving the confidence of winning scores by reducing the effect of overconfidence of winning score and considering the impact of different categories simultaneously.
Outcome:	The proposed model reduces the effect of overconfidence of winning score and considers impact of different categories of uncertainty simultaneously.

Copied to clipboard

Xiao Hu, Xingyu Lu, Liyuan Mao, YiFan Zhang, Tianke Zhang, Bin Wen, Fan Yang, Tingting Gao, Guorui Zhou

Competition-Level Problems are Effective LLM Evaluators (2024.findings-acl)

Challenge:	Recent advances in large language models have driven reasoning performance . low-resource distillation can boost models' performance, but a framework is missing .
Approach:	They conduct a controlled experiment to find out why low-resource distillation can boost model performance . they find that distillation enhances the presence of advanced cognitive behaviors .
Outcome:	The proposed model shows more flexible reasoning, the authors show . they show that distillation enhances the presence of advanced cognitive behaviors .

Copied to clipboard

Yiming Huang, Zhenghao Lin, Xiao Liu, Yeyun Gong, Shuai Lu, Fangyu Lei, Yaobo Liang, Yelong Shen, Chen Lin, Nan Duan, Weizhu Chen

SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated impressive reasoning capabilities, yet there is ongoing debate about their capabilities and the potential data contamination problem.
Approach:	They propose to evaluate the reasoning capabilities of large language models in solving recent competition-level programming problems in Codeforces.
Outcome:	The proposed model has experienced a cliff-like decline in problems after September 2021, which shows the potential data contamination and the challenges for any existing LLM to solve unseen complex reasoning problems.

Copied to clipboard

Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Lintao Ma, Xingyu Lu, Jun Zhou, Pengfei Liu, Jiancan Wu, Xiang Wang

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications (2026.acl-long)

Challenge:	Existing large-scale large-context models suffer from performance degradation when processing long numerical sequences.
Approach:	They propose a framework to mitigate attention dispersion by strategically inserting separator tokens into the model to recalibrat attention to local segments while preserving global context.
Outcome:	The proposed framework improves accuracy and reduces inference token consumption by 16.4% on 9 widely-adopted LLMs.

Copied to clipboard

Xiaoyue Lu, Xianglin Yang, Haijun Liu, Jiahao Liu, Kuntai Cai, Yan Xiao, Jin Song Dong

Structured Data in NLP

Challenge:	Existing safety evaluation paradigms rely on constructed benchmarks or dynamic red-teaming to probe potential vulnerabilities.
Approach:	They propose a framework that integrates specification-based software testing with AI safety.
Outcome:	The proposed framework achieves higher coverage and attack success counts compared to baselines.

Are LLMs Capable of Data-based Statistical and Causal Reasoning? Benchmarking Advanced Quantitative Reasoning with Data (2024.findings-acl)

Copied to clipboard

Xiao Liu, Zirui Wu, Xueqing Wu, Pan Lu, Kai-Wei Chang, Yansong Feng