Papers by Kai Ma

Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models (2025.acl-long)

Challenge:	End-to-end speech-to speech (S2S) dialogue systems face key challenges in incorporating external knowledge into their models.
Approach:	They propose a framework that directly retrieves relevant textual knowledge from speech queries.
Outcome:	The proposed framework improves the performance of end-to-end speech-tospeech dialogue systems while achieving higher retrieval efficiency.

Copied to clipboard

Qika Lin, Tianzhe Zhao, Kai He, Zhen Peng, Fangzhi Xu, Ling Huang, Jingying Ma, Mengling Feng

Sarcasm-R1: Enhancing Sarcasm Detection through Focused Reasoning (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) are gaining popularity due to their lack of knowledge hallucination and lack of a coherent model.
Approach:	They propose a self-supervised quantized representation method to compress KG structural and semantic knowledge into discrete codes that align the format of language sentences.
Outcome:	The proposed framework outperforms existing unsupervised methods producing more distinguishable codes on KG link prediction and triple classification tasks.

Copied to clipboard

Qi Yang, Jingjie Zeng, Liang Yang, Kai Ma, Hongfei Lin

Sentiment Analysis

Challenge:	Existing methods for sarcasm detection are limited by supervised learning or prompt engineering . a new approach decomposes sarcasm detection into three dimensions: language, context, and emotion .
Approach:	They propose a method that decomposes sarcasm detection into three dimensions: language, context, and emotion.
Outcome:	The proposed method outperforms state-of-the-art methods in most cases.

ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)

Copied to clipboard

Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou

Challenge:	Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth.
Approach:	They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning.
Outcome:	The proposed framework outperforms existing methods on ICLR 2025 papers.

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models (2023.acl-long)

Copied to clipboard

Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang, Shiqing Ma

Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing (2020.acl-main)

Challenge:	Existing backdoor attacks against prompt-based learning involve injecting back doors into embedding layers or word embedders.
Approach:	They propose a backdoor attack against prompt-based learning that injects backdoors into embedding layers or word embeddable vectors.
Outcome:	The proposed backdoor attack outperforms two state-of-the-art models on six NLP tasks and three prompting strategies.

Copied to clipboard

Ruisheng Cao, Su Zhu, Chenyu Yang, Chen Liu, Rao Ma, Yanbin Zhao, Lu Chen, Kai Yu

RubricBench: Aligning Model-Generated Rubrics with Human Standards (2026.acl-long)

Challenge:	Existing semantic parsing frameworks rely on nontrivial human labor to generate canonical utterances.
Approach:	They propose a framework that uses an unsupervised paraphrase model to parse canonical utterances.
Outcome:	The proposed framework is effective and compatible with supervised training.

Copied to clipboard

Junyi Zhou, Qiyuan Zhang, Yufei Wang, Fuyuan Lyu, Yidong Ming, Can Xu, Qingfeng Sun, Kai Zheng, Peng Kang, Xue Liu, Chen Ma

Challenge:	Existing benchmarks lack discriminative complexity and ground-truth rubric annotations required for rigorous evaluation.
Approach:	They propose a curated benchmark with 1,147 pairwise comparisons to assess the reliability of rubric-based evaluation.
Outcome:	The proposed benchmarks show that they support diverse domains, exhibit discriminative ability, provide high-quality annotations, and include human-authored rubrics.

F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (2025.acl-long)

Copied to clipboard

Yushen Chen, Zhikang Niu, Ziyang Ma, Keqi Deng, Chunhui Wang, JianZhao JianZhao, Kai Yu, Xie Chen

Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review (2025.findings-acl)

Challenge:	Recent research in Text-to-Speech (TTS) has experienced great advancement . current models can synthesize speech for any given text and mimic the speaker of audio prompt.
Approach:	They propose a fully non-autoregressive text-to-speech system based on flow matching with Diffusion Transformer (DiT) without complex designs such as duration model, text encoder, and phoneme alignment, the text input is simply padded with filler tokens to the same length as input speech, and then denoising is performed for speech generation.
Outcome:	The proposed system achieves an inference RTF of 0.15, which is greatly improved compared to state-of-the-art diffusion-based models.

Copied to clipboard

Pei Fu, Tongkun Guan, Zining Wang, Zhentao Guo, Chen Duan, Hao Sun, Boming Chen, Qianyi Jiang, Jiayao Ma, Kai Zhou, Junfeng Luo

VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder (2024.findings-naacl)

Challenge:	Recent advances in vision-language models have unified perception and understanding tasks within Visual Question Answering paradigms.
Approach:	They propose to outline timeline, architecture, and pipeline of nearly all TIU MLLMs and review their performance on mainstream benchmarks.
Outcome:	The proposed models perform well on mainstream benchmarks and are compared with other models.

Copied to clipboard

Yueen Ma, DaFeng Chi, Jingjing Li, Kai Song, Yuzheng Zhuang, Irwin King

VRoPE: Rotary Position Embedding for Video Large Language Models (2025.emnlp-main)

Challenge:	generative diversity is a critical yet underexplored issue in natural language generation . previous approaches to enhance diversity of Transformer models have been limited by their latent variables .
Approach:	They propose a framework that bridges Transformer with VAE to enhance generative diversity.
Outcome:	The proposed framework improves generative diversity while maintaining generative quality.

Copied to clipboard

Zikang Liu, Longteng Guo, Yepeng Tang, Tongtian Yue, Junxian Cai, Kai Ma, Qingbin Liu, Xi Chen, Jing Liu

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Existing versions of Large Language Models (LLMs) lack a positional encoding strategy for video.
Approach:	They propose a new positional encoding method tailored for Video-LLMs that mitigates positional biases and ensures a more uniform distribution of spatial focus.
Outcome:	The proposed method outperforms existing versions of RoPE in video understanding and reasoning tasks.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

DisastQA: A Comprehensive Benchmark for Evaluating Question Answering in Disaster Management (2026.findings-acl)

Copied to clipboard

Zhitong Chen, Kai Yin, Xiangjue Dong, Chengkai Liu, Xiangpeng Li, Bo Li, Junwei Ma, Yiming Xiao, Ali Mostafavi, James Caverlee

Natural Language Interfaces

Challenge:	Existing benchmarks for question answering (QA) are lacking in a high-stakes environment.
Approach:	They propose a rigorously verified benchmark of 3,000 expert-annotated questions . they propose 'keypoint-based evaluation protocol' emphasizing factual completeness over verbosity .
Outcome:	Experiments with 20 models reveal substantial divergences from general-purpose models such as MMLU-Pro.

Sparsity-Accelerated Training for Large Language Models (2024.findings-acl)

Copied to clipboard

Da Ma, Lu Chen, Pengyu Wang, Hongshen Xu, Hanqi Li, Liangtai Sun, Su Zhu, Shuai Fan, Kai Yu

UnitCoder: Scalable Code Synthesis from Pre-training Corpora (2025.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated proficiency across various NLP tasks but often require additional training, such as continual pre-training and supervised fine-tuning.
Approach:	They propose to leverage sparsity in pre-trained LLMs to accelerate training by disregarding computations for unimportant neurons.
Outcome:	The proposed framework achieves comparable or superior performance to standard training while significantly accelerating the process.

Copied to clipboard

Yichuan Ma, Yunfan Shao, Peiji Li, Demin Song, Qipeng Guo, Linyang Li, Xipeng Qiu, Kai Chen

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

Challenge:	Large Language Models (LLMs) excel at code understanding and generation, yet code generation remains a challenge.
Approach:	They propose a model that supervises pre-training data quality through automatically generated unit tests while ensuring correctness via an iterative fix and refine flow.
Outcome:	The proposed model improves performance on a large dataset with high quality pre-training data.

Copied to clipboard

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

SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoning (2026.findings-acl)

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

Zheng Li, Qingxiu Dong, Jingyuan Ma, Di Zhang, Kai Jia, Zhifang Sui

Reasoning

Challenge:	Recent large reasoning models have shown exceptional performance on various tasks, but they consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency.
Approach:	They propose a self-adaptive reasoning strategy that automatically allocates budgets according to problem complexity and introduces GRPO for reinforcement learning to reduce output length.
Outcome:	The proposed model achieves an average response length compression of 61% on math reasoning tasks while maintaining accuracy.

Mixture of Heterogeneous Grouped Experts for Language Modeling (2026.acl-industry)

Copied to clipboard

Zhicheng Ma, Xiang Liu, Zhaoxiang Liu, Ning Wang, Yi Shen, Kai Wang, Shuming Shi, Shiguo Lian

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

Challenge:	Large Language Models (LLMs) based on Mixture-of-Experts (MoE) enforce uniform expert sizes, creating a rigidity that fails to align computational costs with varying token-level complexity.
Approach:	They propose a mixture of heterogeneous grouped experts (MoHGE) that allows for flexible, resource-aware expert combinations.
Outcome:	The proposed model matches the performance of existing Mixture-of-Experts architectures while maintaining balanced GPU utilization.

Copied to clipboard

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

Speech & Audio in NLP

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

AnyTrans: Translate AnyText in the Image with Large Scale Models (2024.findings-emnlp)

Copied to clipboard

Zhipeng Qian, Pei Zhang, Baosong Yang, Kai Fan, Yiwei Ma, Derek Wong, Xiaoshuai Sun, Rongrong Ji

Multilinguality

Challenge:	Recent advances in natural language processing and computer vision have made it possible to translate images with text in one language into equivalent images displaying that text translated into another language.
Approach:	They propose an all-encompassing framework for the task–In-Image Machine Translation (IIMT) that incorporates contextual cues from both textual and visual elements during translation.
Outcome:	The proposed framework can be constructed using open-source models and requires no training, making it highly accessible and expandable.

InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model (2025.findings-acl)

Copied to clipboard

Yuhang Zang, Xiaoyi Dong, Pan Zhang, Yuhang Cao, Ziyu Liu, Shengyuan Ding, Shenxi Wu, Yubo Ma, Haodong Duan, Wenwei Zhang, Kai Chen, Dahua Lin, Jiaqi Wang

Timely Machine: Awareness of Time Makes Test-Time Scaling Agentic (2026.acl-long)

Challenge:	Despite the promising performance of Large Vision Language Models, they sometimes generate incorrect outputs.
Approach:	They propose a multi-modal reward model that aligns LVLMs with human preferences.
Outcome:	The proposed model achieves excellent results on the latest multi-modal reward model benchmark and shows competitive performance on text-only reward model.

Copied to clipboard

Yichuan Ma, Linyang Li, Yongkang Chen, Peiji Li, Xiaozhe Li, Qipeng Guo, Dahua Lin, Kai Chen

Reasoning

Challenge:	Large language models (LLMs) tackle complex reasoning tasks, but test-time scaling is becoming expensive.
Approach:	They propose to redefine test-time as wall-clock time, where models dynamically adjust strategies based on time budgets.
Outcome:	The proposed model improves time budget awareness and boosts performance across Timely-Eval.

RePair: Automated Program Repair with Process-based Feedback (2024.findings-acl)

Copied to clipboard

Yuze Zhao, Zhenya Huang, Yixiao Ma, Rui Li, Kai Zhang, Hao Jiang, Qi Liu, Linbo Zhu, Yu Su

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)

Challenge:	Commercial-scale language models (LMs) have taken APR to unprecedented levels, but they are limited by parameters and humans interact with them through explicit prompts.
Approach:	They propose a method that utilizes process supervision to improve program repair by allowing users to input feedback from compilers and test cases.
Outcome:	The proposed method outperforms large outcome-based generation methods and is inspired by strategies used in programming competitions.

Copied to clipboard

Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu

GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Challenge:	a recent study shows that large language models have limited generalization in low-resource languages like Chinese.
Approach:	They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private .
Outcome:	The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language.

Copied to clipboard

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (D18-1)

Challenge:	GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach:	They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome:	The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.

Copied to clipboard

Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, Dragomir Radev

Programming Languages in NLP

Challenge:	Existing datasets for semantic parsing are too small in terms of number of programs for training modern data-intensive models.
Approach:	They propose a large-scale complex and cross-domain semantic parsing task for a database . they use a dataset with 10,181 questions and 5,693 unique complex SQL queries .
Outcome:	The proposed task is different from previous tasks because it uses the same database and program . the best model achieves only 9.7% exact matching accuracy on a database split setting.

Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL (2021.findings-acl)

Copied to clipboard

Zhi Chen, Lu Chen, Hanqi Li, Ruisheng Cao, Da Ma, Mengyue Wu, Kai Yu

Programming Languages in NLP

Challenge:	Recent work on Text-to-SQL for multi-turn dialogue has attracted great interest . current approaches mostly employ end-to end models and face data sparsity problems .
Approach:	They propose a decoupled multi-turn text-to-SQL framework where dialogue context is explicitly solved by an utterance rewrite model and a single-turn Text-toSQl parser are proposed.
Outcome:	The proposed method outperforms existing models on SParC and CoSQL datasets without annotated in-domain data.

Learning Autonomous Driving Tasks via Human Feedbacks with Large Language Models (2024.findings-emnlp)

Copied to clipboard

Yunsheng Ma, Xu Cao, Wenqian Ye, Can Cui, Kai Mei, Ziran Wang

FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models (2025.coling-main)

Challenge:	Existing systems focus on making autonomous driving decisions without human interaction, but human-like decision-making is still an important factor in designing autonomous driving systems.
Approach:	They propose a framework leveraging Large Language Models for learning human-centered driving decisions from diverse simulation scenarios and environments that incorporate human feedback.
Outcome:	The proposed framework can match baseline extensively trained reinforcement learning models in driving scenarios and store optimal driving programming policy using Retrieval Augmented Generation (RAG).

Copied to clipboard

Tao Fan, Guoqiang Ma, Yan Kang, Hanlin Gu, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang

SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering? (2026.findings-acl)

Challenge:	Recent research in large language models (LLMs) has focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLM to small language models at downstream clients.
Approach:	They propose a parameter-efficient federated mutual knowledge transfer framework for large and small language models that allows for token alignment and selective knowledge transfer between client-side LLMs and a server-side SLM.
Outcome:	The proposed framework enhances the performance of both LLMs and SLMs with clients' unique domain insights while preserving the server's LLM and client's unique domain insight.

Copied to clipboard

Yuxuan Sun, Yuze Zhao, Yufeng Wang, Yao Du, Zhiyuan Ma, Jinbo Wang, Mengdi Zhang, Kai Zhang, Zhenya Huang

FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion (2026.acl-long)

Challenge:	Evaluating software engineering capabilities is a core component of large language models (LLMs).
Approach:	They propose a benchmark to evaluate LLM-generated test suites that introduces mutated solutions that attempt to "fool" them.
Outcome:	The proposed test suites are based on 2,636 mutated variants derived from 800 original instances and include a multilingual subset spanning nine programming languages.

Copied to clipboard

Tao Fan, Guoqiang Ma, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang

Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks (2021.acl-long)

Challenge:	Existing methods for fine-tuning Large Language Models (LLMs) suffer from a performance bottleneck . Existing approaches like Offsite-Tuning (OT) secure the LLMs IP .
Approach:	They propose a framework that replaces weak adapters with a unified, powerful Proxy Small Language Model (SLM) they propose 'resource-friendly' compression and 'robust optimization' to handle data heterogeneity.
Outcome:	Experiments show that FedProxy outperforms OT and centralized fine-tuning methods.

Copied to clipboard

Weicheng Ma, Kai Zhang, Renze Lou, Lili Wang, Soroush Vosoughi

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models (2026.acl-long)

Challenge:	Prior research has found that only a few attention heads are important in each mono-lingual NLP task and pruning the remaining heads leads to comparable or improved performance of the model.
Approach:	They examine the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks.
Outcome:	The proposed model performs better with the remaining heads pruned than with the other models, the authors show .

Copied to clipboard

Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun, Tian Xia, Kai Chen, Xiaofeng Wang, Baosheng Wang

BrowseComp-Plus: A Fair and Disentangled Evaluation Benchmark for Deep Search Agents (2026.acl-long)

Challenge:	Large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, but reliable evaluation remains a challenge due to data contamination, opaque operation, and subjective preferences.
Approach:	They propose a benchmark-free evaluation paradigm that organizes multiple LLMs into a self-governed league for multi-round mutual evaluation.
Outcome:	Experiments on eight mainstream LLMs in mathematics and programming show that the proposed model can distinguish capabilities while maintaining high internal ranking stability.

Copied to clipboard

Zijian Chen, Xueguang Ma, Shengyao Zhuang, Ping Nie, Kai Zou, Sahel Sharifymoghaddam, Andrew Liu, Joshua Green, Kshama Patel, Ruoxi Meng, Mingyi Su, Yanxi Li, Haoran Hong, Xinyu Shi, Xuye Liu, Hosna Oyarhoseini, Nandan Thakur, Crystina Zhang, Luyu Gao, Wenhu Chen, Jimmy Lin

Detecting Continuously Evolving Scam Calls under Limited Annotation: A LLM-Augmented Expert Rule Framework (2025.findings-emnlp)

Challenge:	Existing benchmarks for deep search agents rely on blackbox web search APIs . dynamic and opaque web APIs hinder reproducibility and fair comparisons - authors .
Approach:	They propose a benchmark that employs a fixed corpus for controlled retrieval for deep search agents.
Outcome:	The new benchmark shows that agents that combine large language models with retrieval tools excel at complex, reasoning-intensive queries.

Copied to clipboard

Haoyu Ma, Qinliang Su, Minhua Huang, Wu Kai

Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models (2026.findings-acl)

Challenge:	Existing methods to detect scam calls rely on labeled data and assume static distribution of scam narratives.
Approach:	They propose a method leveraging large language models to detect continuously evolving scam calls . scammers continuously evolve their tactics, making these methods less effective .
Outcome:	The proposed approach is based on large language models to detect continuously evolving scam calls.

Copied to clipboard

Qiyuan Zhang, Yufei Wang, Tianhe Wu, Can Xu, Qingfeng Sun, Kai Zheng, Xue Liu, Chen Ma

Reasoning

Challenge:	Recent advances in Generative Reward Models have demonstrated that scaling the length of Chain-of-Thought reasoning enhances reliability of evaluation.
Approach:	They propose a framework that reconfigures raw rationales into structured Breadth-CoT and Depth-Co T through a modular synthesis pipeline.
Outcome:	The proposed framework surpasses open-source RMs by an average of 8.2%.

URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models (2025.findings-emnlp)

Copied to clipboard

Ruiqi Yan, Xiquan Li, Wenxi Chen, Zhikang Niu, Chen Yang, Ziyang Ma, Kai Yu, Xie Chen

Speech & Audio in NLP

Challenge:	a lack of comprehensive evaluations for SDMs in speech-to-speech (S2S) scenarios is a major challenge for end-to end spoken dialogue models.
Approach:	They propose to provide an extensive evaluation framework for end-to-end spoken dialogue models (SDMs) that includes both cognitive dimensions and paralinguistic cues .
Outcome:	The proposed benchmark is divided into two difficulty levels: basic track and pro track, each comprising 20 test sets, evaluating the spoken dialogue model’s abilities in Understanding, Reasoning, and O**ral conversation.

GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks (2021.emnlp-main)

Copied to clipboard

Weicheng Ma, Renze Lou, Kai Zhang, Lili Wang, Soroush Vosoughi

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

Challenge:	A key problem in multi-task learning (MTL) research is how to select high-quality auxiliary tasks automatically.
Approach:	They propose an automatic auxiliary task selection method based on gradient calculation in Transformer-based models that improves MT-DNN performance.
Outcome:	The proposed method improves MT-DNN performance on 8 natural language understanding (GLUE) tasks, while costing less than AUTOSEM and comparable GPU consumption.

Copied to clipboard

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

Text Generation

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.

Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage Retrieval (2021.emnlp-main)

Copied to clipboard

Xueguang Ma, Minghan Li, Kai Sun, Ji Xin, Jimmy Lin

Sound Signal Processing with Seq2Tree Network (L18-1)

Challenge:	Dense passage retrieval improves ranking accuracy in open-domain question answering but at the cost of large space and memory requirements.
Approach:	They propose a simple unsupervised pipeline that includes principal component analysis (PCA), product quantization, and hybrid search to improve space efficiency.
Outcome:	The proposed pipeline achieves good accuracy–space trade-offs, for example, 48 compression with less than 3% drop in top-100 retrieval accuracy on average or 96 compression without drop in space requirements.

Copied to clipboard

Weicheng Ma, Kai Cao, Zhaoheng Ni, Peter Chin, Xiang Li

MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space (2025.findings-acl)

Challenge:	Recent LSTM models have been used to model sequential data processing tasks because of their ability to preserve previous information weighted on distance.
Approach:	They propose to use a tree-structured tree-based neural network architecture to solve the problem of unbalanced connections between data units inside and outside semantic groups.
Outcome:	The proposed model outperforms the state-of-the-art Bidirectional LSTM model on a signal and noise separation task.

Copied to clipboard

Yicheng Chen, Yining Li, Kai Hu, Ma Zerun, HaochenYe HaochenYe, Kai Chen

ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning (2024.emnlp-industry)

Challenge:	Existing methods for instruction-tuning datasets prioritize instance quality and use heuristic rules to maintain diversity.
Approach:	They propose a method that quantifies diversity based on the distribution of information within a label graph.
Outcome:	The proposed method outperforms state-of-the-art methods on 5% Tulu3 datasets and base models.

Copied to clipboard

Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Jinhua Zhao, Zhan Zhao, Wei Ma

MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers (2026.acl-long)

Challenge:	Existing urban itinerary planning studies focus on traditional tourism, but they lack the precision and accuracy needed to create a personalized itinerary.
Approach:	They propose an open-domain urban itinerary planning system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs.
Outcome:	The proposed system can generate personalized urban itineraries based on user needs and scale with existing methods.

Copied to clipboard

Linrui Ma, Chun Hei Lo, Xinyu Wang, Peng Lu, Xihao Yuan, Hanting Chen, Kai Han, Xinghao Chen, Chengjun Zhan, Hanlin xu, Yichun Yin, Lifeng Shang, Feng Wen, Boxing Chen, Yufei Cui

ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference (2022.findings-acl)

Challenge:	Existing approaches to improve efficiency often enforce rigid structural constraints such as local attention windows.
Approach:	They propose a framework that augments sparse-attention mechanisms with dynamically integrated in-context information through an efficient retrieval system.
Outcome:	Empirical results show that MATCH significantly improves the performance of sparse-attention models on synthetic and real-world natural-language tasks.

Copied to clipboard

Kai Hui, Honglei Zhuang, Tao Chen, Zhen Qin, Jing Lu, Dara Bahri, Ji Ma, Jai Gupta, Cicero Nogueira dos Santos, Yi Tay, Donald Metzler