Papers by Yuan Yao

Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language Models (2024.findings-emnlp)

Challenge:	OpenGlass is an open-source, privacy-oriented, local-first system for low-latency multimodal visual assistance . cloud MLLM assistants offer strong visual understanding but often require uploading first-person visual data .
Approach:	They propose an open-source system for low-latency multimodal visual assistance . they use an ESP32-based glasses-side unit to capture visual context .
Outcome:	The proposed system captures visual context while a nearby device performs local MLLM inference and speech output.

Copied to clipboard

Kai Yao, Penglei Gao, Lichun Li, Yuan Zhao, Xiaofeng Wang, Wei Wang, Jianke Zhu

ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models (2026.acl-long)

Challenge:	Parameter-Efficient Fine-Tuning (PEFT) methods have gained popularity for adapting pre-trained Large Language Models (LLMs) to downstream tasks.
Approach:	They propose a method to optimize the importance of full layers with layer-wise importance scoring by leveraging the estimated importance scores.
Outcome:	The proposed method is compatible with PEFT methods that operate on a per-layer basis and achieves better performance.

Copied to clipboard

Jincheng Liu, Sijun He, Jingjing Wu, Xiangsen Wang, Yang Chen, Zhaoqi Kuang, Siqi Bao, Yuan Yao

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)

Challenge:	Existing evaluation frameworks focus on isolated question-answering tasks that may not capture the essential aspects of strategic reasoning.
Approach:	They evaluate 13 large language models across over 800 games in chess . they use a chessian-based framework to test strategic reasoning and pattern recognition .
Outcome:	The proposed framework improves performance and basic understanding of large language models.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning (2025.findings-naacl)

Challenge:	Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach:	They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome:	The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.

Copied to clipboard

Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

EventRAG: Enhancing LLM Generation with Event Knowledge Graphs (2025.acl-long)

Challenge:	Existing decoding strategies for chain-of-thought reasoning do not exploit prior information about question difficulty.
Approach:	They propose a decoding strategy called self-consistency to improve reasoning performance by adjusting the number of samples based on the posterior distribution of a set of pre-samples.
Outcome:	The proposed method outperforms baseline methods on arithmetic, commonsense and symbolic reasoning tasks while achieving comparable performance.

Copied to clipboard

Zairun Yang, Yilin Wang, Zhengyan Shi, Yuan Yao, Lei Liang, Keyan Ding, Emine Yilmaz, Huajun Chen, Qiang Zhang

R³A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platforms (2026.acl-industry)

Challenge:	Existing approaches to text generation often neglect event structures that shape real-world narratives.
Approach:	They propose a framework that integrates structured event semantics with iterative retrieval and inference to enhance text generation.
Outcome:	Experiments on UltraDomain and MultiHopRAG show that the proposed framework outperforms baseline RAG systems in generation effectiveness, logical consistency, and multi-hop reasoning accuracy.

Copied to clipboard

Xiaowei Yuan, Lei Jin, Haoxin Zhang, Ziyang Huang, Yan Gao, null Yiwu, Yao Hu, Jun Zhao, Kang Liu

Rhetorical Questions in LLM Representations: A Linear Probing Study (2026.acl-long)

Challenge:	Existing approaches to query–document relevance assessment are limited . ambiguous user intent and asymmetric relevance are challenges for RAG platforms .
Approach:	They propose a decomposed reasoning model for relevance assessment that decomposes query intent into intent inference and evidence grounding.
Outcome:	The proposed model outperforms strong baselines on offline benchmarks and achieves significant gains in large-scale online A/B testing.

Copied to clipboard

Louie Hong Yao, Vishesh Anand, Yuan Zhuang, Tianyu Jiang

Semantic Text Processing

Challenge:	Rhetorical questions are asked not to seek information, but to persuade or signal stance . how large language models internally represent rhetorical questions remains unclear .
Approach:	They analyze rhetorical questions in LLM representations using linear probes on two social-media datasets with different discourse contexts.
Outcome:	The results show that rhetorical signals emerge early and are most stably captured by last-token representations.

QBridge: Bridging Natural Language and SQL via Gold Query Rewriting with Agentic Refinement (2026.acl-long)

Copied to clipboard

Zhensheng Luo, Sai Wu, Yuan Qiu, Chang Yao, Gang Chen, Xiu Tang

Programming Languages in NLP

Challenge:	Natural language to SQL (NL2SQL) is an intuitive interface for querying structured data . but real user questions are noisy, ambiguous, and weakly grounded to database semantics.
Approach:	They propose an agentic feedback-driven NL2SQL framework that bridges natural language and SQL via Gold Query.
Outcome:	The proposed framework outperforms strong prompting and agentic baselines on spider, BIRD, and three robustness variants on NL2SQL.

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

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

Meta-Information Guided Meta-Learning for Few-Shot Relation Classification (2020.coling-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

Bowen Dong, Yuan Yao, Ruobing Xie, Tianyu Gao, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Challenge:	Existing meta-learning models rely on implicit instance statistics and are unreliability and weak interpretability.
Approach:	They propose a meta-information guided meta-learning framework that uses semantics to guide meta- learning . experimental results demonstrate the effectiveness of the proposed framework .
Outcome:	The proposed framework can establish connections between instance-based information and semantic-based data, enabling faster initialization and adaptation.

Copied to clipboard

Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang

Hierarchical Attention Generates Better Proofs (2025.acl-long)

Challenge:	Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach:	They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome:	The proposed method achieves the strongest alignment-forging Pareto front among competing methods.

Copied to clipboard

Jianlong Chen, Chao Li, Yang Yuan, Andrew C Yao

Focused Large Language Models are Stable Many-Shot Learners (2024.emnlp-main)

Challenge:	Large language models (LLMs) have shown promise in formal theorem proving, but their token-level processing often fails to capture the inherent hierarchical nature of mathematical proofs.
Approach:	They propose a regularization method that aligns LLMs’ attention mechanisms with mathematical reasoning structures and establishes a five-level hierarchy from foundational elements to high-level concepts.
Outcome:	The proposed method improves proof success rates by 2.05% on miniF2F and 1.69% on ProofNet while reducing proof complexity by 23.81% and 16.50% respectively.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

InsBank: Evolving Instruction Subset for Ongoing Alignment (2025.findings-emnlp)

Challenge:	In-Context Learning (ICL) enables large language models to achieve rapid task adaptation by learning from demonstrations.
Approach:	They propose a training-free method that disperses model attention from the query . they propose 'focus' search strategy that uses model perplexity to ensure sufficient attention .
Outcome:	The proposed method achieves an average performance improvement of 5.2% over vanilla ICL and scales well with many-shot demonstrations.

Copied to clipboard

Jiayi Shi, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Huan Ren, Yao Hu, Kan Li

Green & Sustainable NLP

Challenge:	Recent studies emphasize that quality and diversity of instruction data are more crucial than quantity, highlighting the need to select diverse, high-quality subsets to reduce training costs.
Approach:	They propose to use a continuously updated repository to integrate the latest valuable instruction data with a progressive evolution framework to evolve InsBank over time.
Outcome:	The proposed framework outperforms baselines in InsBank evolution and extracts budget-specific subsets.

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation (2024.acl-long)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Xinglin Wang, Yiwei Li, Shaoxiong Feng, Peiwen Yuan, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution (2021.acl-long)

Challenge:	Existing methods to improve output quality without aggregating input tokens are limited by the complexity of aggregation of responses.
Approach:	They propose to extract and integrate segment-level commonalities from candidate samples to enhance performance of LLMs in open-ended and reasoning tasks.
Outcome:	The proposed method improves performance on reasoning, code generation and mathematical reasoning tasks without requiring additional models and overlooking the knowledge present among the candidates.

Copied to clipboard

Fanchao Qi, Yuan Yao, Sophia Xu, Zhiyuan Liu, Maosong Sun

Robustness in NLP

Challenge:	Recent studies show that neural natural language processing models are vulnerable to backdoor attacks.
Approach:	They propose to inject neural models with backdoors activated by word substitution . their results raise a serious alarm to the security of NLP models, they argue .
Outcome:	The proposed backdoors are activated by a learnable combination of word substitution and exhibit higher invisibility than previous methods.

Cognitive-Level Adaptive Generation via Capability-Aware Retrieval and Style Adaptation (2025.findings-emnlp)

Copied to clipboard

Qingsong Wang, Tao Wu, Wang Lin, Yueying Feng, Gongsheng Yuan, Chang Yao, Jingyuan Chen

Information Retrieval

Challenge:	Large Language Models struggle to adapt content to users with differing cognitive capacities, leading to cognitive misalignment.
Approach:	They propose a cognitive-level alignment framework that aligns both knowledge complexity and presentation style with user cognition.
Outcome:	The proposed framework aligns knowledge complexity and presentation style with user cognition.

Prompt Tuning for Discriminative Pre-trained Language Models (2022.findings-acl)

Copied to clipboard

Yuan Yao, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, Jianyong Wang

From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning, Efficiency and beyond (2024.lrec-tutorials)

Challenge:	Recent studies have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing tasks.
Approach:	They propose a prompt tuning framework that reformulates NLP tasks into a discriminative language modeling problem.
Outcome:	The proposed framework improves on text classification and question answering tasks and prevents unstable tuning problems in low-resource settings.

Copied to clipboard

Hao Fei, Yuan Yao, Zhuosheng Zhang, Fuxiao Liu, Ao Zhang, Tat-Seng Chua

PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models (2022.emnlp-main)

Challenge:	This tutorial aims to deliver a comprehensive review of cutting-edge research in MLLMs.
Approach:	This tutorial will review cutting-edge research in MLLMs and examine the impact of ML in learning and reasoning.
Outcome:	This course will review cutting-edge research in MLLMs and examine the impact of ML models on learning, learning, and multimodal reasoning.

Copied to clipboard

Yuan Yao, Qianyu Chen, Ao Zhang, Wei Ji, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun

Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO (2026.acl-long)

Challenge:	Recent advances on self-supervised learning have led to powerful vision-language pre-training models that achieve state-of-the-art performance on a wide range of cross-modal tasks.
Approach:	They propose a vision-language pre-training framework that reformulates discretized object positions and language in a unified language modeling framework.
Outcome:	The proposed model improves performance on position-sensitive vision-language (VL) tasks and also improves on position insensitive tasks.

Copied to clipboard

Jinquan Zheng, Jia Yuan, Jiacheng Yao, Chenyang Gu, Pujun Zheng, Guoxiu He

OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction (D19-3)

Challenge:	Existing inference-time debiasing ignores that the same question should yield consistent answers across permutations.
Approach:	They propose a permutation-aware group-relative policy optimization which enforces permutations-consistent semantic reasoning.
Outcome:	The proposed model outperforms strong baselines across seven benchmarks while maintaining high overall performance.

Copied to clipboard

Xu Han, Tianyu Gao, Yuan Yao, Deming Ye, Zhiyuan Liu, Maosong Sun

IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact (2024.findings-acl)

Challenge:	OpenNRE provides a framework to implement neural relation extraction (RE) . the toolkit provides various functional modules based on TensorFlow and PyTorch .
Approach:	OpenNRE is an open-source framework to implement neural relation extraction models. they also release an online system to meet real-time extraction without any training and deployment.
Outcome:	OpenNRE provides a framework to implement neural models for relation extraction (RE) the toolkit also includes an online system to meet real-time extraction without training and deployment .

Copied to clipboard

Ruikang Liu, Haoli Bai, Haokun Lin, Yuening Li, Han Gao, Zhengzhuo Xu, Lu Hou, Jun Yao, Chun Yuan

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks (2021.emnlp-main)

Challenge:	Existing quantization methods are compromising performance of large language models (LLMs) despite their high computational intensity, LLMs are still demanding intensive computation.
Approach:	They propose to generate the KV cache of pivot tokens losslessly from the full-precision model.
Outcome:	The proposed method generates the KV cache of pivot tokens losslessly from the full-precision model with no extra inference overhead.

Copied to clipboard

Fanchao Qi, Yangyi Chen, Mukai Li, Yuan Yao, Zhiyuan Liu, Maosong Sun

Robustness in NLP

Challenge:	Backdoor attacks can manipulate the output of deep neural networks and possess high insidiousness.
Approach:	They propose a textual backdoor defense based on outlier word detection that can handle all the textual attacks.
Outcome:	The proposed method can handle all the textual backdoor attack situations.

GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models (2025.acl-long)

Copied to clipboard

Kai Yao, Zhaorui Tan, Penglei Gao, Lichun Li, Kaixin Wu, Yinggui Wang, Yuan Zhao, Yixin Ji, Jianke Zhu, Wei Wang

FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)

Challenge:	Existing methods for offsite-tuning of large language models require high computational costs and lack theoretical analysis.
Approach:	They propose an offsite-tuning approach that selectively applies compression techniques such as rank compression and channel pruning to preserve the gradients of fine-tuned adapters while ensuring privacy.
Outcome:	The proposed method surpasses existing OT methods in privacy protection and model performance.

Copied to clipboard

Xu Han, Hao Zhu, Pengfei Yu, Ziyun Wang, Yuan Yao, Zhiyuan Liu, Maosong Sun

Low-Resource NLP

Challenge:	Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans.
Approach:	They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers.
Outcome:	The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans.

Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation (2025.acl-long)

Copied to clipboard

Peiwen Yuan, Yueqi Zhang, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Green & Sustainable NLP

Challenge:	Existing efficient methods estimate performance of models on large benchmarks, but these methods rely on the assumption that target models have high prediction consistency with source models.
Approach:	They propose a method that conducts customized evaluation tailored to each target model.
Outcome:	The proposed method reduces the MAE of estimates by 31.4% on benchmarks across 300 models.

LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Merging (2025.findings-emnlp)

Copied to clipboard

Zehua Liu, Han Wu, Yuxuan Yao, Xiaojin Fu, Ruifeng She, Xiongwei Han, Tao Zhong, Mingxuan Yuan

Semantic Text Processing

Challenge:	a framework for model merging is proposed without additional training . task vectors from fine-tuned models exhibit a limited number of dominant singular values .
Approach:	They propose a framework for model merging based on low-rank estimation of task vectors without access to the base model.
Outcome:	The proposed framework improves models without additional training without additional inputs.

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)

Copied to clipboard

Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)

Challenge:	Current outcome-centric verification paradigms neglect potential errors in the derivation process.
Approach:	They propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
Outcome:	The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models.

Copied to clipboard

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts (2025.findings-acl)

Challenge:	Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities.
Approach:	They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments.
Outcome:	The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments.

Copied to clipboard

Yifan Zhang, Yifan Luo, Yang Yuan, Andrew C Yao

Numerical Reasoning

Challenge:	Existing methods that require human annotations or training a dedicated data filter to curate high-quality mathematical texts are based on autonomous data selection.
Approach:	They propose a method that leverages base language models as zero-shot "generative classifiers" they use a model's logits to determine whether a given passage is mathematically informative and educational .
Outcome:	The proposed method significantly boosts downstream performance on math benchmarks while using far fewer tokens than previous methods.

Open Hierarchical Relation Extraction (2021.naacl-main)

Copied to clipboard

Kai Zhang, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

Open Relation Extraction: Relational Knowledge Transfer from Supervised Data to Unsupervised Data (D19-1)

Challenge:	Existing OpenRE methods cast different relation types in isolation without considering their hierarchical dependency.
Approach:	They propose a framework to establish bidirectional connections between OpenRE and relation hierarchies by integrating hierarchy information into relation representations.
Outcome:	The proposed framework outperforms state-of-the-art models on relation clustering and hierarchy expansion.

Copied to clipboard

Ruidong Wu, Yuan Yao, Xu Han, Ruobing Xie, Zhiyuan Liu, Fen Lin, Leyu Lin, Maosong Sun

MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension (2024.findings-emnlp)

Challenge:	Existing methods to extract relational facts from open domain corpora are time-consuming and human-intensive.
Approach:	They propose a framework to learn similarity metrics of relations from labeled data . they propose to transfer relational knowledge to identify novel relations in unlabeled data.
Outcome:	Experiments on two real-world datasets show that the proposed framework improves compared with state-of-the-art methods.

Copied to clipboard

Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, Yu Li

Question Answering

Challenge:	Existing models generate erroneous information and evaluations fail to assess factual correctness of models.
Approach:	They propose to use MoleculeQA to evaluate molecular factual correctness in large language models by organizing molecules into a taxonomy and building QA pairs through human and LLM efforts.
Outcome:	The proposed model improves the factual correctness of generated information and enables the development of new models.

CogLM: Tracking Cognitive Development of Large Language Models (2025.naacl-long)

Copied to clipboard

Xinglin Wang, Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have recently shown remarkable abilities across a wide variety of tasks, but few studies have explored the reasons behind the evolutionary relationship among various abilities.
Approach:	They construct a benchmark CogLM based on Piaget's Theory of Cognitive Development (PTC) which measures the cognitive levels of Large Language Models (LLMs) using 1,220 questions spanning 10 cognitive abilities crafted by more than 20 human experts.
Outcome:	The proposed framework provides a comprehensive testbed for the cognitive levels of LLMs.

Copied to clipboard

Zhuo Li, Guodong DU, Zesheng Shi, Weiyang Guo, Weijun Yao, Yuan Zhou, Jiabo Zhang, Jing Li

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) can specialize under fixed memory and inference budgets, but they struggle to achieve high performance across heterogeneous domains.
Approach:	They propose a modular improvement framework that partitions full capabilities of a general-purpose model into domain-specific delta modules that reorganize and refine the model's internal knowledge.
Outcome:	The proposed framework outperforms monolithic models on multi-task and agentic benchmarks and achieves up to 4 speedup.

GUICourse: From General Vision Language Model to Versatile GUI Agent (2025.acl-long)

Copied to clipboard

Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan Yao, Yankai Lin, Zhiyuan Liu, Maosong Sun

Visual Data in NLP

Challenge:	Graphical User Interfaces (GUIs) are a pivotal medium for human-computer interaction.
Approach:	They propose a series of datasets for training visual-based GUI agents using general VLMs.
Outcome:	The proposed GUICourse datasets show that even a small-sized GUI agent performs better on GUI tasks.

Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Copied to clipboard

Yiwei Li, Jiayi Shi, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Yueqi Zhang, Ji Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

Denoising Relation Extraction from Document-level Distant Supervision (2020.emnlp-main)

Challenge:	Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach:	They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome:	The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.

Copied to clipboard

Chaojun Xiao, Yuan Yao, Ruobing Xie, Xu Han, Zhiyuan Liu, Maosong Sun, Fen Lin, Leyu Lin

Fine-Grained Legal Argument-Pair Extraction via Coarse-Grained Pre-training (2024.lrec-main)

Challenge:	Existing methods to generate auto-labeled sentences for relation extraction (RE) are difficult to extend to document-level relation extraction as noise from DS may be even multiplied in documents.
Approach:	They propose a pre-trained model which de-emphasizes noisy DS data via multiple pre-training tasks.
Outcome:	The proposed model can capture useful information from noisy data and achieve promising results on the large-scale DocRE benchmark.

Copied to clipboard

Chaojun Xiao, Yutao Sun, Yuan Yao, Xu Han, Wenbin Zhang, Zhiyuan Liu, Maosong Sun

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Challenge:	Current methods conceptualize LAE as a supervised sentence-pair classification problem and necessitate extensive manual annotations.
Approach:	They propose a model that focuses on fine-grained alignment of argument pairs building upon coarse-grain complaint-defense pairs.
Outcome:	The proposed model outperforms baseline models by 3.7 and 2.4 points on average.

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild (2021.emnlp-main)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

Yuan Yao, Jiaju Du, Yankai Lin, Peng Li, Zhiyuan Liu, Jie Zhou, Maosong Sun

From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGen (2025.acl-long)

Challenge:	Existing relation extraction methods focus on extracting relational facts between entity pairs within single sentences or documents.
Approach:	They present a problem of cross-document relation extraction (CRE) using human annotations.
Outcome:	The proposed dataset is the first human-annotated cross-document RE dataset . it shows that it is challenging to existing RE methods including strong BERT-based models.

Copied to clipboard

Peiwen Yuan, Chuyi Tan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Boyuan Pan, Yao Hu, Kan Li

Challenge:	Existing methods to control text length are lacking in LCTG, posing a major limitation for practical applications.
Approach:	They propose a plug-and-play approach that decomposes LCTG sub-abilities with human patterns as reference and performs detailed error analysis.
Outcome:	The proposed method significantly improves LCTG across various settings, exhibiting outstanding effectiveness and generalizability.

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Copied to clipboard

Yiwei Li, Ji Zhang, Shaoxiong Feng, Peiwen Yuan, Xinglin Wang, Jiayi Shi, Yueqi Zhang, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service (2025.findings-acl)

Challenge:	Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach:	They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome:	The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.

Copied to clipboard

Yihang Cheng, Lan Zhang, Junyang Wang, Mu Yuan, Yunhao Yao

PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes (2024.findings-emnlp)

Challenge:	Large language models (LLMs) have a tendency to generate factually incorrect or purely fictional responses, a phenomenon known as hallucination.
Approach:	They propose to use remote RAG to protect user query from privacy leakage . they introduce (n,)-DistanceDP to characterize privacy leakages of user query .
Outcome:	The proposed solution can resist embedding inversion attacks while achieving no loss in retrieval under various settings.

Copied to clipboard

He Cao, Yanjun Shao, Zhiyuan Liu, Zijing Liu, Xiangru Tang, Yuan Yao, Yu Li

Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions (2025.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have seen growing adoption across various scientific domains.
Approach:	They propose a framework that bridges the molecule-text modality gap by integrating a comprehensive benchmark of pretraining strategies and dataset configurations.
Outcome:	The proposed framework improves multimodal LLMs through cross-modal alignment and multi-graph understanding.

Copied to clipboard

Xinbei Ma, Yiting Wang, Yao Yao, Tongxin Yuan, Aston Zhang, Zhuosheng Zhang, Hai Zhao

P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models (2024.findings-acl)

Challenge:	Experimental results show that multimodal GUI agents are susceptible to environmental distractions.
Approach:	They propose a scenario where both user and agent are benign and environment is not malicious . they implement an adversarial environment injection and analyze the approach to improve faithfulness .
Outcome:	The proposed approach improves faithfulness of multimodal large language model agents in a graphical user interface environment.

Copied to clipboard

Shuo Yang, Chenchen Yuan, Yao Rong, Felix Steinbauer, Gjergji Kasneci

VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service (2025.acl-long)

Challenge:	Contemporary approaches to generate tabular data are limited due to the lack of external knowledge.
Approach:	They propose to use proximal policy optimization to apply GANs and fine-tune Large Language Models to enhance the probability distribution of tabular features.
Outcome:	The proposed method improves accuracy of GANs and LLMs over state-of-the-art over three real-world datasets.

Copied to clipboard

Xiasi Wang, Tianliang Yao, Simin Chen, Runqi Wang, Lei Ye, Kuofeng Gao, Yi Huang, Yuan Yao

i-Code Studio: A Configurable and Composable Framework for Integrative AI (2024.emnlp-demo)

Challenge:	Existing studies evaluate efficiency robustness of vision-language models under unrealistic assumptions, requiring access to model architecture and parameters.
Approach:	They propose a novel approach to evaluate VLM efficiency robustness in a realistic black-box setting.
Outcome:	The proposed approach generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%.

Copied to clipboard

Yuwei Fang, Mahmoud Khademi, Chenguang Zhu, Ziyi Yang, Reid Pryzant, Yichong Xu, Yao Qian, Takuya Yoshioka, Lu Yuan, Michael Zeng, Xuedong Huang

ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use (2025.acl-long)

Challenge:	Existing frameworks for Integrative AI lack flexibility and composability to handle multimodal tasks.
Approach:	They propose a configurable framework for Integrative AI that orchestrates multiple pre-trained models to conduct complex multimodal tasks.
Outcome:	The proposed framework achieves impressive results on zero-shot multimodal tasks . it can communicate and personalize for users, and it can be used in a multimodal agent .

Copied to clipboard

Junjie Ye, Zhengyin Du, Xuesong Yao, Weijian Lin, Yufei Xu, Zehui Chen, Zaiyuan Wang, Sining Zhu, Zhiheng Xi, Siyu Yuan, Tao Gui, Qi Zhang, Xuanjing Huang, Jiecao Chen

Chatbot To Help Patients Understand Their Health (2025.findings-emnlp)

Challenge:	Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models.
Approach:	They propose a dataset that provides rigorous evaluation of multi-hop tool use.
Outcome:	The proposed model achieves 49.04% accuracy across five model families.

Copied to clipboard

Won Seok Jang, Hieu Tran, Manav Shaileshkumar Mistry, Sai Kiran Gandluri, Yifan Zhang, Sharmin Sultana, Sunjae Kwon, Yuan Zhang, Zonghai Yao, Hong Yu

Dialogue Systems & Conversational Agents

Challenge:	NoteAid-Chatbot is a conversational AI designed to help patients better understand their health .
Approach:	They propose a new learning paradigm that leverages a multi-agent large language model and reinforcement learning framework without relying on costly human-generated training data.
Outcome:	The proposed framework surpasses non-expert human training methods.

Behavior Knowledge Merge in Reinforced Agentic Models (2026.acl-long)

Copied to clipboard

Xiangchi Yuan, Dachuan Shi, Chunhui Zhang, Zheyuan Liu, Shenglong Yao, Soroush Vosoughi, Wenke Lee

Challenge:	Existing methods for supervised fine-tuning (SFT) are suboptimal to preserve task-specific capabilities on RL-trained agentic models.
Approach:	They propose a distribution-aware merging framework specifically designed for RL-trained agentic models that disentangles shared and task-specific unique parameter updates while selectively preserving and rescaling unique ones.
Outcome:	Experiments across multiple agent domains and model architectures show that the proposed framework surpasses baselines and unlocks synergistic potential among agents.

PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models (2024.acl-long)

Copied to clipboard

Haoran Li, Dadi Guo, Donghao Li, Wei Fan, Qi Hu, Xin Liu, Chunkit Chan, Duanyi Yao, Yuan Yao, Yangqiu Song

Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models (2025.findings-naacl)

Challenge:	generative large language models (LLMs) exhibit surprising capability and integrate previous tasks into a unified text generation formulation.
Approach:	They propose a privacy evaluation benchmark to quantify the privacy leakage of language models.
Outcome:	The proposed benchmark compares PPLMs with different privacy implementations to find out how privacy leakage is handled.

Copied to clipboard

Weidi Luo, He Cao, Zijing Liu, Yu Wang, Aidan Wong, Bin Feng, Yuan Yao, Yu Li

Poor-Supervised Evaluation for SuperLLM via Mutual Consistency (2024.findings-acl)

Challenge:	Existing defense methods struggle with two key issues: inadequate defense capabilities and over-defensiveness.
Approach:	They propose a multi-agents-based framework that leverages accurate external information to provide an unbiased summary of user intentions and safety response guidance.
Outcome:	Experiments on popular jailbreak attacks and benign datasets show that the proposed framework can enhance LLM's robustness against jailbreaks without compromising its general functionality.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Boyuan Pan, Heda Wang, Yao Hu, Kan Li

Is Parameter Collision Hindering Continual Learning in LLMs? (2025.coling-main)

Challenge:	evaluating superLLMs is especially difficult because of their intelligence-intensive nature.
Approach:	They propose an evaluation benchmark with accurate labels for SuperLLMs whose capabilities surpass those of humans . they first prove that consistency between model under evaluation and reference model can equalize the true capabilities of the model to be evaluated .
Outcome:	The proposed evaluation benchmarks can assess the true capabilities of the model to be evaluated without accurate labels.

Copied to clipboard

Shuo Yang, Kun-Peng Ning, Yu-Yang Liu, Jia-Yu Yao, Yong-Hong Tian, Yi-Bing Song, Li Yuan

Semantic Text Processing

Challenge:	Existing methods to learn multiple tasks in parallel often lead to catastrophic forgetting, resulting in overwriting knowledge.
Approach:	They propose a non-collision low-rank Adaptation approach that leverages low collision rates to enhance continual learning (CL) in large language models.
Outcome:	The proposed approach achieves better task orthogonality and higher task orthognality than existing SOTA methods.

DocRED: A Large-Scale Document-Level Relation Extraction Dataset (P19-1)

Copied to clipboard

Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, Maosong Sun

InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery (2025.coling-main)

Challenge:	Existing relation extraction methods focus on extracting intra-sentence relations for single entities.
Approach:	They propose a relation extraction dataset from Wikipedia and Wikidata with three features . document-level relation extraction is a task to identify relational facts between entities .
Outcome:	The proposed dataset is the largest human-annotated dataset for document-level RE from plain text.

Copied to clipboard

He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, Yu Li