Papers by Su Wang

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Challenge:	Current evaluations of FEC models that depend on factuality metrics are not reliable and detailed enough.
Approach:	They propose a fine-grained evaluation framework that automatically evaluates FEC models on different error categories.
Outcome:	The proposed evaluation framework compares models on different error categories and finds the best training modes and significant differences in the performance of existing models.

Copied to clipboard

Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts (2026.acl-long)

Copied to clipboard

Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang, Ke Wang, Jinbo Su, Mengshu Sun, Lei Liang, Jing Zhang

Challenge:	Existing methods for storing key-value caches during long-horizon rollouts cause performance collapses.
Approach:	They propose a new training paradigm that empowers stable RL training under sparse rollouts.
Outcome:	The proposed model reduces rollout overhead while maintaining the performance.

CoRanking: Collaborative Ranking with Small and Large Ranking Agents (2025.findings-emnlp)

Copied to clipboard

Wenhan Liu, Xinyu Ma, Yutao Zhu, Lixin Su, Shuaiqiang Wang, Dawei Yin, Zhicheng Dou

Generating Commonsense Reasoning Questions with Controllable Complexity through Multi-step Structural Composition (2025.coling-main)

Challenge:	Listwise ranking based on Large Language Models (LLMs) has achieved state-of-the-art performance in Information Retrieval (IR) however, their effectiveness often depends on LLMs with massive parameter scales and computationally expensive sliding window processing, leading to substantial efficiency bottlenecks.
Approach:	They propose a Collaborative Ranking framework (CoRanking) for LLM-based listwise ranking based on large language models with massive parameter scales and computationally expensive sliding window processing.
Outcome:	The proposed framework reduces ranking latency by approximately 70% while improving effectiveness compared to the standalone large reranker.

Copied to clipboard

Jianxing Yu, Shiqi Wang, Hanjiang Lai, Wenqing Chen, Yanghui Rao, Qinliang Su, Jian Yin

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models (2026.acl-long)

Challenge:	Existing work mainly learns to map text into questions, lacking a mechanism to control results with desired complexity.
Approach:	They propose a novel controllable framework to generate QGs with desired complexity using contextual and commonsense clues from text.
Outcome:	The proposed framework can generate complex questions with desired complexity levels.

Copied to clipboard

Zhiwen Ruan, Yichao Du, Jianjie Zheng, Longyue Wang, Yun Chen, Peng Li, Jinsong Su, Yang Liu, Guanhua Chen

Self-Taught Agentic Long Context Understanding (2025.acl-long)

Challenge:	Existing adapter-based transfer methods treat instruction-tuned models as passive targets . direct fine-tuning can disrupt this delicate balance and lead to instability or performance degradation.
Approach:	They propose a framework that incorporates instruction-level guidance into task adaptation.
Outcome:	The proposed framework outperforms direct fine-tuning and representative transfer-based baselines while maintaining robust generalization and favorable test-time scaling behavior.

Copied to clipboard

Yufan Zhuang, Xiaodong Yu, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Jingbo Shang, Zicheng Liu, Emad Barsoum

A Sequence-to-Sequence&Set Model for Text-to-Table Generation (2023.findings-acl)

Challenge:	Extensive experiments across seven long-context tasks demonstrate that AgenticLU significantly outperforms state-of-the-art prompting methods and specialized long-consumer LLMs.
Approach:	They propose a framework to enhance an LLM's understanding of long-context questions by integrating targeted self-clarification with contextual grounding within an agentic workflow.
Outcome:	The proposed framework outperforms state-of-the-art prompting methods and specialized long-context LLMs in seven long-constitut tasks.

Copied to clipboard

Tong Li, Zhihao Wang, Liangying Shao, Xuling Zheng, Xiaoli Wang, Jinsong Su

MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation (2025.coling-main)

Challenge:	Existing models for text-to-table generation are order-insensitive, but suffer from errors . a novel sequence-tosequence&set model generates table body rows in parallel .
Approach:	They propose a sequence-to-sequence generation task that serializes each table into a token sequence during training by concatenating all rows in a top-down order.
Outcome:	The proposed model outperforms baselines on commonly-used datasets.

Copied to clipboard

Yihang Wang, Bowen Tian, Yueyang Su, Yixing Fan, Jiafeng Guo

Question Answering

Challenge:	Existing methods for QA data generation are limited by the dependence of existing evaluation metrics on ground truth labels.
Approach:	They propose a set of unsupervised evaluation metrics for QA data that enable multidimensional assessment based on the relationships among context,question and answer.
Outcome:	The proposed method outperforms state-of-the-art methods on public datasets and shows that it produces high-quality and domain-specific QA pairs.

Confidence Based Bidirectional Global Context Aware Training Framework for Neural Machine Translation (2022.acl-long)

Copied to clipboard

Chulun Zhou, Fandong Meng, Jie Zhou, Min Zhang, Hongji Wang, Jinsong Su

M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection (2024.eacl-long)

Challenge:	Existing studies focus on how to effectively exploit bidirectional global contexts in neural machine translation models.
Approach:	They propose a Confidence Based Bidirectional Global Context Aware training framework for NMT . they incorporate bidirectional global context to the NMT model on unconfidently-predicted target words .
Outcome:	The proposed framework improves the NMT model on three large-scale translation datasets by +1.02, +0.57 BLEU scores.

Copied to clipboard

Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Chenxi Whitehouse, Osama Mohammed Afzal, Tarek Mahmoud, Toru Sasaki, Thomas Arnold, Alham Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov

Self-Consistency Boosts Calibration for Math Reasoning (2024.findings-emnlp)

Challenge:	Large language models generate fluent responses to user queries, but they are also susceptible to misuse in journalism, education, and academia.
Approach:	They propose a large-scale benchmark for machine-generated text detection that is a multi-generator, multi-domain, and multi-lingual corpus.
Outcome:	The proposed system can detect machine-generated text and pinpoint misuse . the proposed system is based on a large-scale benchmark dataset .

Copied to clipboard

Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu

Leveraging Dependency Forest for Neural Medical Relation Extraction (D19-1)

Challenge:	Existing solutions for math reasoning tasks use semantic parsing or AST decoding, but performance can degrade dramatically even with slight changes to the questions.
Approach:	They propose three calibration methods based on self-consistency for math reasoning tasks.
Outcome:	The proposed methods bridge model confidence and accuracy better than existing methods based on p(True) or logit.

Copied to clipboard

Linfeng Song, Yue Zhang, Daniel Gildea, Mo Yu, Zhiguo Wang, Jinsong Su

QueryForm: A Simple Zero-shot Form Entity Query Framework (2023.findings-acl)

Challenge:	Existing methods for medical relation extraction use dependency syntax as a source of features.
Approach:	They propose a method to extract relational information from medical literature by using dependency forests.
Outcome:	The proposed method outperforms the standard tree-based methods in the medical domain.

Copied to clipboard

Zifeng Wang, Zizhao Zhang, Jacob Devlin, Chen-Yu Lee, Guolong Su, Hao Zhang, Jennifer Dy, Vincent Perot, Tomas Pfister

Su Wang, Eric Holgate, Greg Durrett, Katrin Erk

Challenge:	Form-like document understanding is a key yet under-investigated problem . endlessly training specialized models on new document types is not scalable in many practical scenarios.
Approach:	They propose to use large-scale query-entity pairs generated from form-like webpages to pre-train QueryForm.
Outcome:	The proposed framework sets state-of-the-art average F1 score on XFUND and Payment benchmarks.

Picking Apart Story Salads (D18-1)

Copied to clipboard

Text Clustering

Challenge:	Story salads are mixtures of multiple documents that can be generated at scale . they exhibit challenging inference problems, and require global context and coherence .
Approach:	They propose to generate salads that exhibit challenging inference problems by exploiting the Wikipedia hierarchy . they propose a task where the objective is to group sentences from the same narratives .
Outcome:	The proposed task is based on a novel, challenging clustering task using Wikipedia . it is difficult to identify relevant information and assemble it into coherent narratives .

In Plain Sight: Media Bias Through the Lens of Factual Reporting (D19-1)

Copied to clipboard

Lisa Fan, Marshall White, Eva Sharma, Ruisi Su, Prafulla Kumar Choubey, Ruihong Huang, Lu Wang

I-AM-G: Interest Augmented Multimodal Generator for Item Personalization (2024.emnlp-main)

Challenge:	lexical bias stems from content realization, or how things are said, but other forms of bias stem from content selection and organization.
Approach:	They use a dataset to analyze news articles annotated with 1,727 bias spans to investigate informational bias.
Outcome:	The proposed model shows that informational bias appears more frequently than lexical bias.

Copied to clipboard

Xianquan Wang, Likang Wu, Shukang Yin, Zhi Li, Yanjiang Chen, Hufeng Hufeng, Yu Su, Qi Liu

The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models (2026.acl-long)

Challenge:	e-commerce and recommender systems lack a framework for personalized generation . a new framework extracts tags from multimodal information of items that the user has interacted with .
Approach:	They propose a framework that extracts tags from multimodal information and rewrites item description . they then use a decoupled text-to-text and image-to image retriever to search for similar item text .
Outcome:	The proposed framework can generate results aligned with user preferences . it can be used in e-commerce and recommender systems to win over diverse user base .

Copied to clipboard

Yan Wang, Yitao Xu, Nanhan Shen, Jinyan Su, Jimin Huang, Zining Zhu

Challenge:	Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing.
Approach:	They propose a framework that analyzes routing behavior at the level of expert groups rather than individual experts.
Outcome:	The proposed framework analyzes routing behavior at the level of expert groups rather than individual experts.

Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training (2022.coling-1)

Copied to clipboard

Zhongjian Miao, Xiang Li, Liyan Kang, Wen Zhang, Chulun Zhou, Yidong Chen, Bin Wang, Min Zhang, Jinsong Su

DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback (2025.naacl-long)

Challenge:	Existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
Approach:	They propose an iterative scheduled data-switch training framework to mitigate this problem by injecting noise into authentic examples and indiscriminately exploiting two types of examples.
Outcome:	The proposed model outperforms several competitive benchmarks on four translation benchmarks.

Copied to clipboard

Jiao Sun, Deqing Fu, Yushi Hu, Su Wang, Royi Rassin, Da-Cheng Juan, Dana Alon, Charles Herrmann, Sjoerd Van Steenkiste, Ranjay Krishna, Cyrus Rashtchian

Sanitizing Large Language Models in Bug Detection with Data-Flow (2024.findings-emnlp)

Challenge:	Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user’s input text.
Approach:	They propose a training algorithm that trains T2I models to be faithful to the input text.
Outcome:	The proposed model improves both the semantic alignment and aesthetic appeal of two diffusion-based T2I models, evidenced by multiple benchmarks (+1.7% on TIFA, +2.9% on DSG1K, +3.4% on VILA aesthetic).

Copied to clipboard

Chengpeng Wang, Wuqi Zhang, Zian Su, Xiangzhe Xu, Xiangyu Zhang

DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection (2026.acl-long)

Challenge:	Large language models (LLMs) have potential in code reasoning tasks but the hallucination effect can compromise the reliability of bug reports.
Approach:	They propose a new schema of bug detection that enforces LLMs to emit data-flow paths in few-shot chain-of-thought prompting and validates them via the program-property decomposition.
Outcome:	The proposed approach achieves 91.03% precision and 74.00% recall upon synthetic benchmarks and boosts precision by 21.99% with the sanitization.

Copied to clipboard

Junchao Wu, Yefeng Liu, Chenyu Zhu, Hao Zhang, Zeyu Wu, Tianqi Shi, Yichao Du, Longyue Wang, Weihua Luo, Jinsong Su, Derek F. Wong

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

Challenge:	Existing detectors are limited in their ability to detect large language models generated content in multilingual environments.
Approach:	They propose a multilingual benchmark to evaluate advanced detectors across 8 dimensions to better align with real-world applications.
Outcome:	The proposed benchmark encompasses 8 languages commonly used in commercial contexts and collects human-written texts from 6 domains highly susceptible to LLM misuse.

Copied to clipboard

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

Explainability & Interpretability in NLP

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

Query-focused Scenario Construction (D19-1)

Copied to clipboard

Su Wang, Greg Durrett, Katrin Erk

An Evaluation Resource for Grounding Translation Errors (2025.findings-emnlp)

Challenge:	Stronger neural network models and harder synthetic training settings are important to achieve high performance.
Approach:	They propose a query-based system that extracts compatible sets of events from news data . stronger neural network models and harder synthetic training settings are important to achieve high performance .
Outcome:	The proposed system outperforms baselines on a human-curated dataset of scenarios about real-world news topics.

Copied to clipboard

Sujin Chen, Kang Wang, Zixuan Zhou, Xiangyu Duan, Wanqun Zhang, Hao Yang, Jinsong Su, Min Zhang

Explainability & Interpretability in NLP

Challenge:	Current fine-grained error analyses do not ground the errors to the reasons why the annotated text spans are erroneous.
Approach:	They use a bi-directional grounding scheme to ground erroneous text in two directions . if the error spans of both directions are consistent, the explanation is valid .
Outcome:	The proposed grounding process improves translation error detection significantly.

Towards Rationality in Language and Multimodal Agents: A Survey (2025.naacl-long)

Copied to clipboard

Bowen Jiang, Yangxinyu Xie, Xiaomeng Wang, Yuan Yuan, Zhuoqun Hao, Xinyi Bai, Weijie J Su, Camillo Jose Taylor, Tanwi Mallick

Dynamic Energy-Based Contrastive Learning with Multi-Stage Knowledge Verification for Event Causality Identification (2025.emnlp-main)

Challenge:	despite advances in language and multimodal agents, large language models lack rationality . despite their progress, large-scale models lack real-world grounding and feedback mechanisms .
Approach:	They propose to build more rational language and multimodal agents . they also examine what criteria define rationality in intelligent systems .
Outcome:	This paper assesses the state-of-the-art in language and multimodal agents . it also outlines open challenges and future research directions .

Copied to clipboard

Ya Su, Hu Zhang, Yue Fan, Guangjun Zhang, YuJie Wang, Ru Li, Hongye Tan

Exploiting Emotion-Semantic Correlations for Empathetic Response Generation (2023.findings-emnlp)

Challenge:	Existing methods for event causal identification rely on rule-based or random sampling strategies, which introduce spurious causal positives.
Approach:	They propose an ECI method enhanced by Dynamic Energy-based Contrastive Learning with multi-stage knowledge verification which generates high-quality contrastive samples and effectively suppresses spurious causal disturbances.
Outcome:	The proposed method outperforms state-of-the-art methods on two benchmarks.

Copied to clipboard

Zhou Yang, Zhaochun Ren, Wang Yufeng, Xiaofei Zhu, Zhihao Chen, Tiecheng Cai, Wu Yunbing, Yisong Su, Sibo Ju, Xiangwen Liao

CHisIEC: An Information Extraction Corpus for Ancient Chinese History (2024.lrec-main)

Challenge:	Empathetic response generation aims to generate empathetic responses by understanding the speaker’s emotional feelings from the language of dialogue.
Approach:	They propose a dynamical Emotion-Semantic Correlation Model (ESCM) which constructs dynamic emotion-semantics through the interaction of context and emotions.
Outcome:	The proposed model understands emotions more accurately and expresses fluent and informative empathetic responses.

Copied to clipboard

Xuemei Tang, Qi Su, Jun Wang, Zekun Deng

TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments (2025.findings-acl)

Challenge:	Historical and cultural heritage preservation is an important branch of digital humanities, where the rich tapestry of the past meets the cutting-edge tools of the digital age.
Approach:	They present a dataset to evaluate NER and RE tasks in ancient Chinese history . they use four distinct entity types and twelve relation types to identify them .
Outcome:	The "Chinese Historical Information Extraction Corpus" is a dataset from 13 dynasties spanning over 1830 years . the dataset encompasses four distinct entity types and twelve relation types .

Copied to clipboard

Yuheng Lu, Qian Yu, Hongru Wang, Zeming Liu, Wei Su, Yanping Liu, Yuhang Guo, Maocheng Liang, Yunhong Wang, Haifeng Wang

Challenge:	Existing GUI agents struggle to adapt to dynamic and interconnected nature of real-world digital environments, authors show .
Approach:	They propose a benchmark to evaluate the transferability of GUI agents across three key dimensions . transBench includes 15 app categories with diverse functionalities .
Outcome:	The proposed benchmark shows that existing GUI agents struggle to adapt to dynamic, interconnected environments.

SPAGBias: Uncovering and Tracing Structured Spatial Gender Bias in Large Language Models (2026.acl-long)

Copied to clipboard

Binxian Su, Haoye Lou, Shucheng Zhu, Weikang Wang, Ying Liu, Dong Yu, Pengyuan Liu

NOSE: Neural Olfactory-Semantic Embedding with Tri-Modal Orthogonal Contrastive Learning (2026.acl-long)

Challenge:	Large language models (LLMs) are being used in urban planning but there is concern that they reproduce or amplify such biases.
Approach:	They propose a framework to evaluate spatial gender bias in large language models . they use a taxonomy of 62 urban micro-spaces, a prompt library and three diagnostic layers .
Outcome:	The proposed framework identifies structured gender-space associations that go beyond the public-private divide, forming nuanced micro-level mappings.

Copied to clipboard

Yanyi Su, Hongshuai Wang, Zhifeng Gao, Jun Cheng

Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)

Challenge:	Existing representation methods fail to fully capture olfactory pathway . current approaches focus on isolated segments of the olefactory pathways .
Approach:	They propose a representation learning framework that aligns molecular structure, receptor sequence, and natural language description.
Outcome:	The proposed framework achieves state-of-the-art and excellent zero-shot generalization . it decouples contributions of molecular structure, receptor sequence, and natural language description .

Copied to clipboard

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Ningyu Zhang, Fei Huang, Wentao Zhang, Jingren Zhou

BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine Translation (2023.findings-acl)

Challenge:	Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments.
Approach:	They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts.
Outcome:	Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability.

Copied to clipboard

Liyan Kang, Luyang Huang, Ningxin Peng, Peihao Zhu, Zewei Sun, Shanbo Cheng, Mingxuan Wang, Degen Huang, Jinsong Su

A Survey of Pun Generation: Datasets, Evaluations and Methodologies (2025.findings-emnlp)

Challenge:	Existing datasets focus on captions describing images or videos, which are not large and diverse enough.
Approach:	They propose a large-scale video subtitle translation dataset to facilitate multi-modality machine translation.
Outcome:	The proposed dataset is 10 times larger than the widely used How2 and VaTeX datasets.

Copied to clipboard

Yuchen Su, Yonghua Zhu, Ruofan Wang, Zijian Huang, Diana Benavides-Prado, Michael J. Witbrock

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)

Challenge:	Pun generation aims to modify linguistic elements in text to produce humour or evoke double meanings.
Approach:	They propose to review pun generation datasets and methods across different stages . pun generation aims to produce humour or evoke double meanings .
Outcome:	This paper summarises both automated and human evaluation metrics used to assess the quality of pun generation.

Copied to clipboard

Yi Su, Jiayi Zhang, Shu Yang, Xinhai Wang, Lijie Hu, Di Wang

Explainability & Interpretability in NLP

Challenge:	Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis.
Approach:	They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts .
Outcome:	The proposed method bridges psychological value frameworks with neuron analysis in large language models.

FinBPM: A Framework for Portfolio Management-based Financial Investor Behavior Perception Model (2024.eacl-long)

Copied to clipboard

Zhilu Zhang, Procheta Sen, Zimu Wang, Ruoyu Sun, Zhengyong Jiang, Jionglong Su

Agent Laboratory: Using LLM Agents as Research Assistants (2025.findings-emnlp)

Challenge:	a portfolio management framework based on reinforcement learning is needed to optimize stock price movements.
Approach:	They propose a framework that takes irrational investment into account when calculating portfolio weights . they use financial text to analyze intrinsic value information of companies and time series data .
Outcome:	The proposed framework gains 13.26% returns over state-of-the-art models while controlling for risk.

Copied to clipboard

Samuel Schmidgall, Yusheng Su, Ze Wang, Ximeng Sun, Jialian Wu, Xiaodong Yu, Jiang Liu, Michael Moor, Zicheng Liu, Emad Barsoum

Programming Languages in NLP

Challenge:	Agent Laboratory is an autonomous LLM-based framework that can complete the entire research process.
Approach:	Agent Laboratory is an autonomous LLM-based framework that can complete the entire research process.
Outcome:	Agent Laboratory is an autonomous LLM-based framework that can complete the entire research process.

A Multi-Agent Framework with Automated Decision Rule Optimization for Cross-Domain Misinformation Detection (2025.emnlp-main)

Copied to clipboard

Hui Li, Ante Wang, Kunquan Li, Zhihao Wang, Liang Zhang, Delai Qiu, Qingsong Liu, Jinsong Su

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing methods for misinformation detection are limited by domain knowledge and expert experience.
Approach:	They propose a Multi-Agent Framework for cross-domain misinformation detection with Automated Decision Rule Optimization (MARO) they first employ multiple expert agents to analyze target-domain news, then introduce a question-reflection mechanism that guides expert agents for higher-quality analysis.
Outcome:	The proposed framework improves on a common dataset and shows that iteratively improves over existing methods.

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

Low-Resource Generation of Multi-hop Reasoning Questions (2020.acl-main)

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

Copied to clipboard

Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin

Low-Resource NLP

Challenge:	Existing methods to generate valid and fluent questions from text are limited and insufficient for training.
Approach:	They propose to generate multi-hop reasoning questions from the raw text in a low resource circumstance by deducing over multiple relations on several sentences in the text.
Outcome:	The proposed model can be applied to the task of machine reading comprehension and achieve significant performance improvements.

Distilling Large Embeddings via Hyperspherical Householder Quantization (2026.acl-long)

Copied to clipboard

Yihang Wang, Bin Wu, Yueyang Su, Tianfu Zhang, Yiqi Du, Lei Yu, Jiafeng Guo, Xueqi Cheng

Is He Extroverted? Identifying Missing Relevant Personas for Faithful User Simulation (2026.eacl-srw)

Challenge:	Existing methods for quantizing large embeddings rely on Euclidean quantization, which is poorly aligned with the angular geometry induced by contrastive embeddment training.
Approach:	They propose a geometry-aware distillation method that compresses large embeddings into short discrete representations via iterative Householder transformations on the unit hypersphere.
Outcome:	The proposed method reduces decoding cost and maintains strong semantic retrieval accuracy.

Copied to clipboard

Weiwen Su, Yuhan Zhou, Zihan Wang, Naoki Yoshinaga, Masashi Toyoda

Refine, Align, and Aggregate: Multi-view Linguistic Features Enhancement for Aspect Sentiment Triplet Extraction (2024.findings-acl)

Challenge:	Existing user simulation approaches focus on generating user-like responses in dialogue without verifying whether critical personas are supplied.
Approach:	They propose a task of identifying persona dimensions that are relevant but missing in simulating a user's reply for a given dialogue context.
Outcome:	The proposed model identifies persona dimensions that are relevant but missing in simulating a user’s response for a given dialogue context.

Copied to clipboard

Guixin Su, Mingmin Wu, Zhongqiang Huang, Yongcheng Zhang, Tongguan Wang, Yuxue Hu, Ying Sha

Sentiment Analysis

Challenge:	Aspect Sentiment Triplet Extraction (ASTE) aims to extract the triplets of aspect terms, their associated sentiment and opinion terms.
Approach:	They propose to use multi-view linguistic features enhancement to explore the prior indication effect in the “Refine, Align, and Aggregate” learning process to enhance aspect-opinion relations.
Outcome:	The proposed model achieves state-of-the-art on several benchmark datasets and is robust to state- of-the art constraints.

FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)

Copied to clipboard

Zhuohan Xie, Daniil Orel, Rushil Thareja, Dhruv Sahnan, Hachem Madmoun, Fan Zhang, Debopriyo Banerjee, Georgi Nenkov Georgiev, Xueqing Peng, Lingfei Qian, Jimin Huang, Jinyan Su, Aaryamonvikram Singh, Rui Xing, Rania Elbadry, Chen Xu, Haonan Li, Fajri Koto, Ivan Koychev, Tanmoy Chakraborty, Yuxia Wang, Salem Lahlou, Veselin Stoyanov, Sophia Ananiadou, Preslav Nakov

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

Challenge:	Existing benchmarks emphasize final numerical answers while neglecting intermediate reasoning steps.
Approach:	They propose a symbolic benchmark for verifiable Chain-of-Thought evaluation in finance . FINCHAIN spans 58 topics across 12 financial domains and three difficulty levels .
Outcome:	The proposed benchmark aims to bridge symbolic reasoning and factual verification.

Copied to clipboard

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

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

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

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

R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling (2021.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

Xiang Hu, Haitao Mi, Zujie Wen, Yafang Wang, Yi Su, Jing Zheng, Gerard de Melo

MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling (2025.findings-emnlp)

Challenge:	Existing models with stacked layers do not explicitly model hierarchical structure of language understanding.
Approach:	They propose a recursive Transformer model based on differentiable CKY style binary trees to emulate hierarchical composition process.
Outcome:	The proposed model can predict words given their left and right abstraction nodes.

Copied to clipboard

Zhaopeng Feng, Jiahan Ren, Jiayuan Su, Jiamei Zheng, Hongwei Wang, Zuozhu Liu

A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models (2024.emnlp-main)

Challenge:	MT-RewardTree provides a framework for constructing, evaluating, and deploying process reward models in machine translation (MT)
Approach:	They propose a method for automatically generating token-level preference pairs using approximate Monte Carlo Tree Search.
Outcome:	The proposed framework achieves state-of-the-art performance in token-level evaluation and sequence-level analysis.

Copied to clipboard

Zhihao Wang, Shiyu Liu, Jianheng Huang, Wang Zheng, YiXuan Liao, Xiaoxin Chen, Junfeng Yao, Jinsong Su

GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generation (2025.findings-emnlp)

Challenge:	Version updates are an indispensable requirement for Large Language Models . a large learning rate in the first stage and a complete learning decay process are crucial for version updates of LLMs.
Approach:	They propose a learning rate path switching training paradigm for version updates of Large Language Models.
Outcome:	The proposed paradigm reduces training cost to 58% when training four versions of LLMs compared to PTFS and CPT .

Copied to clipboard

Wen Ye, Zhaocheng Liu, Gui Yuwei, Tingyu Yuan, Yunyue Su, Bowen Fang, Chaoyang Zhao, Qiang Liu, Liang Wang

FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction (2022.acl-long)

Challenge:	Existing methods for text-to-image synthesis lack systematic error analysis and refinement strategies, resulting in limited reliability and effectiveness.
Approach:	They propose a plug-and-play multi-agent system called GenPilot that integrates error analysis, clustering-based adaptive exploration, fine-grained verification and a memory module for iterative optimization.
Outcome:	The proposed method improves text consistency and structural coherence on images with a plug-and-play system.

Copied to clipboard

Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, Tomas Pfister

ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)

Challenge:	Form-like document understanding is a surging research topic due to its practical applications . form documents have unique challenges stemming from their structural characteristics .
Approach:	They propose a structure-aware sequence model that leverages spatial relationships between tokens in a form for more precise attention score calculation.
Outcome:	The proposed model outperforms existing methods with a more compact model size and less pre-training data.

Copied to clipboard

Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen

Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval (2021.acl-long)

Challenge:	Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection.
Approach:	They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization.
Outcome:	The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models.

Copied to clipboard

Zijing Ou, Qinliang Su, Jianxing Yu, Bang Liu, Jingwen Wang, Ruihui Zhao, Changyou Chen, Yefeng Zheng

M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection (2024.acl-long)

Challenge:	Existing methods for document hashing combine only one of semantics and neighborhood information, lacking a theoretical principle to guide the integration process.
Approach:	They propose to encode neighborhood information with a graph-induced Gaussian distribution and integrate it with generative models.
Outcome:	The proposed model can be trained as efficiently as state-of-the-art methods on benchmark datasets.

Copied to clipboard

Yuxia Wang, Jonibek Mansurov, Petar Ivanov, Jinyan Su, Artem Shelmanov, Akim Tsvigun, Osama Mohammed Afzal, Tarek Mahmoud, Giovanni Puccetti, Thomas Arnold, Alham Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov

KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation (2020.emnlp-main)

Challenge:	Large Language Models (LLMs) have brought an unprecedented surge in machine-generated text (MGT) societal implications are posed by their potential misuse and lack of training data.
Approach:	They propose a benchmark to detect machine-generated text in multiple languages . they use multi-domain and multi-generator corpus to identify which model generated the text .
Outcome:	The proposed benchmark compares a multilingual, multi-domain and multi-generator corpus of MGTs with human-generated content.

Copied to clipboard

Wenhu Chen, Yu Su, Xifeng Yan, William Yang Wang

RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correction (2025.findings-emnlp)

Challenge:	Existing methods for data-to-text generation rely on labeled data, which is costly to acquire and limits their application to new tasks and domains.
Approach:	They propose to leverage pre-training and transfer learning to address this problem by leveraging a general knowledge-grounded generation model and a knowledge-based model.
Outcome:	The proposed model can generate knowledge-enriched text on a knowledge-grounded text corpus crawled from the web in three settings.

Copied to clipboard

Jinbo Su, Lingzhe Gao, Wei Li, Shihao Liu, Haojie Lei, Xinyi Wang, Yuanzhao Guo, Ke Wang, Daiting Shi, Dawei Yin

Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal (2024.acl-long)

Challenge:	Large language models (LLMs) exhibit remarkable capabilities across many tasks, but face critical challenges in the CSC scenario: (1) poor generalization to rare entities in open-domain searches; and (2) failure to adapt to temporal entity variations due to static parameters, resulting in serious over-correction issues.
Approach:	They propose a Chinese Spelling Check system with RAG and multi-task learning that integrates dynamic knowledge retrieval and entity-centric RAG to address rare entities.
Outcome:	The proposed system outperforms existing baselines in the CSC task and achieves a maximum improvement of +9.92% on the search scenario benchmark and +3.2% on the general-domain dataset.

Copied to clipboard

Jianheng Huang, Leyang Cui, Ante Wang, Chengyi Yang, Xinting Liao, Linfeng Song, Junfeng Yao, Jinsong Su

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent (2025.findings-emnlp)

Challenge:	Existing methods to train LLMs on previous training data are not feasible in real-world applications because of catastrophic forgetting.
Approach:	They propose a framework that uses the LLM to generate synthetic instances for rehearsal and refine the instance outputs based on the synthetic inputs.
Outcome:	The proposed framework achieves superior or comparable performance compared to conventional rehearsal-based approaches while being more data-efficient.

Copied to clipboard

Pengyu Zhu, Zhenhong Zhou, Yuanhe Zhang, Shilinlu Yan, Kun Wang, Sen Su

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)

Challenge:	a new method for detecting advanced backdoors is proposed to bypass safety audits.
Approach:	They propose a backdoor implantation strategy that introduces dynamic encryption to bypass safety audits.
Outcome:	The proposed method achieves an attack success rate approaching 100% while maintaining a detection rate of 0%.

Copied to clipboard

Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng

Challenge:	Existing studies on large language model-based agents focus on evaluation benchmarks without training support.
Approach:	They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents.
Outcome:	The proposed model performs poorly in a large-scale and challenging shopping environment in China.

WR-One2Set: Towards Well-Calibrated Keyphrase Generation (2022.emnlp-main)

Copied to clipboard

Binbin Xie, Xiangpeng Wei, Baosong Yang, Huan Lin, Jun Xie, Xiaoli Wang, Min Zhang, Jinsong Su

McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models (2025.findings-acl)

Challenge:	Experimental results show that keyphrase generation has serious calibration errors . ONE2SET generates short phrases summarizing an input document .
Approach:	They propose a paradigm for keyphrase generation that generates short phrases summarizing an input document.
Outcome:	The proposed model over-estimates tokens and makes it well-calibrated on common datasets.

Copied to clipboard

Tian Lan, Xiangdong Su, Xu Liu, Ruirui Wang, Ke Chang, Jiang Li, Guanglai Gao

Unified Grid Tagging Scheme for Aspect Sentiment Quad Prediction (2025.coling-main)

Challenge:	Existing datasets on bias evaluation for large language models focus on English and North American culture and are limited to one task.
Approach:	They propose to evaluate Chinese language models' biases from multiple perspectives using a multi-task Chinese Bias Evaluation Benchmark.
Outcome:	The proposed model covers 12, 82 subcategories and 5 evaluation tasks covering a wide range of categories and content diversity.

Copied to clipboard

Guixin Su, Yongcheng Zhang, Tongguan Wang, Mingmin Wu, Ying Sha

Syntactic Text Processing

Challenge:	Existing table-filling methods decompose the ASQP task into subtasks without considering the association between sentiment elements.
Approach:	They propose a simple yet effective Unified Grid Tagging Scheme to extract sentiment quadruplets in one shot . they leverage syntactic dependency tree and AMR graph to enrich association between sentiment elements .
Outcome:	The proposed model extracts all sentiment elements in quads for a given review to explain the reason for the sentiment.

Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models (2025.findings-acl)

Copied to clipboard

Jiangxu Wu, Cong Wang, Tianhuang Su, Lin Haozhi, JunYang JunYang, Zhangchao Zhangchao, Binqiang Pan, SongpanYang SongpanYang, Mingpeng Mingpeng, Kai Shi, Zixian Li

Accurate KV Cache Quantization with Outlier Tokens Tracing (2025.acl-long)

Challenge:	Existing methods for generating multi-turn dialogue data struggle to ensure both diversity and quality in instructions.
Approach:	They propose a framework that synthesizes multi-turn conversations through an iterative "Ask-Respond-Review" process involving three agent roles: a Candidate, multiple Reviewers, and a Chairman.
Outcome:	The proposed framework synthesizes multi-turn conversations through an iterative "Ask-Respond-Review" process involving three agent roles: a Candidate, multiple Reviewers, and a Chairman.

Copied to clipboard

Yi Su, Yuechi Zhou, Quantong Qiu, Juntao Li, Qingrong Xia, Ping Li, Xinyu Duan, Zhefeng Wang, Min Zhang

Multi-Level Cross-Modal Alignment for Speech Relation Extraction (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) require substantial computational resources during deployment.
Approach:	They propose a method to identify outlier tokens and exclude them from quantization . they find that the method can deliver a 6.4 times reduction in memory usage and a 2.5 times increase in throughput .
Outcome:	The proposed method delivers a 6.4 times reduction in memory usage and a 2.5 times increase in throughput under 2-bit quantization.

Copied to clipboard

Liang Zhang, Zhen Yang, Biao Fu, Ziyao Lu, Liangying Shao, Shiyu Liu, Fandong Meng, Jie Zhou, Xiaoli Wang, Jinsong Su

HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment (2026.acl-long)

Challenge:	Existing studies use synthetic speech to train and evaluate SpeechRE models, hindering their development . modality gap issue limits performance of existing models, limiting future researches .
Approach:	They propose to use speech data to train and evaluate SpeechRE models by using real speech . they propose to train a cross-modal alignment model to bridge the modality gap .
Outcome:	The proposed model can train to bridge the modality gap between speech encoder and text decoder . the proposed model is based on two real SpeechRE datasets .

Copied to clipboard

Zhanyu Liu, Qingguo Hu, Ante Wang, Chenqing Liu, Zhishang Xiang, Hui Li, Delai Qiu, Jinsong Su

Low-Resource NLP

Challenge:	Existing methods for training reasoning-oriented large language models assume high-resource settings with abundant data.
Approach:	They propose a framework that integrates high-value general-domain data to promote more diverse exploration.
Outcome:	The proposed framework matches or surpasses RLVR trained with 32 target-domain samples using 32 target domain samples.

Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification (2022.acl-short)

Copied to clipboard

Xi’ao Su, Ran Wang, Xinyu Dai

Enhancing Event Causality Identification with LLM Knowledge and Concept-Level Event Relations (2025.coling-main)

Challenge:	Existing methods for multi-label text classification neglect the knowledge from the existing similar instances when predicting labels of a specific text.
Approach:	They propose a k nearest neighbor mechanism which retrieves several neighbor instances and interpolates the model output with their labels.
Outcome:	Extensive experiments show that the proposed method can bring significant performance improvements to multiple MLTC models including state-of-the-art pretrained and non-pretrained ones.

Copied to clipboard

Ya Su, Hu Zhang, Guangjun Zhang, Yujie Wang, Yue Fan, Ru Li, Yuanlong Wang

Knowledge Representation

Challenge:	Existing methods to identify causal relationships between events often overlook the dependencies between similar events.
Approach:	They propose an ECI method enhanced by LLM Knowledge and Concept-Level Event Relations (LKCER) the method constructs a conceptual-level heterogeneous event graph by leveraging local contextual information of related event mentions.
Outcome:	The proposed method outperforms previous state-of-the-art methods on both benchmarks, EventStoryLine and Causal-TimeBank.

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

From Factuality to Meta-Factivity: A Cognitive Blueprint for Trustworthy LLMs (2026.acl-short)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Liu Daohuan, Xia Lun, Yuer Wang, Jiaoyang Su, Xuri Tang

TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning (2025.emnlp-main)

Challenge:	Current evaluation paradigms on Event Factuality Prediction (EFP) focus on static classification tasks and shortcut learning and unreliable reasoning.
Approach:	They propose a meta-factivity framework that moves evaluation beyond surface recognition to belief trajectory reasoning and epistemic regulation.
Outcome:	The proposed framework shifts from event factuality to meta-factivity . the proposed framework lays the groundwork for a more rigorous benchmark for explainable self-governance .

Copied to clipboard

Hang Ni, Fan Liu, Xinyu Ma, Lixin Su, Shuaiqiang Wang, Dawei Yin, Hui Xiong, Hao Liu

F²Bench: An Open-ended Fairness Evaluation Benchmark for LLMs with Factuality Considerations (2025.emnlp-main)

Challenge:	Existing studies on large language models (LLMs) focus on basic plan validity, but neglect critical aspects such as route efficiency, POI appeal, and real-time adaptability.
Approach:	They propose a benchmark for retrieval-augmented, spatiotemporal-aware travel planning that integrates retrieved trajectories with LLMs’ intrinsic reasoning.
Outcome:	The proposed framework improves spatial efficiency and POI rationality while challenging universality and robustness due to conflicting references and noisy data.

Copied to clipboard

Tian Lan, Jiang Li, Yemin Wang, Xu Liu, Xiangdong Su, Guanglai Gao

ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)

Challenge:	Existing fairness evaluation benchmarks for large language models rely on closed-ended evaluation formats that overlook factuality considerations rooted in historical, social, physiological, and cultural contexts.
Approach:	They propose an open-ended fairness evaluation benchmark for large language models . they incorporate factuality considerations and multi-turn reasoning into the benchmark .
Outcome:	The proposed benchmark incorporates factual grounding and text generation to better reflect the complexities of real-world model usage.

Copied to clipboard

Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong

Restoring Ancient Ideograph: A Multimodal Multitask Neural Network Approach (2024.lrec-main)

Challenge:	Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure.
Approach:	They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction.
Outcome:	The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models.

Copied to clipboard

Siyu Duan, Jun Wang, Qi Su

Keep the Primary, Rewrite the Secondary: A Two-Stage Approach for Paraphrase Generation (2021.findings-acl)

Challenge:	despite efforts to preserve cultural relics, many ancient artefacts have fallen prey to ravages of time, natural deterioration, or deliberate human actions.
Approach:	They propose a multimodal multitask restoration model that uses visual and context understanding to restore ancient texts.
Outcome:	The proposed model predicts damaged characters and generates restored images simultaneously.

Copied to clipboard

Yixuan Su, David Vandyke, Simon Baker, Yan Wang, Nigel Collier

Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key? (2024.acl-long)

Challenge:	Existing approaches to generate paraphrases are decomposable, but some use a sequence-to-sequence model to generate each word in a uniform way.
Approach:	They propose a framework for identification then aggregation of input tokens and a custom decoder to generate paraphrases.
Outcome:	The proposed framework outperforms previous studies on two benchmark datasets and generates paraphrases in interpretable and controllable way.

Copied to clipboard

Qineng Wang, Zihao Wang, Ying Su, Hanghang Tong, Yangqiu Song

Suggest-Verify-Revise: A Three-Stage Document-Level Event Causality Identification with Narrative Consistency (2026.acl-long)

Challenge:	Recent progress in LLMs discussion suggests that multi-agent discussion improves the reasoning abilities of LLM.
Approach:	They propose a group discussion framework to enrich the set of discussion mechanisms.
Outcome:	The proposed framework performs better on a wide range of reasoning tasks and backbone LLMs.

Copied to clipboard

Ya Su, Hu Zhang, Dan Qiao, YuJie Wang, Yunxiao Zhao, Yue Fan, Shike Li, Ru Li, Hongye Tan

Challenge:	Existing methods for document-level Event Causality Identification rely on local semantic similarity for independent event-pair discrimination . Existing approaches ignore the influence of the overall narrative backbone in the propagation of causal dependencies and the role differentiation of events within multi-cause/multi-effect structures.
Approach:	They propose a suggest-verify-revise approach for document-level Event Causality Identification with narrative consistency (SVRECI) they integrate heuristic causal suggestions generated by an LLM with structural suggestions derived from hypergraph modeling .
Outcome:	The proposed approach outperforms existing methods on event-storylines and Causal-TimeBank datasets.

How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models (2025.emnlp-main)

Copied to clipboard

Kangtao Lv, Haibin Chen, Yujin Yuan, Langming Liu, Shilei Liu, Yongwei Wang, Wenbo Su, Bo Zheng

Glyph: Scaling Context Windows via Visual-Text Compression (2026.acl-long)

Challenge:	Recent studies show that strategically infusing domain knowledge during pretraining can substantially improve downstream performance.
Approach:	They propose a knowledge infusion scaling law that predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.
Outcome:	The proposed model predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.

Copied to clipboard

Jiale Cheng, Yusen Liu, Xinyu Zhang, Yulin Fei, Wenyi Hong, Ruiliang Lyu, Weihan Wang, Zhe Su, Xiaotao Gu, Xiao Liu, Yushi Bai, Jie Tang, Hongning Wang, Minlie Huang

Training LLMs to be Better Text Embedders through Bidirectional Reconstruction (2025.emnlp-main)

Challenge:	Large language models (LLMs) traditionally represent text as sequences of discrete tokens . a long-context scaling problem requires processing more tokens more efficiently .
Approach:	They propose a framework that renders long texts into compact visual pages and processes them with a vision-language model.
Outcome:	The proposed framework renders long texts into compact visual pages and processes them with a vision-language model.

Copied to clipboard

Chang Su, Dengliang Shi, Siyuan Huang, Jintao Du, Changhua Meng, Yu Cheng, Weiqiang Wang, Zhouhan Lin

Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference (2022.findings-acl)

Challenge:	Existing text embedding approaches often leverage the embeddment of the final token, typically a reserved special token such as ‘[EOS]‘.
Approach:	They propose to add a new training stage before contrastive learning to enrich the semantics of the final token embedding.
Outcome:	The proposed training stage improves performance on the Massive Text Embedding Benchmark (MTEB), achieving new state-of-the-art results across different LLM base models and scales.

Copied to clipboard

Yuxia Wang, Minghan Wang, Yimeng Chen, Shimin Tao, Jiaxin Guo, Chang Su, Min Zhang, Hao Yang

RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial Attacks (2023.acl-long)

Challenge:	Previously, it's common to disregard it as noise or as a sign of poor-quality data, as their annotations are heavily based on personal experience and opinions.
Approach:	They propose to capture the human disagreement distribution from the perspective of model calibration.
Outcome:	The proposed model can achieve competitive performance when well-calibrated, on divergence scores between predictive probability and the true human opinion distribution, and the accuracy.

Copied to clipboard

Zhaoyang Wang, Zhiyue Liu, Xiaopeng Zheng, Qinliang Su, Jiahai Wang

Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI (2026.acl-long)

Challenge:	Existing defenses focus on improving robustness of the victim model in training, but neglect to mitigate adversarial attacks during inference.
Approach:	They propose a framework that confuses attackers and corrects adversarial contexts . their framework helps improve the robustness of the victim model during inference .
Outcome:	The proposed framework improves the robustness of the victim model in training . it also corrects abnormal contexts in the representation level and filtering out examples .

Copied to clipboard

Yuxia Wang, Rui Xing, Jonibek Mansurov, Giovanni Puccetti, Zhuohan Xie, Minh Ngoc Ta, Jiahui Geng, Jinyan Su, Mervat Abassy, Saadeldine Eletter, Kareem Elozeiri, Nurkhan Laiyk, Maiya Goloburda, Tarek Mahmoud, Raj Vardhan Tomar, Alexander Aziz, Ryuto Koike, Masahiro Kaneko, Artem Shelmanov, Ekaterina Artemova, Vladislav Mikhailov, Akim Tsvigun, Alham Fikri Aji, Nizar Habash, Iryna Gurevych, Preslav Nakov

OpenFact: Factuality Enhanced Open Knowledge Extraction (2023.tacl-1)

Challenge:	Prior studies have shown that distinguishing text generated by Large Language Models from human-written text is challenging for humans and often no better than random guessing.
Approach:	They conduct extensive case study to determine the upper bound of human detection accuracy.
Outcome:	The findings challenge previous conclusions on human detection accuracy across languages and domains.

Copied to clipboard

Linfeng Song, Ante Wang, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su, Yue Zhang, Dong Yu

CuMA: Aligning LLMs with Sparse Cultural Values via Demographic-Aware Mixture of Adapters (2026.acl-long)

Challenge:	Existing OIE systems organize knowledge into subject-relation-object (SRO) triplets, and they use templates to extract such knowledge triplet.
Approach:	They propose a framework to handle expressiveness and groundedness in OpenFact . they propose to use templates, extra constraints, and adopt human efforts to ensure that most triplets contain enough details.
Outcome:	The proposed framework improves expressiveness and groundedness of OpenFact . it is more accurate and denser than OPIEC-Linked, which is grounded to Wikidata .

Copied to clipboard

Ao Sun, Xiaoyu Wang, Zhe Tan, Yu Li, Zhu Jiachen, Yuheng Jia, Shu Su

NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing (P18-1)

Challenge:	Large Language Models (LLMs) have a global audience, so alignment must extend to cultural resonance.
Approach:	They propose a framework that frames alignment as a conditional capacity separation problem.
Outcome:	The proposed framework outperforms both dense baselines and semantic-only MoEs on three large language models.

Copied to clipboard

Dinghan Shen, Qinliang Su, Paidamoyo Chapfuwa, Wenlin Wang, Guoyin Wang, Ricardo Henao, Lawrence Carin

Challenge:	Existing approaches to fast similarity search require two-stage training and the binary constraints are handled ad-hoc.
Approach:	They propose an end-to-end neural architecture for semantic hashing where binary hash codes are treated as Bernoulli latent variables.
Outcome:	The proposed approach outperforms state-of-the-art models on unsupervised and supervised scenarios on three public datasets.

Improving LLM Generations via Fine-Grained Self-Endorsement (2024.findings-acl)

Copied to clipboard

Ante Wang, Linfeng Song, Baolin Peng, Lifeng Jin, Ye Tian, Haitao Mi, Jinsong Su, Dong Yu

Domain Adaptation for Conversational Query Production with the RAG Model Feedback (2023.findings-emnlp)

Challenge:	Recent large language models (LLMs) have demonstrated remarkable capabilities but can still fail frequently on knowledge-intensive tasks.
Approach:	They propose a self-endorsement framework that leverages fine-grained fact-level comparisons across multiple sampled responses.
Outcome:	The proposed framework can improve factuality of generations with simple prompts across scales of LLMs.

Copied to clipboard

Ante Wang, Linfeng Song, Ge Xu, Jinsong Su

PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models (2025.findings-emnlp)

Challenge:	Existing studies have focused on human-annotated search queries but they can not cover conversations of various domains.
Approach:	They propose a domain adaptation framework that uses retrieval-augmented generation to improve the model's robustness.
Outcome:	The proposed model is more robust and performs significantly better in a more challenging setting over strong baselines.

Copied to clipboard

Yuanhe Zhang, Xinyue Wang, Haoran Gao, Zhenhong Zhou, Fanyu Meng, Yuyao Zhang, Sen Su

Towards Linear Time Neural Machine Translation with Capsule Networks (D19-1)

Challenge:	Existing work lacks mitigation strategies against resource consumption attacks . existing work does not provide mitigation strategies for real-world LLM deployments .
Approach:	They propose a pluggable and dynamic doS-Defense framework which employs a two-stage approach to defend against resource consumption attacks from both the input and output sides.
Outcome:	The proposed framework significantly mitigates resource consumption attacks, improving users’ access capacity by up to 500% during adversarial load.

Copied to clipboard

Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Lei Li

LI4: Label-Infused Iterative Information Interacting Based Fact Verification in Question-answering Dialogue (2024.lrec-main)

Challenge:	Neural Machine Translation (NMT) is an endto-end learning approach to machine translation.
Approach:	They propose a capsule network with dynamic routing for linear time Neural Machine Translation . they map the source sentence into a matrix with pre-determined size and apply a deep LSTM network to decode the target sequence from the source representation.
Outcome:	The proposed network achieves comparable results with the Transformer system on English-German and English-French tasks.

Copied to clipboard

Xiaocheng Zhang, Chang Wang, Guoping Zhao, Xiaohong Su

Towards Universal Debiasing for Language Models-based Tabular Data Generation (2025.findings-emnlp)

Challenge:	Existing studies on fact verification have failed to fully exploit question structures and ignoring relevant label information during the verification process.
Approach:	They propose a new approach for question-answering dialogue based fact verification using label-infused iterative information interacting.
Outcome:	The proposed approach achieves remarkable performance on HEALTHVER, FAVIQ, and COLLOQUIAL.

Copied to clipboard

Tianchun Li, Tianci Liu, Xingchen Wang, Rongzhe Wei, Pan Li, Lu Su, Jing Gao

Structural Information Preserving for Graph-to-Text Generation (2020.acl-main)

Challenge:	Existing large language models have exacerbated fairness issues in tabular data generation . inherent historical biases in tabulated data cause LLMs to exacerbate fairness problems .
Approach:	They propose a universal debiasing framework that minimizes group-level dependencies . it leverages the autoregressive structure and analytic sampling distributions of LLM-based tabular data generators .
Outcome:	The proposed framework minimizes group-level dependencies while reducing mutual information between advantaged and protected attributes.

Copied to clipboard

Linfeng Song, Ante Wang, Jinsong Su, Yue Zhang, Kun Xu, Yubin Ge, Dong Yu

Structured Data in NLP

Challenge:	Existing models that mess up or drop the core structural information of input graphs are lacking in graph-to-text generation.
Approach:	They propose to leverage richer training signals to guide a graph-to-text generation model by focusing on autoencoding losses and back-propagating the losses to better calibrate the model.
Outcome:	Experiments on two benchmarks show the proposed model over a state-of-the-art model . two types of autoencoding losses are used to back-propagate the model based on multitask training .

How Large a Vocabulary Does Text Classification Need? A Variational Approach to Vocabulary Selection (N19-1)

Copied to clipboard

Wenhu Chen, Yu Su, Yilin Shen, Zhiyu Chen, Xifeng Yan, William Yang Wang

Generating Deep Questions with Commonsense Reasoning Ability from the Text by Disentangled Adversarial Inference (2023.findings-acl)

Challenge:	Using a pre-defined vocabulary is a common approach to selecting text inputs . however, using a large vocabulary is not economical, as it limits the model's applicability on computation-or memoryconstrained scenarios.
Approach:	They propose a more sophisticated variational vocabulary dropout to perform vocabulary selection . they propose two new metrics to measure area under accuracy-vocab curve and Vocab Size under X% accuracy drop .
Outcome:	The proposed framework outperforms the baselines on the vocabulary selection problem on multiple NLP classification tasks.

Copied to clipboard

Jianxing Yu, Shiqi Wang, Libin Zheng, Qinliang Su, Wei Liu, Baoquan Zhao, Jian Yin

MHGRL: An Effective Representation Learning Model for Electronic Health Records (2024.lrec-main)

Challenge:	Existing methods for commonsense question generation produce shallow questions that can be answered by simple word matching.
Approach:	They propose a task of commonsense question generation that aims to yield deep-level questions from the text.
Outcome:	The proposed model can yield deep-level and to-the-point questions from the text.

Copied to clipboard

Feiyan Liu, Liangzhi Li, Xiaoli Wang, Feng Luo, Chang Liu, Jinsong Su, Yiming Qian

2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision (2025.findings-naacl)

Challenge:	Effective EHR representations are key to achieving high performance in healthcare applications.
Approach:	They propose a multimodal heterogeneous graph-enhanced representation learning to learn EHR representations using medical ontology and textual notes.
Outcome:	The proposed model outperforms baseline models on two real clinical datasets in downstream tasks.

Copied to clipboard

Shilong Li, Yancheng He, Hui Huang, Xingyuan Bu, Jiaheng Liu, Hangyu Guo, Weixun Wang, Jihao Gu, Wenbo Su, Bo Zheng

Challenge:	Existing methods that optimize for scalar scores or ranking reward ignore multi-dimensional nature of human preferences.
Approach:	They propose to extend the preference of Direct Preference Optimization to two dimensions: segments and aspects.
Outcome:	The proposed framework decomposes the overall objective into multi-segment and multi-aspect objectives.

MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark (2025.acl-long)

Copied to clipboard

Xiang Yue, Tianyu Zheng, Yuansheng Ni, Yubo Wang, Kai Zhang, Shengbang Tong, Yuxuan Sun, Botao Yu, Ge Zhang, Huan Sun, Yu Su, Wenhu Chen, Graham Neubig

OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure (2025.tacl-1)

Challenge:	Recent advances in multimodal large language models have led to progress in tackling complex reasoning tasks that combine textual and visual information.
Approach:	They introduce a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark.
Outcome:	The proposed model performs lower on MMMU-Pro than on the previous benchmark, ranging from 16.8% to 26.9%.

Copied to clipboard

Jikai Wang, Yi Su, Juntao Li, Qingrong Xia, Zi Ye, Xinyu Duan, Zhefeng Wang, Min Zhang

Don’t Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls (2025.acl-long)

Challenge:	Autoregressive language models generate one token in one step, limiting inference efficiency . Existing methods do not adapt to different situations to maximize acceptance length . speculative decoding has shown great potential for lossless acceleration .
Approach:	They propose an algorithm to construct adaptive and scalable draft trees for autoregressive language models.
Outcome:	Experimental results show that OPT-Tree outperforms existing draft trees and achieves speed-up ratio of up to 3.2 compared with autoregressive decoding.

Copied to clipboard

Ante Wang, Linfeng Song, Ye Tian, Dian Yu, Haitao Mi, Xiangyu Duan, Zhaopeng Tu, Jinsong Su, Dong Yu

Green & Sustainable NLP

Challenge:	Recent advances in tree search algorithms guided by verifiers have significantly enhanced the reasoning capabilities of large language models (LLMs), but at the cost of increased computational resources.
Approach:	They propose an e ffici ent tree sear ch framework that is a plug-and-play system compatible with various tree search algorithms.
Outcome:	The proposed framework reduces computational costs and prioritizes resource allocation to harder tasks (Levels 3-4) over simpler ones (Level 1-2), addressing both over-exploration in basic problems and under-exploation in complex cases.

Jailbreak LLMs through Internal Stance Manipulation (2025.emnlp-main)

Copied to clipboard

Shuangjie Fu, Du Su, Beining Huang, Fei Sun, Jingang Wang, Wei Chen, Huawei Shen, Xueqi Cheng

OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation (2026.acl-long)

Challenge:	Existing approaches to exploit LLMs' inherent safety mechanism, including GCG and AutoDAN, are ineffective for certain malicious requests.
Approach:	They propose a method that generates jailbreak prompts to suppress a refusal stance and induce affirmative responses by modifying adversarial prompts.
Outcome:	The proposed method outperforms the best baseline approach in Llama-2-7b-chat and achieves a 92.2% success rate across all models.

Copied to clipboard

Ziyi Wang, Yuxuan Lu, Wenbo Li, Amirali Amini, Bo Sun, Yakov Bart, Weimin Lyu, Jiri Gesi, Tian Wang, Jing Huang, Yu Su, Upol Ehsan, Malihe Alikhani, Toby Jia-Jun Li, Lydia Chilton, Dakuo Wang

Challenge:	evaluating LLMs' ability to mimic real user behavior remains an open challenge due to the lack of high-quality, publicly available datasets that capture both the observable actions and the internal reasoning of an actual user.
Approach:	They propose a dataset of Observation, Persona, Rationale, and Action collected from real human participants during online shopping sessions.
Outcome:	The proposed dataset is the first to evaluate how well current LLMs can accurately simulate the next web action of a specific user.

OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene Grounding (2021.naacl-main)

Copied to clipboard

Ke-Jyun Wang, Yun-Hsuan Liu, Hung-Ting Su, Jen-Wei Wang, Yu-Siang Wang, Winston Hsu, Wen-Chin Chen

Visual Data in NLP

Challenge:	Visual grounding (VG) is a crucial task in natural language processing, computer vision, and robotics.
Approach:	They propose a visual grounding task with referring expressions of occluded objects in a OCID-Ref dataset with 2,300 scenes and a point cloud input.
Outcome:	The proposed dataset shows that it can handle 2D and 3D signals but referring to occluded objects remains challenging for the modern visual grounding systems.

On Transferability of Prompt Tuning for Natural Language Processing (2022.naacl-main)

Copied to clipboard

Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou

A Unified Generative Framework for Bilingual Euphemism Detection and Identification (2024.findings-acl)

Challenge:	Pre-trained language models (PLMs) can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but require much more training time than fine-timing.
Approach:	They empirically investigate the transferability of soft prompts across different downstream tasks and PLMs to determine what decides prompt transferability.
Outcome:	The proposed method can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but requires much more training time than fine-timing.

Copied to clipboard

Yuxue Hu, Junsong Li, Tongguan Wang, Dongyu Su, Guixin Su, Ying Sha

Multilinguality

Challenge:	Existing euphemism datasets are only domain-specific or language-specific.
Approach:	They propose a unified model to jointly conduct bilingual euphemism detection and identification tasks.
Outcome:	The proposed model is effective and provides a new reference standard for euphemism detection and identification.

Exploring All-In-One Knowledge Distillation Framework for Neural Machine Translation (2023.emnlp-main)

Copied to clipboard

Zhongjian Miao, Wen Zhang, Jinsong Su, Xiang Li, Jian Luan, Yidong Chen, Bin Wang, Min Zhang

BAPO: Boundary-Aware Policy Optimization for Reliable Agentic Search (2026.findings-acl)

Challenge:	Existing knowledge distillation methods only obtain one lightweight student each time . this could be resource-intensive and resulting in multiple students not being optimally utilized .
Approach:	They propose a knowledge distillation framework which generates multiple satisfactory students at once.
Outcome:	The proposed framework generates multiple satisfactory students at once.

Copied to clipboard

Shiyu Liu, Yongjing Yin, Jianhao Yan, Yunbo Tang, Qinggang Zhang, Bei Li, Xin Chen, Jingang Wang, Xunliang Cai, Jinsong Su

Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenization (2025.findings-emnlp)

Challenge:	Existing RL-based agentic search models fail to recognize reasoning boundaries and rarely admit "I DON'T KNOW" lack of reliability leads to plausible but unreliable answers, introducing significant risks .
Approach:	They propose a framework to cultivate reliable boundary awareness without compromising accuracy.
Outcome:	Experiments show that the proposed framework improves the reliability of agentic search models.

Copied to clipboard

Yunyue Su, Zhang Jinshuai, Bowen Fang, Wen Ye, Jinghao Zhang, Bowen Song, Weiqiang Wang, Qiang Liu, Liang Wang

Syntactic Text Processing

Challenge:	Extensive experiments demonstrate the effectiveness of SGTC across various tasks.
Approach:	They propose a generative tool invocation framework that introduces structure-aware semantic tokenization to encode tools as discrete code sequences.
Outcome:	The proposed framework reduces the size of the representation space and underutilizes collaborative signals among tools in downstream tasks.

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs (2025.emnlp-main)

Copied to clipboard

Hexiang Tan, Fei Sun, Sha Liu, Du Su, Qi Cao, Xin Chen, Jingang Wang, Xunliang Cai, Yuanzhuo Wang, Huawei Shen, Xueqi Cheng

Challenge:	Existing detection methods fail to account for self-consistent error . study identifies self-consistency errors and evaluates them .
Approach:	They propose a method that fuses hidden state evidence from an external verifier LLM to detect self-consistent errors.
Outcome:	The proposed method significantly enhances performance on self-consistent errors across three LLM families.

Adaptive Gating in Mixture-of-Experts based Language Models (2023.emnlp-main)

Copied to clipboard

Jiamin Li, Qiang Su, Yitao Yang, Yimin Jiang, Cong Wang, Hong Xu

Knowledge Graph-Driven Memory Editing with Directional Interventions (2025.findings-emnlp)

Challenge:	Existing models employ a fixed gating network where each token is computed by the same number of experts.
Approach:	They propose a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution.
Outcome:	The proposed model reduces training time and inference quality while maintaining sparsity while maintaining inference accuracy.

Copied to clipboard

Jinhu Fu, Kun Wang, Chongye Guo, Junfeng Fang, Wentao Zhang, Sen Su

One Embedder, Any Task: Instruction-Finetuned Text Embeddings (2023.findings-acl)

Challenge:	Large Language Models (LLMs) are hampered by inaccuracies and outdated information.
Approach:	They propose a framework that constructs knowledge graphs using available information to guide the direction of knowledge editing.
Outcome:	The proposed framework allows consistent, aligned, and stable information during large-scale editing scenarios.

Copied to clipboard

Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, Tao Yu

Getting the Most out of Simile Recognition (2022.findings-emnlp)

Challenge:	a new method for embedding text is developed for tasks that require specialized encoders . INSTRUCTOR is a single embedder that can generate text embeddables tailored to different tasks and domains based on instruction finetuning .
Approach:	They introduce a new method for computing text embeddings given task instructions . they first annotate instructions for 330 diverse tasks and train INSTRUCTOR on this multitask mixture .
Outcome:	The proposed method improves on 70 embedding evaluation tasks with fewer parameters than the previous best model.

Copied to clipboard

Xiaoyue Wang, Linfeng Song, Xin Liu, Chulun Zhou, Hualin Zeng, Jinsong Su

Challenge:	Recent work ignores features other than surface strings and suffers from data hunger issue.
Approach:	They propose to use simile sentence classification and simile component extraction to find simile components.
Outcome:	The proposed model outperforms current state-of-the-art systems and baselines.

Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving (2021.acl-short)

Copied to clipboard

Shih-hung Tsai, Chao-Chun Liang, Hsin-Min Wang, Keh-Yih Su

AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation (2026.findings-acl)

Challenge:	Existing neural solvers only generate binary expression trees that contain basic arithmetic operators and do not explicitly use the math formulas.
Approach:	They propose a sequence-to-general tree that generates interpretable and executable operation trees where nodes can be formulas with an arbitrary number of arguments.
Outcome:	The proposed tree generates interpretable and executable operation trees with formulas with an arbitrary number of arguments.

Copied to clipboard

Wentao Shi, Yu Wang, Yuyang Zhao, Yuxin Chen, Fuli Feng, Xueyuan Hao, Xi Su, Qi GU, Hui Su, Xunliang Cai, Xiangnan He

Challenge:	Existing approaches to verify agent behaviors in complex environments rely on rule-based verifiers or LLM-as-a-Judge models.
Approach:	They propose a benchmark to evaluate Agent-as-a-Judge across three domains . the benchmark covers search, data systems, and graphical user interfaces - with 155 tasks and 516 trajectories .
Outcome:	The proposed benchmark outperforms existing benchmarks in search, data systems, and GUI domains while revealing open challenges in agent-based verification.

RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relation for Multimodal NER (2020.coling-main)

Copied to clipboard

Lin Sun, Jiquan Wang, Yindu Su, Fangsheng Weng, Yuxuan Sun, Zengwei Zheng, Yuanyi Chen

PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models (2025.emnlp-industry)

Challenge:	Named entity recognition (MNER) for tweets is a key task of many applications.
Approach:	They propose a pre-trained multimodal named entity recognition model based on Relationship Inference and Visual Attention (RIVA) for tweets.
Outcome:	The proposed model improves on the multimodal named entity recognition (MNER) task on tweets with the aid of visual clues.

Copied to clipboard

He Zhu, Junyou Su, Minxin Chen, Wen Wang, Yijie Deng, Guanhua Chen, Wenjia Zhang

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models (2024.findings-acl)

Challenge:	Existing Vision-Language Models (VLMs) fail to analyze planning maps . specialized visual representations of land use zones, transportation networks, and development policies are needed to interpret complex planning maps.
Approach:	They propose a domain-specific VLM tailored for urban planning maps that employs three innovations: PlanAnno-V framework for high-quality VQA data synthesis, Critical Point Thinking (CPT) and PlanBench-V benchmark for systematic evaluation.
Outcome:	The new model outperforms general-purpose VLMs on planning map interpretation tasks.

Copied to clipboard

Weihang Su, Changyue Wang, Qingyao Ai, Yiran Hu, Zhijing Wu, Yujia Zhou, Yiqun Liu

MICO: A Multi-alternative Contrastive Learning Framework for Commonsense Knowledge Representation (2022.findings-emnlp)

Challenge:	Existing studies on hallucination detection for LLMs focus on how to identify possible factrelated errors in outputs.
Approach:	They propose an unsupervised training framework that leverages the internal states of LLMs for real-time hallucination detection without requiring manual annotations.
Outcome:	The proposed framework outperforms existing state-of-the-art methods in hallucination detection.

Copied to clipboard

Ying Su, Zihao Wang, Tianqing Fang, Hongming Zhang, Yangqiu Song, Tong Zhang

User Feedback Alignment for LLM-powered Exploration in Large-scale Recommendation Systems (2025.acl-industry)

Challenge:	Existing approaches to commonsense reasoning include fine-tuning large pre-trained language models or injecting the entire knowledge base for CKGC.
Approach:	They propose to learn commonsense knowledge representation by using a multi-alternative contrastive learning framework on COmmonsense Knowledge graphs.
Outcome:	Extensive experiments show that the proposed framework is effective in commonsense reasoning tasks.

Copied to clipboard

Jianling Wang, Yifan Liu, Yinghao Sun, Xuejian Ma, Yueqi Wang, He Ma, Zhengyang Su, Minmin Chen, Mingyan Gao, Onkar Dalal, Ed H. Chi, Lichan Hong, Ningren Han, Haokai Lu

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

Challenge:	Large Language Models (LLMs) can be used to broaden user experiences beyond established preferences and reinforce feedback loops.
Approach:	They propose a hierarchical approach that combines hierarchic planning with LLM inference-time scaling to improve recommendation relevancy without compromising novelty.
Outcome:	The proposed approach shows significant gains in both user satisfaction and exploration diversity.

Copied to clipboard

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

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

XL-NBT: A Cross-lingual Neural Belief Tracking Framework (D18-1)

Copied to clipboard

Wenhu Chen, Jianshu Chen, Yu Su, Xin Wang, Dong Yu, Xifeng Yan, William Yang Wang

BACO: A Background Knowledge- and Content-Based Framework for Citing Sentence Generation (2021.acl-long)

Challenge:	a multi-lingual approach to training dialog systems is expensive and tedious, but it can be useful for cross-lingual support.
Approach:	They propose to annotate data for multiple languages and train a multi-lingual dialog system for each language.
Outcome:	The proposed framework bypasses the expensive human annotation and achieves promising results.

Copied to clipboard

Yubin Ge, Ly Dinh, Xiaofeng Liu, Jinsong Su, Ziyao Lu, Ante Wang, Jana Diesner

Entity-centered Cross-document Relation Extraction (2022.emnlp-main)

Challenge:	citing sentences capture salient information in cited papers and the connection between citing and citing papers.
Approach:	They propose a BAckground knowledge- and COntent-based framework for citing sentence generation that integrates two types of information: background knowledge and content.
Outcome:	The proposed framework outperforms baselines in the citation sentence generation task.

Copied to clipboard

Fengqi Wang, Fei Li, Hao Fei, Jingye Li, Shengqiong Wu, Fangfang Su, Wenxuan Shi, Donghong Ji, Bo Cai

Meta-LMTC: Meta-Learning for Large-Scale Multi-Label Text Classification (2021.emnlp-main)

Challenge:	Existing methods for relation extraction only use text snippets surrounding target entities in multiple documents.
Approach:	They propose a relation-extraction model that uses cross-path entity relation attention to detect the semantic relations between entities in a given text.
Outcome:	The proposed method outperforms the state-of-the-art methods in the dataset CodRED by 10%.

Copied to clipboard

Ran Wang, Xi’ao Su, Siyu Long, Xinyu Dai, Shujian Huang, Jiajun Chen

Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion (2026.acl-long)

Challenge:	Large-scale multi-label text classification tasks often face long-tailed label distributions, where many labels have few or even no training instances.
Approach:	They propose a meta-learning approach that incorporates the objective of adapting to new low-resource tasks into the meta-Learning phase.
Outcome:	The proposed approach achieves state-of-the-art against strong baselines and can still enhance powerful BERTlike models.

Copied to clipboard

Shunian Chen, Xinyuan Xie, Zheshu Chen, Owen Lee, Liyan Zhao, Zhan Su, Qilin Sun, Benyou Wang

CEDAR: A Chinese Evaluation Dataset for Computational Argumentation (2026.acl-long)

Challenge:	Existing methods for audio captioning lack fine-grained detail and contextual accuracy due to limited unimodal or superficial information.
Approach:	They propose a two-stage automated pipeline that uses pretrained models to extract contextual cues from video . a large language model synthesizes these inputs to generate detailed and context-aware captions .
Outcome:	The proposed method is scalable and generates detailed and context-aware captions on large-scale audio datasets.

Copied to clipboard

Tian Lan, Jiang Li, Rong Yan, Feilong Bao, Weihua Wang, Guanglai Gao, Xiangdong Su

A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges (2025.findings-acl)

Challenge:	Existing debate datasets neglect important labels for argument mining, generation, and evaluation.
Approach:	They propose a Chinese Evaluation Dataset for Computational Argumentation that includes key arguments and key rhetorical figures, debater roles, modal words, debate results and transcripts.
Outcome:	The proposed dataset covers 600 debates about 318 topics from Chinese debate competitions.

Copied to clipboard

Yibo Yan, Jiamin Su, Jianxiang He, Fangteng Fu, Xu Zheng, Yuanhuiyi Lyu, Kun Wang, Shen Wang, Qingsong Wen, Xuming Hu

Automatic Evaluation of Attribution by Large Language Models (2023.findings-emnlp)

Challenge:	This survey provides the first comprehensive analysis of mathematical reasoning in the era of multimodal large language models . integrating large language model with mathematical reasoning tasks is becoming significant as AI advances .
Approach:	They review over 200 studies published since 2021 and examine the state-of-the-art developments in Math-LLMs . they identify five major challenges hindering the realization of AGI in this domain .
Outcome:	The authors examine the state-of-the-art developments in Math-LLMs with a focus on multimodal settings.

Copied to clipboard

Xiang Yue, Boshi Wang, Ziru Chen, Kai Zhang, Yu Su, Huan Sun

API Is Enough: Conformal Prediction for Large Language Models Without Logit-Access (2024.findings-emnlp)

Challenge:	Generative large language models (LLMs) incorporate external references to generate and support claims. however, evaluating the attribution remains an open problem.
Approach:	They investigate automatic evaluation of attribution given by large language models . they define different types of attributed errors and then explore two approaches .
Outcome:	The proposed methods highlight promising signals and challenges.

Copied to clipboard

Jiayuan Su, Jing Luo, Hongwei Wang, Lu Cheng

MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responses (2025.emnlp-main)

Challenge:	Existing methods for quantifying uncertainty in large language models with black-box API access are limited due to the complex data distributions and inner model mechanism.
Approach:	They propose a conformal prediction method that minimizes the size of prediction sets and ensures a statistical guarantee of the user-defined coverage.
Outcome:	The proposed method outperforms existing methods on close-ended and open-ended questions.

Copied to clipboard

Tong Chen, Zimu Wang, Yiyi Miao, Haoran Luo, Sun Yuanfei, Wei Wang, Zhengyong Jiang, Procheta Sen, Jionglong Su

Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms (P18-1)

Challenge:	Existing medical fact-checking datasets focus on human-generated content, leaving the verification of content generated by large language models (LLMs) relatively unexplored.
Approach:	They propose to use Chinese medical fact-checking datasets to verify LLM-generated medical content by combining in-context learning and fine-tuning.
Outcome:	The first evidence-based Chinese medical fact-checking dataset of LLM-generated medical content consists of 1,321 questions and 7,409 claims .

Copied to clipboard

Dinghan Shen, Guoyin Wang, Wenlin Wang, Martin Renqiang Min, Qinliang Su, Yizhe Zhang, Chunyuan Li, Ricardo Henao, Lawrence Carin

LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error (2024.acl-long)

Challenge:	Existing deep learning architectures to model compositionality in text sequences require a large number of parameters and expensive computations.
Approach:	They propose two additional pooling strategies over word embeddings for improved interpretability and hierarchical pooling for spatial (n-gram) information within text sequences.
Outcome:	The proposed pooling strategies improve interpretability and preserve spatial (n-gram) information within text sequences.

Copied to clipboard

Boshi Wang, Hao Fang, Jason Eisner, Benjamin Van Durme, Yu Su

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)

Challenge:	Existing work on tool-augmented LLMs focuses on the broad coverage of tools and the flexibility of adding new tools.
Approach:	They propose a biologically inspired method for tool-augmented LLMs that orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory.
Outcome:	The proposed method improves tool learning for LLMs under both in-context learning and fine-tuning settings, bringing a boost of 46.7% to Mistral-Instruct-7B and outperforms GPT-4.

Copied to clipboard

Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng

Exploring Better Text Image Translation with Multimodal Codebook (2023.acl-long)

Challenge:	Large language models suffer from factual hallucinations where they generate verifiable falsehoods.
Approach:	They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge.
Outcome:	The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods.

Copied to clipboard

Zhibin Lan, Jiawei Yu, Xiang Li, Wen Zhang, Jian Luan, Bin Wang, Degen Huang, Jinsong Su

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood (2026.acl-long)

Challenge:	Current studies on text image translation face bottlenecks due to lack of a publicly available dataset and poor optical character recognition.
Approach:	They propose a text image translation model with a multimodal codebook and an OCR dataset for Chinese-English translation.
Outcome:	The proposed model can associate the image with relevant texts, providing useful supplementary information for translation.

Copied to clipboard

Xingyu Lin, Yilin Wen, Du Su, En Wang, Wenbin Liu, Zhonghou Lv, Jinchang Hou, Chenfu Bao

Plan-then-Generate: Controlled Data-to-Text Generation via Planning (2021.findings-emnlp)

Challenge:	Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs).
Approach:	They propose a token-level framework that leverages sequence-level likelihood to link group-level rewards with individual tokens via token- level aggregation and introduces a KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates.
Outcome:	Experiments show that TEPO achieves state-of-the-art performance on mathematical reasoning benchmarks and reduces convergence time by 50% compared with GRPO/DAPO.

Copied to clipboard

Yixuan Su, David Vandyke, Sihui Wang, Yimai Fang, Nigel Collier

U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents (2026.findings-acl)

Challenge:	Existing studies focus on producing results that are close to the references, i.e. what to generate and in what order (the output structure) cannot be explicitly controlled by the users.
Approach:	They propose a Plan-then-Generate framework to improve the controllability of neural data-to-text models.
Outcome:	The proposed model can control both the intra-sentence and inter-sentent structure of the generated output.

Copied to clipboard

Jin Su, Runnan Fang, Yeqiu Li, Xiaobin Wang, Shihao Cai, Pengjun Xie, Ningyu Zhang, Fajie Yuan

FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models (2025.emnlp-main)

Challenge:	Existing context-folding methods are designed for single-query or single-intent scenarios.
Approach:	They propose a dynamic context-folding framework tailored to user-centric tasks that preserves fine-grained information through dynamic context folding.
Outcome:	The proposed framework outperforms ReAct and previous folding frameworks on long, noisy tasks.

Copied to clipboard

Hengxing Cai, Jinhan Dong, Jingjun Tan, Jingcheng Deng, Sihang Li, Zhifeng Gao, Haidong Wang, Zicheng Su, Agachai Sumalee, Renxin Zhong

HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring (2025.acl-long)

Challenge:	Existing methods for vision-and-language navigation struggle with insufficient multimodal fusion, weak generalization, and poor interpretability.
Approach:	They propose a framework for UAV vision-and-language navigation that integrates natural language instructions with visual observations to improve multimodal fusion and interpretability.
Outcome:	The proposed framework achieves state-of-the-art performance across all scenarios, with a 9.22% higher success rate than the strongest baseline in unseen environments.

Copied to clipboard

Zhixiong Su, Yichen Wang, Herun Wan, Zhaohan Zhang, Minnan Luo

Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems (2021.naacl-industry)

Challenge:	Existing literature focuses on binary, document-level detection, neglecting texts composed jointly by human and LLM contributions.
Approach:	They propose to use a dataset to generate human-AI coauthored texts via an automatic pipeline with word-level attribution labels.
Outcome:	The proposed method can detect human-AI coauthored texts with a numeric AI ratio.

Copied to clipboard

Tong Wang, Jiangning Chen, Mohsen Malmir, Shuyan Dong, Xin He, Han Wang, Chengwei Su, Yue Liu, Yang Liu

SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science (2025.acl-long)

Challenge:	In dialog systems, the Natural Language Understanding component makes the interpretation decision before the mentioned entities are resolved.
Approach:	They propose to leverage Entity Resolution (ER) features in NLU reranking to learn model weights . they propose a score distribution matching method to ensure the models are calibrated .
Outcome:	The proposed approach outperforms the baseline model on multiple domain evaluations.

Copied to clipboard

Jie Ying, Zihong Chen, Zhefan Wang, Wanli Jiang, Chenyang Wang, Zhonghang Yuan, Haoyang Su, Huanjun Kong, Fan Yang, Nanqing Dong

GaLa: Hypergraph-Guided Visual Language Models for Procedural Planning (2026.findings-acl)

Challenge:	Seed science is essential for modern agriculture, but its application in seed science remains limited due to a shortage of experts and limited availability of online resources.
Approach:	They evaluate 26 leading large language models and compare them against a set of benchmarks . they find that there is a gap between the power of LLMs and real-world seed science problems .
Outcome:	The new seed benchmark highlights the gap between the power of large language models and real-world seed science problems.

Copied to clipboard

Kun Wang, Li Yiming, Mingcheng Qu, Aqiang Zhang, Guang Yang, Tonghua Su

Supervised Gradual Machine Learning for Aspect-Term Sentiment Analysis (2023.tacl-1)

Challenge:	Existing methods for procedural planning over-rely on visual inputs and lack structured semantic information.
Approach:	They propose a vision–language framework for multimodal procedural planning that exploits implicit spatial relations and deep semantics encoded in object attributes.
Outcome:	The proposed framework outperforms existing methods in terms of execution success rate, LCS, and planning correctness.

Copied to clipboard

Yanyan Wang, Qun Chen, Murtadha H.M. Ahmed, Zhaoqiang Chen, Jing Su, Wei Pan, Zhanhuai Li

Sentiment Analysis

Challenge:	Recent work shows that Aspect-Term Sentiment Analysis (ATSA) can be performed by Gradual Machine Learning (GML) but the current unsupervised solution is limited by inaccurate knowledge conveyance.
Approach:	They propose a supervised approach which leverages binary polarity relations between instances to enable supervised knowledge conveyance.
Outcome:	The proposed approach outperforms pure DNN solutions on real benchmark data.

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)

Copied to clipboard

Yancheng He, Shilong Li, Jiaheng Liu, Yingshui Tan, Weixun Wang, Hui Huang, Xingyuan Bu, Hangyu Guo, Chengwei Hu, Boren Zheng, Zhuoran Lin, Dekai Sun, Zhicheng Zheng, Wenbo Su, Bo Zheng

FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction (2023.acl-long)

Challenge:	Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence.
Approach:	They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics .
Outcome:	The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate .

Copied to clipboard

Chen-Yu Lee, Chun-Liang Li, Hao Zhang, Timothy Dozat, Vincent Perot, Guolong Su, Xiang Zhang, Kihyuk Sohn, Nikolay Glushnev, Renshen Wang, Joshua Ainslie, Shangbang Long, Siyang Qin, Yasuhisa Fujii, Nan Hua, Tomas Pfister

Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings (2021.emnlp-main)

Challenge:	Existing approaches that extend the mask language modeling to other modalities require careful multi-task tuning, complex reconstruction target designs, or additional pre-training data.
Approach:	They propose a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss.
Outcome:	The proposed model achieves state-of-the-art performance on FUNSD, CORD, SROIE and Payment benchmarks with a more compact model size.

Copied to clipboard

Shaopeng Lai, Ante Wang, Fandong Meng, Jie Zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang, Jinsong Su

Structured Data in NLP

Challenge:	Existing sentence ordering models can be classified into pairwise ordering models and set-to-sequence models.
Approach:	They propose a novel sentence ordering framework which introduces two classifiers to make better use of pairwise orderings for graph-based sentence ordering.
Outcome:	The proposed model achieves state-of-the-art performance on five commonly-used datasets.

VLN-NF: Feasibility-Aware Vision-and-Language Navigation with False-Premise Instructions (2026.acl-long)

Copied to clipboard

Hung-Ting Su, Ting-Jun Wang, Jia-Fong Yeh, Min Sun, Winston H. Hsu

On the Evaluation of Vision-and-Language Navigation Instructions (2021.eacl-main)

Challenge:	Existing Vision-and-Language Navigation benchmarks assume instructions are feasible and the referenced target exists.
Approach:	They propose a benchmark with false-premise instructions where the target is absent . they propose supervised room-level navigation with LLM/VLM-driven in-room exploration .
Outcome:	The proposed benchmark produces false-premise goals that are plausible but factually incorrect . ROAM achieves the best REV-SPL among compared methods, while baselines often under-explore and terminate prematurely under unreliable instructions.

Copied to clipboard

Ming Zhao, Peter Anderson, Vihan Jain, Su Wang, Alexander Ku, Jason Baldridge, Eugene Ie

HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy (2026.findings-acl)

Challenge:	Existing instruction generators have not been evaluated using human wayfinders . BLEU, ROUGE, METEOR and CIDEr are ineffective for evaluating grounded navigation instructions.
Approach:	They propose an instruction-trajectory compatibility model that operates without reference instructions to improve wayfinding performance.
Outcome:	The proposed model shows the highest correlation with human wayfinding outcomes when scoring individual instructions.

Copied to clipboard

Guoqi Ma, Liang Zhang, Hongyao Tu, Hao Fu, Hui Li, Yujie Lin, Longyue Wang, Weihua Luo, Jinsong Su

Neural Machine Translation with Decoding History Enhanced Attention (C18-1)

Challenge:	Existing approaches to cross-document relation extraction (RE) focus on identifying relations between head and tail entities from single sentence or document.
Approach:	They propose a hierarchical relation tree-based LLM-based hierarchic classification model for cross-document relation extraction (HCRE) based on predefined relations, the model can perform hierarchically classification level by level.
Outcome:	The proposed model outperforms existing baselines and validates its effectiveness.

Copied to clipboard

Mingxuan Wang, Jun Xie, Zhixing Tan, Jinsong Su, Deyi Xiong, Chao Bian

Logical Natural Language Generation from Open-Domain Tables (2020.acl-main)

Challenge:	Neural machine translation with source-side attention has been criticized for its poor memory performance.
Approach:	They propose to use a Decoding History Enhanced Attention mechanism to render NMT models better at selecting both source-side and target-side information.
Outcome:	The proposed model improves by 0:9 BLEU on Chinese-English translation and the state-of-the-art on a larger task.

Copied to clipboard

Wenhu Chen, Jianshu Chen, Yu Su, Zhiyu Chen, William Yang Wang

CLLE: A Benchmark for Continual Language Learning Evaluation in Multilingual Machine Translation (2022.findings-emnlp)

Challenge:	Existing studies on neural natural language generation focus on surface-level realizations with limited emphasis on logical inference.
Approach:	They propose a task where a model is tasked with generating natural language statements that can be logically entailed by facts in an open-domain semi-structured table.
Outcome:	The proposed task is based on the existing TabFact dataset with a wide range of logical/symbolic inferences.

Copied to clipboard

Han Zhang, Sheng Zhang, Yang Xiang, Bin Liang, Jinsong Su, Zhongjian Miao, Hui Wang, Ruifeng Xu

Multilinguality

Challenge:	Existing benchmarks for Continual Language Learning (CLL) are limited due to the complexity of the task and the lack of unified benchmarks.
Approach:	They propose a Continual Language Learning Evaluation benchmark CLLE in multilingual translation.
Outcome:	The proposed method is effective when compared with other strong benchmarks.

Dialogue Response Selection with Hierarchical Curriculum Learning (2021.acl-long)

Copied to clipboard

Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin, Simon Baker, Yunbo Cao, Shuming Shi, Nigel Collier, Yan Wang

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing (2025.findings-acl)

Challenge:	Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics.
Approach:	They propose a hierarchical curriculum learning framework that trains matching models in an “easy-to-difficult” scheme.
Outcome:	The proposed framework significantly improves the model performance across evaluation metrics on three benchmark datasets with three state-of-the-art matching models.

Copied to clipboard

Changyue Wang, Weihang Su, Qingyao Ai, Yujia Zhou, Yiqun Liu

EmoTrans: Emotional Transition-based Model for Emotion Recognition in Conversation (2024.lrec-main)

Challenge:	Existing knowledge editing approaches directly edit model context without isolating target knowledge from the reasoning path of model inference, resulting in unreliable and low-quality outputs, especially in multi-hop tasks.
Approach:	They propose a framework that separates model reasoning from knowledge editing and propose 'DecKER' that allows users to modify specific factual associations without retraining the entire model.
Outcome:	The proposed framework significantly improves multi-hop reasoning performance by mitigating knowledge conflicts and preserving reasoning integrity.

Copied to clipboard

Zhongquan Jian, Ante Wang, Jinsong Su, Junfeng Yao, Meihong Wang, Qingqiang Wu

Sentiment Analysis

Challenge:	Emotions are causally transmitted among communication participants, facilitating comprehension of intricate changes in emotional states during the conversation.
Approach:	They propose an Emotional Transition-based Emotion Recognizer that captures ET features in an emotional conversation by concatenating the most recent utterances with their corresponding speakers.
Outcome:	The proposed model is sensitive to emotions and captures ET features in the sample.

FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation (2025.acl-long)

Copied to clipboard

Qinggang Zhang, Zhishang Xiang, Yilin Xiao, Le Wang, Junhui Li, Xinrun Wang, Jinsong Su

Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis (2026.acl-long)

Challenge:	Existing faithful RAG approaches enforce strict context adherence, but they forcibly suppress the model’s parametric knowledge, which undermines the model's internal knowledge structure and increases the risk of misinterpreting the context.
Approach:	They propose a framework that resolves knowledge conflicts by explicitly modeling discrepancies between the model’s parametric knowledge and retrieved context.
Outcome:	The proposed framework outperforms state-of-the-art methods in knowledge conflict cases and identifies conflicting knowledge at the fact level and designs a self-thinking process.

Copied to clipboard

Wang Cai, Yilin Wen, Jinchang Hou, Du Su, Guoqiu Wang, Zhonghou Lv, Chenfu Bao, Yunfang Wu

Smoothed Contrastive Learning for Unsupervised Sentence Embedding (2022.coling-1)

Challenge:	Existing mitigation strategies rely on global gradient geometry to resolve alignment conflicts . however, they overlook Modular Heterogeneity within Transformers, resulting in suboptimal trade-offs . Conflict-Aware Sparse Tuning (CAST) combines head-level diagnosis with sparse fine-tuning .
Approach:	They propose a framework that integrates head-level diagnosis with sparse fine-tuning to address this limitation.
Outcome:	The proposed framework integrates head-level diagnosis with sparse fine-tuning to reduce alignment conflicts in LLMs.

Copied to clipboard

Xing Wu, Chaochen Gao, Yipeng Su, Jizhong Han, Zhongyuan Wang, Songlin Hu

M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

Challenge:	Unsupervised contrastive sentence embedding models use InfoNCE loss function . increasing batch size leads to performance degradation when it exceeds threshold .
Approach:	They propose a simple smoothing strategy upon the InfoNCE loss function to reduce the number of false-negative pairs in a batch without increasing the batch size.
Outcome:	The proposed smoothing strategy improves unsupervised SimCSE on semantic similarity tasks.

Copied to clipboard

Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Programming Languages in NLP

Challenge:	Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach:	They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome:	The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.

ToMELP: A Theory-of-Mind Benchmark for Route-Controlled Persuasion under the Elaboration Likelihood Model (2026.findings-acl)

Copied to clipboard

Ruirui Wang, Haoran Zhang, Tian Lan, Zehua Duo, Jiang Li, Guanglai Gao, Xiangdong Su

Linguistics & Cognitive NLP

Challenge:	Theory of Mind (ToM) is widely regarded as central to effective persuasion, yet existing evaluations fail to capture the infer–apply loop that arises in real-world dialogue.
Approach:	They propose a benchmark that conditions on the audience persona p and the Elaboration Likelihood Model (ELM) route r within persuasive conversations.
Outcome:	The proposed model can model the interlocutor's mental states over multiple turns and adapt strategy and tone accordingly.

Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study (2025.findings-acl)

Copied to clipboard

Yujie Lin, Ante Wang, Moye Chen, Jingyao Liu, Hao Liu, Jinsong Su, Xinyan Xiao

A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2020.acl-main)

Challenge:	Inference-time scaling of chain-of-thought (CoT) has been demonstrated as a promising approach for addressing multi-modal reasoning tasks.
Approach:	They propose to integrate visual and textual modalities within the reasoning process . they adopt a consistency-enhanced verifier to ensure effective guidance for both methods across different thought paradigms.
Outcome:	The proposed method outperforms text-only reasoning on 10 tasks spanning diverse domains and requires higher token consumption for processing richer visual inputs.

Copied to clipboard

Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang

Asclepius: A Spectrum Evaluation Benchmark for Medical Multi-Modal Large Language Models (2025.acl-long)

Challenge:	Existing approaches to extract relational triples from unstructured text are inadequate to solve the overlapping triple problem.
Approach:	They propose a cascade binary tagging framework that models relations as functions that map subjects to objects in a sentence.
Outcome:	The proposed framework outperforms state-of-the-art methods on two datasets . it outperformed baseline methods by 17.5 and 30.2 absolute gains .

Copied to clipboard

Jie Liu, Wenxuan Wang, Su Yihang, Jingyuan Huang, Yudi Zhang, Cheng-Yi Li, Wenting Chen, Xiaohan Xing, Kao-Jung Chang, Linlin Shen, Michael R. Lyu

Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency (2025.acl-long)

Challenge:	Medical Multi-Modal Large Language Models (Med-MLLMs) are a promising new form of artificial general intelligence due to their ability to tackle complex tasks.
Approach:	They propose a new benchmark that comprehensively assesses medical multi-modal large language models in terms of distinct medical specialties and different diagnostic capacities.
Outcome:	The proposed model covers 15 medical specialties and different diagnostic capacities, and excludes overlap with existing VQA dataset.

Copied to clipboard

Jiafeng Liang, Shixin Jiang, Xuan Dong, Ning Wang, Zheng Chu, Hui Su, Jinlan Fu, Ming Liu, See-Kiong Ng, Bing Qin

Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Models (2025.findings-emnlp)

Challenge:	Large Multimodal Models (LMMs) have demonstrated impressive performance on general video comprehension benchmarks, but their robustness needs to be thoroughly investigated for broader applications.
Approach:	They propose a temporal robustness benchmark which introduces temporal inconsistency perturbations separately at the visual and textual modalities to assess the robustness of models.
Outcome:	The proposed method improves the model’s robustness and reliability in temporal analysis.

Copied to clipboard

Xiaojun Wu, Junxi Liu, Huan-Yi Su, Zhouchi Lin, Yiyan Qi, Chengjin Xu, Jiajun Su, Jiajie Zhong, Fuwei Wang, Saizhuo Wang, Fengrui Hua, Jia Li, Jian Guo

OneRec-Think: In-Text Reasoning for Generative Recommendation (2026.acl-long)

Challenge:	Existing financial benchmarks suffer from limited language and task coverage, low-quality datasets, and inadequate adaptability for LLM evaluation.
Approach:	They propose a bilingual benchmark for financial LLMs that assesses models’ language understanding and generation capabilities.
Outcome:	The proposed bilingual benchmark assesses models’ language understanding and generation capabilities.

Copied to clipboard

Zhanyu Liu, Shiyao Wang, Xingmei Wang, Rongzhou Zhang, Jiaxin Deng, Honghui Bao, Jinghao Zhang, Wuchao Li, PengFei Zheng, Xiangyu Wu, Yifei Hu, Qigen Hu, Xinchen Luo, Lejian Ren, Zhang Zixing, Qianqian Wang, Kuo Cai, Yunfan Wu, Hongtao Cheng, Zexuan Cheng, Lu Ren, Huanjie Wang, Yi Su, Ruiming Tang, Kun Gai, Guorui Zhou

BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026.acl-long)

Challenge:	Existing generative models lack the capacity for explicit and controllable reasoning, a key advantage of LLMs.
Approach:	They propose a framework that integrates dialogue, reasoning, and personalized recommendation.
Outcome:	Experiments across public benchmarks show state-of-the-art performance.

Copied to clipboard

Hexiang Tan, Wanli Yang, Junwei Zhang, Xin Chen, Rui Tang, Du Su, Jingang Wang, Yuanzhuo Wang, Fei Sun, Xueqi Cheng

An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling (2025.acl-short)

Challenge:	Post-trained LLMs typically compromise reliability with severe overconfidence, resulting in inaccurate responses.
Approach:	They propose a solution that feeds PoLLMs into the base LLM to get confidence.
Outcome:	The proposed solution reduces expected calibration error (ECE) by 42.90% compared to the best unsupervised baselines.

Copied to clipboard

Xuemei Tang, Jun Wang, Qi Su, Chu-Ren Huang, Jinghang Gu

IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models (2023.emnlp-main)

Challenge:	Existing approaches to enhance sequence labeling models require data heterogeneity and additional modules.
Approach:	They propose a dual-stage curriculum learning framework specifically designed for sequence labeling tasks.
Outcome:	The proposed model improves training and accelerates training, mitigating the slow training issue of complex models.

Copied to clipboard

Xiaoyue Wang, Xin Liu, Lijie Wang, Yaoxiang Wang, Jinsong Su, Hua Wu

Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension (D19-58)

Challenge:	Using manual data analysis, dataset refinement approaches are often unable to cover all the potential biased features.
Approach:	They propose an iterative bias-aware dataset refinement framework which debiases NLU models without predefining biased features.
Outcome:	The proposed framework outperforms existing methods and is compatible with model-centric methods.

Copied to clipboard

Qian Li, Hui Su, Cheng Niu, Daling Wang, Zekang Li, Shi Feng, Yifei Zhang

TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking (2026.acl-long)

Challenge:	Existing question reformulation models are based on supervised question labels without considering feedback information from answers.
Approach:	They propose a question reformulation model that integrates conversational history information with reinforcement learning.
Outcome:	The proposed model is more effective in conversational machine comprehension with reinforcement learning.

Copied to clipboard

Xiaocheng Zhang, Xi Wang, Yifei Lu, Jianing Wang, Zhuangzhuang Ye, Mengjiao Bao, Peng Yan, Xiaohong Su

ProgCo: Program Helps Self-Correction of Large Language Models (2025.acl-short)

Challenge:	Existing benchmarks lack social metadata and evaluation framework to meet this urgent evaluation needs.
Approach:	They propose a benchmark capable of evaluating HPA and three fact-checking tasks.
Outcome:	The proposed framework improves HPA and computational efficiency for RLM-driven systems.

Copied to clipboard

Xiaoshuai Song, Yanan Wu, Weixun Wang, Jiaheng Liu, Wenbo Su, Bo Zheng

LMDX: Language Model-based Document Information Extraction and Localization (2024.findings-acl)

Challenge:	Existing LLMs fail to self-correct and generate correct feedback, leading to misleading refinement and failure of self-refinement.
Approach:	They propose a program-driven self-correction approach that uses program-based verification to self-refine initial responses without external feedback.
Outcome:	The proposed model achieves self-correction and can be further enhanced when combined with real program tools.

Copied to clipboard

Vincent Perot, Kai Kang, Florian Luisier, Guolong Su, Xiaoyu Sun, Ramya Sree Boppana, Zilong Wang, Zifeng Wang, Jiaqi Mu, Hao Zhang, Chen-Yu Lee, Nan Hua

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging (2025.acl-long)

Challenge:	Large Language Models have revolutionized Natural Language Processing but their application in extracting information from visually rich documents has not been successful.
Approach:	They propose a language model-based document information extraction and localization methodology to reframe the document information extract task for a LLM.
Outcome:	The proposed method enables extraction of singular, repeated, and hierarchical entities with and without training data.

Copied to clipboard

Tingfeng Hui, Zhenyu Zhang, Shuohuan Wang, Yu Sun, Hua Wu, Sen Su

Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions (2024.emnlp-main)

Challenge:	Existing methods for tuning large language models from dense to MoE face significant data requirements and require large-scale post-training.
Approach:	They propose an upcycling instruction tuning approach for tuning a dense pre-trained model into a MoE instruction model using genetic algorithm and parameter merging.
Outcome:	The proposed approach improves the performance of large language models with a small amount of seed data and improves their scaling.

Copied to clipboard

Inderjeet Nair, Jiaye Tan, Xiaotian Su, Anne Gere, Xu Wang, Lu Wang

DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text (2023.findings-emnlp)

Challenge:	Recent advances in language models (LMs) have made it possible to automatically generate feedback that is actionable and well-aligned with human-specified attributes.
Approach:	They propose a tool that PROduces Feedback via learning from LM simulated student revisions and propose to iteratively optimize the feedback generator by directly maximizing the effectiveness of students’ overall revising performance.
Outcome:	The proposed approach surpasses baseline methods in effectiveness of improving students’ writing and demonstrates enhanced pedagogical values, even though it was not explicitly trained for this aspect.

Copied to clipboard

Jinyan Su, Terry Zhuo, Di Wang, Preslav Nakov

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025.acl-long)

Challenge:	Large language models generate huge amounts of text, making it impractical to manually distinguish whether a text is machine-generated.
Approach:	They propose two methods to detect machine-generated text by leveraging Log-Rank information and propose a faster method that uses less perturbations to achieve the same level of performance.
Outcome:	The proposed methods improve over the state of the art by 3.9 and 1.75 AUROC points absolute and require less perturbations to achieve the same level of performance.

Copied to clipboard

Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Z.y. Peng, Zhaoxiang Zhang, Zhicheng Zheng, Wenbo Su, Bo Zheng

A Peek into Token Bias: Large Language Models Are Not Yet Genuine Reasoners (2024.emnlp-main)

Challenge:	Recent advances in o1-like models have generated long Chain-of-Thought reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs).
Approach:	They propose a DeltaBench to analyze the quality and effectiveness of o1-like models and measure their ability to detect errors in long COT reasoning.
Outcome:	The proposed model can detect errors in long COT reasoning.

Copied to clipboard

Bowen Jiang, Yangxinyu Xie, Zhuoqun Hao, Xiaomeng Wang, Tanwi Mallick, Weijie Su, Camillo Taylor, Dan Roth

Knowledge Editing through Chain-of-Thought (2025.emnlp-main)

Challenge:	a new hypothesis-testing framework is developed to assess whether large language models possess genuine reasoning abilities or primarily depend on token bias.
Approach:	They propose a framework to assess whether large language models have genuine reasoning abilities or primarily depend on token bias.
Outcome:	The proposed framework outlines a list of hypotheses where token biases are readily identifiable . the results suggest that most LLMs still struggle with logical reasoning .

Copied to clipboard

Changyue Wang, Weihang Su, Qingyao Ai, Yichen Tang, Yiqun Liu

An Expert is Worth One Token: Synergizing Multiple Expert LLMs as Generalist via Expert Token Routing (2024.acl-long)

Challenge:	Existing knowledge editing methods focus on multi-hop QA tasks and require frequent retraining.
Approach:	They propose a new knowledge editing framework that updates large language models with new information to maintain their world knowledge without retraining.
Outcome:	The proposed method achieves state-of-the-art performance while offering superior generalization, effectiveness, and stability compared to existing methods.

Copied to clipboard

Ziwei Chai, Guoyin Wang, Jing Su, Tianjie Zhang, Xuanwen Huang, Xuwu Wang, Jingjing Xu, Jianbo Yuan, Hongxia Yang, Fei Wu, Yang Yang

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities across a wide spectrum of tasks, but performance and reliability in certain specialized domains still fall short of expectations.
Approach:	They propose a unified generalist framework that facilitates seamless integration of multiple expert LLMs.
Outcome:	The proposed framework outperforms existing multi-LLM collaboration paradigms across six diverse expert domains.

Revisiting Non-Autoregressive Translation at Scale (2023.findings-acl)

Copied to clipboard

Zhihao Wang, Longyue Wang, Jinsong Su, Junfeng Yao, Zhaopeng Tu

Multilinguality

Challenge:	Extensive experiments on two advanced NAT models show scaling can improve translation performance.
Approach:	They empirically examine the impact of scaling on NAT behaviors on a large-scale WMT dataset.
Outcome:	The proposed model can achieve comparable performance with the scaling model while maintaining the superiority of decoding speed with standard NAT models.

CoDA: Restoring Contextual Dominance via Copy-Encouraged Attention Intervention for Mitigating RAG Hallucinations (2026.findings-acl)

Copied to clipboard

JinWei Shi, Qizhuo Xie, Qianzi Hou, Zhipeng Wang, Wanting Su, Jianhua Zhao, Tao Zheng, Tieke He

CLEVA: Chinese Language Models EVAluation Platform (2023.emnlp-demo)

Challenge:	Retrieval-augmented generation reduces hallucination by grounding outputs in external evidence.
Approach:	They propose a lightweight inference-time attention intervention that amplifies evidence-aligned value states to enhance contextual faithfulness and reduce hallucination.
Outcome:	The proposed model reduces hallucination by grounding model outputs in external evidence.

Copied to clipboard

Yanyang Li, Jianqiao Zhao, Duo Zheng, Zi-Yuan Hu, Zhi Chen, Xiaohui Su, Yongfeng Huang, Shijia Huang, Dahua Lin, Michael Lyu, Liwei Wang

Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry (2026.acl-long)

Challenge:	Large language models (LLMs) have revolutionized natural language processing.
Approach:	They propose a Chinese-based platform that assesses Chinese LLMs using a standardized workflow and a unique sampling strategy.
Outcome:	CLEVA evaluates Chinese LLMs on a standardized workflow and a competitive leaderboard with minimal coding.

Copied to clipboard

Jiang Li, Tian Lan, Shanshan Wang, Dongxing Zhang, Dianqing Lin, Guanglai Gao, Derek F. Wong, Xiangdong Su

Challenge:	a recent study shows that large language models can generate text, but they can also fabricate large amounts of false or misleading content.
Approach:	They propose a benchmark to detect LLM-generated classical Chinese poetry . they compare 12 different AI detectors to find out whether a poem is authored by AI .
Outcome:	The proposed benchmark compared 12 AI detectors with a dataset of 30,664 Chinese poems . the results highlight the limitations of current Chinese text detectors .

M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)

Copied to clipboard

Zhaopeng Feng, Jiayuan Su, Jiamei Zheng, Jiahan Ren, Yan Zhang, Jian Wu, Hongwei Wang, Zuozhu Liu

Orchestrating Tokens and Sequences: Dynamic Hybrid Policy Optimization for RLVR (2026.findings-acl)

Challenge:	Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments.
Approach:	They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment.
Outcome:	The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini.

Copied to clipboard

Zijun Min, Bingshuai Liu, Ante Wang, Long Zhang, Anxiang Zeng, Haibo Zhang, Jinsong Su

Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings (2025.findings-acl)

Challenge:	Existing RLVR algorithms focus on different granularities and have complementary strengths and limitations.
Approach:	They propose a framework for reinforcement learning with verifiable rewards that bridges RLVR and GSPO . group-level importance ratios are used to update a policy, which preserves fine-grained credit assignment .
Outcome:	The proposed framework outperforms existing methods on seven reasoning benchmarks.

Copied to clipboard

Yuanhe Zhang, Zhenhong Zhou, Wei Zhang, Xinyue Wang, Xiaojun Jia, Yang Liu, Sen Su