Papers by Xiao He

Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition (2023.acl-long)

Challenge:	Prompt Engineering (PE) is renowned for improving IE performance through prompt modifications, but the realm of sample design for downstream fine-tuning remains unexplored.
Approach:	They propose a methodical approach to enhancing LLMs’ post-tuning performance by refining input, output, and reasoning designs.
Outcome:	The proposed approach outperforms heuristic design strategies on three complex IE tasks with four additional LLMs.

Copied to clipboard

Haodong Zhao, Ruifang He, Mengnan Xiao, Jing Xu

The “Knowledge–Behavior Gap” in Cultural Taboo Safety of Large Language Models (2026.acl-long)

Challenge:	Multi-level implicit discourse relation recognition (MIDRR) aims at identifying hierarchical discourse relations among arguments.
Approach:	They propose a prompt-based multi-level implicit discourse relation recognition framework that leverages parameter-efficient prompt tuning to drive inputted arguments to match the pre-trained space.
Outcome:	The proposed framework achieves comparable results on PDTB 2.0 and 3.0 using about 0.1% trainable parameters compared with baselines.

Copied to clipboard

Ying He, Sihang Jiang, Xingzhou Chen, Zhouhong Gu, Yiwei Gu, Minggui HE, Shimin Tao, null Mahongxia, Yanghua Xiao

Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)

Challenge:	Existing cultural benchmarks assess cultural knowledge or values biases, but ignore cultural taboos.
Approach:	They propose a benchmark to evaluate and improve the cultural taboo safety of large language models.
Outcome:	The proposed benchmark spans 77 countries and regions, and includes over 2,020 taboos.

Copied to clipboard

Yanda Li, Dixuan Wang, Jiaqing Liang, Guochao Jiang, Qianyu He, Yanghua Xiao, Deqing Yang

Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but struggle with some more complex reasoning tasks including logical reasoning.
Approach:	They propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW to evaluate LLMs’ capability of logical fallacy understanding.
Outcome:	The proposed dataset can be used to evaluate LLMs’ LFU capability and to fine-tune LLM models to obtain significantly enhanced performance on logical reasoning.

Copied to clipboard

Ying He, Zhouhong Gu, Zhecheng Hu, Yubo Zhou, Hao Shen, Jiaqing Liang, Zhaoqian Dai, Ma Shuguang, Fei Yu, Yanghua Xiao, Zhixu Li

JiraiBench: A Bilingual Benchmark for Evaluating Large Language Models’ Detection of Human risky health behavior Content in Jirai Community (2026.eacl-long)

Challenge:	Existing LLMs struggle to identify errors in financial documents, a study shows . 18% of financial practitioners make errors daily, one-third make errors several times weekly, and 59% make errors multiple times monthly.
Approach:	They introduce FinED-Bench, a publicly available Benchmark for financial error detection . it covers nine real-world financial scenarios and includes over 900 documents in 2025 . supervised fine-tuning can significantly improve the performance of weaker LLMs, they show .
Outcome:	The proposed benchmark covers nine real-world financial scenarios and includes over 900 documents reported in 2025 that are unseen by existing language models.

Copied to clipboard

Yunze Xiao, Tingyu He, Lionel Z. Wang, Yiming Ma, Xingyu Song, Xiaohang Xu, Mona T. Diab, Irene Li, Ka Chung Ng

HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet Expansion (2023.acl-long)

Challenge:	a cross-lingual dataset captures a transnational cultural phenomenon . risky health behaviors (RHB) are often linked to complex mental health conditions .
Approach:	They present the first cross-lingual dataset that captures a transnational cultural phenomenon . their dataset of more than 15,000 annotated social media posts forms the core of JiraiBench .
Outcome:	The study shows that cultural context can be more influential than linguistic similarity . the study also shows that the Japanese prompts better handle Chinese content .

Copied to clipboard

Wanrong He, Haoyu Dong, Yihuai Gao, Zhichao Fan, Xingzhuo Guo, Zhitao Hou, Xiao Lv, Ran Jia, Shi Han, Dongmei Zhang

Challenge:	HermEs is a spreadsheet formula prediction language that is difficult for Excel users without programming experience to master.
Approach:	They propose a hierarchical approach to formula prediction via HiEraRchical forMulet ExpanSion . they propose generating formulas in a fixed order using hierarchically generated formulas .
Outcome:	The proposed approach improves formula prediction accuracy by guaranteeing correct grammar and streamlining token-level decoding with high-level Formulet.

Order Doesn’t Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentation (2025.emnlp-main)

Copied to clipboard

Qianxi He, Qianyu He, Jiaqing Liang, Weikang Zhou, Zeye Sun, Fei Yu, Yanghua Xiao

SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis (2020.acl-main)

Challenge:	Logical reasoning is essential for large language models (LLMs) to ensure accurate and coherent inferences.
Approach:	They propose an order-centric data augmentation framework based on commutativity in logical reasoning that randomly shuffles independent premises to introduce condition order augmentation.
Outcome:	The proposed framework improves LLMs’ reasoning performance and adaptability to diverse logical structures.

Copied to clipboard

Hao Tian, Can Gao, Xinyan Xiao, Hao Liu, Bolei He, Hua Wu, Haifeng Wang, Feng Wu

DrAgent: Empowering Large Language Models as Medical Agents for Multi-hop Medical Reasoning (2025.findings-emnlp)

Challenge:	sentiment knowledge is ignored in sentiment analysis, despite its use in pretraining.
Approach:	They propose to use sentiment knowledge to learn a unified sentiment representation for multiple sentiment analysis tasks.
Outcome:	The proposed method outperforms strong pre-training baseline on three kinds of sentiment tasks.

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xin Liu, Zhengyang Wang, Xianfeng Tang, Shiyang Li, Xiang He, Ruijie Wang, Bing Yin, Xiao Gu, Lei Clifton, David A. Clifton

HAUSER: Towards Holistic and Automatic Evaluation of Simile Generation (2023.acl-long)

Challenge:	commercial LLMs can be difficult to use in real-world clinical decision-making . a lightweight LLM can be used to collaborate with diverse clinical tools .
Approach:	They propose a lightweight LLM that can be used to build medical LLMs as agents . they use recursive curriculum learning to optimize the LLM in an easy-to-hard progression .
Outcome:	The proposed approach outperforms human experts in medical examinations on diverse datasets.

Copied to clipboard

Qianyu He, Yikai Zhang, Jiaqing Liang, Yuncheng Huang, Yanghua Xiao, Yunwen Chen

Text Generation

Challenge:	Similes are a crucial part of creative writing, but there is still a lack of evaluation metrics for simile generation.
Approach:	They propose to use similes as a tool to evaluate simile generation metrics . they propose to combine five criteria and automatic metrics for each criterion .
Outcome:	The proposed metrics are significantly more correlated with human ratings from each perspective compared with prior automatic metrics.

Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Copied to clipboard

Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu

PodAgent: A Comprehensive Framework for Podcast Generation (2025.findings-acl)

Challenge:	Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach:	They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome:	The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.

Copied to clipboard

Yujia Xiao, Lei He, Haohan Guo, Feng-Long Xie, Tan Lee

MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment (2025.acl-long)

Challenge:	Existing automatic audio generation methods struggle to generate podcast-like audio programs effectively.
Approach:	They propose a framework for creating podcast-like audio programs that generates informative topic-discussion content by designing a multi-agent collaboration system, builds a voice pool and uses LLM-enhanced speech synthesis to generate expressive conversational speech.
Outcome:	The proposed framework surpasses direct GPT-4 generation in topic-discussion dialogue content, and produces more expressive conversational speech.

Copied to clipboard

Weicong Qin, Yi Xu, Weijie Yu, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu

Information Retrieval

Challenge:	Existing personalized product search methods assume that users’ query fully captures their real motivation, but in practice, user's queries do not always articulate the requirements.
Approach:	They propose a Motivation-Aware Personalized Search method that embeds queries and consultations into a unified semantic space via LLMs and utilizes a Mixture of Attention Experts (MoAE) to prioritize critical semantics.
Outcome:	Extensive experiments on real and synthetic data show that the proposed method outperforms existing methods in retrieval and ranking tasks.

Exploring the Capacity of Pretrained Language Models for Reasoning about Actions and Change (2023.acl-long)

Copied to clipboard

Weinan He, Canming Huang, Zhanhao Xiao, Yongmei Liu

TMFN: A Target-oriented Multi-grained Fusion Network for End-to-end Aspect-based Multimodal Sentiment Analysis (2024.lrec-main)

Challenge:	Recent transformer-based language models (LMs) provide reasoning over textual benchmarks . RAC is essential to understand and interact with the ever-changing environment .
Approach:	They propose to use a transformer-based language model to learn to reason over textual benchmarks.
Outcome:	The proposed model minimizes the influence of other linguistic requirements to focus on RAC.

Copied to clipboard

Di Wang, Yuzheng He, Xiao Liang, Yumin Tian, Shaofeng Li, Lin Zhao

Stumbling Blocks: Stress Testing the Robustness of Machine-Generated Text Detectors Under Attacks (2024.acl-long)

Challenge:	Existing methods for multimodal aspect-based sentiment analysis focus on fusing image regional information and textual words.
Approach:	They propose a multimodal aspect-based sentiment analysis method that integrates regional and global image information with global image data.
Outcome:	Experiments show that the proposed method outperforms state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Yichen Wang, Shangbin Feng, Abe Hou, Xiao Pu, Chao Shen, Xiaoming Liu, Yulia Tsvetkov, Tianxing He

Robustness in NLP

Challenge:	Existing studies on this topic focus on the robustness of specific detectors or particular attack methods.
Approach:	They stress test the detectors’ robustness to malicious attacks under realistic scenarios using LLMs and metric-based detectors.
Outcome:	The proposed methods are based on a set of LLM-based models and their performance is compared under different budget levels.

Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference (2026.acl-long)

Copied to clipboard

null Zhouxuwen, Fangxin Liu, Chao Wang, Xiao Zheng, Hao Zheng, Min He, Li Jiang, Haibing Guan

Green & Sustainable NLP

Challenge:	Speculative decoding (SD) is a powerful and efficient way to accelerate autoregressive generation.
Approach:	They propose a training-free framework that recovers valid tokens discarded by standard verification . they use online correction memory and Semantic Consistency Gating to analyze rejections .
Outcome:	The proposed framework outperforms existing methods and achieves peak throughput speedup of 2.33x.

Let’s Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models (2024.lrec-main)

Copied to clipboard

Shunyu Liu, Jie Zhou, Qunxi Zhu, Qin Chen, Qingchun Bai, Jun Xiao, Liang He

Sentiment Analysis

Challenge:	Empirical evaluations conducted on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.
Approach:	They propose a diffusion model which extracts aspects step by step and learns a denoising process that progressively restores them in a reverse manner.
Outcome:	Empirical evaluations on eight benchmark datasets underscore the compelling advantages offered by DiffusionABSA when compared against robust baseline models.

Leveraging Web-Crawled Data for High-Quality Fine-Tuning (2024.findings-emnlp)

Copied to clipboard

Jing Zhou, Chenglin Jiang, Wei Shen, Xiao Zhou, Xiaonan He

Translation or Recitation? Calibrating Evaluation Scores for Machine Translation of Extremely Low-Resource Languages (2026.acl-short)

Challenge:	Currently, large language models are fine-tuned using expensive human-annotated data or GPT-4 generated data.
Approach:	They propose to use web-crawled data to train a language model on a smaller set of data . their results show that the model can convert web data with irregular formats into high-quality ones .
Outcome:	The proposed model outperforms open-source models larger than 32B and outperformed open-sourced models such as GPT-3.5.

Copied to clipboard

Danlu Chen, Ka Sing He, Jiahe Tian, Chenghao Xiao, Zhaofeng Wu, Taylor Berg-Kirkpatrick, Freda Shi

Multilinguality

Challenge:	Existing studies show that performance across low-resource settings is variable, resulting in a significant barrier for the MT community.
Approach:	They propose to use FRED Difficulty Metrics to contextualize reported performance across different language pairs to determine whether breakthroughs reported in other contexts are artifacts of benchmark collection.
Outcome:	The proposed metrics explain a significant portion of result variability rather than model capability.

End-to-End Conversational Search for Online Shopping with Utterance Transfer (2021.emnlp-main)

Copied to clipboard

Liqiang Xiao, Jun Ma, Xin Luna Dong, Pascual Martínez-Gómez, Nasser Zalmout, Chenwei Zhang, Tong Zhao, Hao He, Yaohui Jin

Natural Language Interfaces

Challenge:	a new study proposes a conversational search system that integrates product attributes and dialog with search . but it faces two real world challenges: imperfect product schema/knowledge and lack of training dialog data .
Approach:	They propose an end-to-end conversational search system that integrates search with text . they propose an utterance transfer approach that generates dialogue utterations from other domains .
Outcome:	The proposed system outperforms the best tested baseline in a conversational search dataset for online shopping.

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond (2025.acl-industry)

Copied to clipboard

Liang Wen, Yunke Cai, Fenrui Xiao, Xin He, Qi An, Zhenyu Duan, Yimin Du, Junchen Liu, Tanglifu Tanglifu, Xiaowei Lv, Haosheng Zou, Yongchao Deng, Shousheng Jia, Xiangzheng Zhang

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Challenge:	Experimental results show that opensource curriculum training is more effective when distinct datasets are available for different training stages.
Approach:	They propose an opensource suite for training long reasoning models using publicdata and models.
Outcome:	The proposed model outperforms DeepSeek-R1-DistillQwen-32B models in math reasoning.

Copied to clipboard

Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang

BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models (2020.findings-emnlp)

Challenge:	Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach:	They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome:	The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.

Copied to clipboard

Bin He, Di Zhou, Jinghui Xiao, Xin Jiang, Qun Liu, Nicholas Jing Yuan, Tong Xu

Pengwei Zhan, Jing Yang, He Wang, Chao Zheng, Xiao Huang, Liming Wang

Challenge:	Existing knowledge representation learning methods do not use graph contextualized knowledge.
Approach:	They propose to model subgraphs in a medical KG and integrate it with a pre-trained language model to do knowledge generalization.
Outcome:	The proposed model achieves state-of-the-art on several medical NLP tasks . it improves on MedERNIE, and the proposed model is effective .

Copied to clipboard

SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams (2026.findings-acl)

Challenge:	Neural language models are vulnerable to word-level adversarial text attacks . previous word-based search methods assume important words influence prediction .
Approach:	They propose a method for similarizing the influence of words with contrast learning that encourages model to learn sentence representations in which words of varying importance have a more uniform influence on prediction.
Outcome:	The proposed method is compatible with various training methods and improves model robustness against various adversarial attacks.

Copied to clipboard

Chenglong Wang, Canjia Li, Xingzhao Zhu, Yifu Huo, Huiyu Wang, Weixiong Lin, Yun Yang, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Tong Xiao

Challenge:	Existing approaches to generate relevance judgments are limited due to dynamic nature of query distributions.
Approach:	They propose a self-evolving relevance model approach to generalize queries to practical search scenarios . they use a multi-agent sample miner and a relevance annotator to generate reliable labels .
Outcome:	The proposed approach can achieve significant performance gains on a large-scale industrial platform, validated by offline multilingual evaluations and online testing.

Harnessing Consistency for Robust Test-Time LLM Ensemble (2026.findings-eacl)

Copied to clipboard

Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong

Robustness in NLP

Challenge:	Existing efforts to improve LLM ensemble quality have focused on model consistency, but failures are often due to heterogeneous tokenization schemes and varying model expertise.
Approach:	They propose a plug-and-play technique that harnesses model consistency for robust LLM ensemble.
Outcome:	The proposed technique improves ensemble performance and robustness against erroneous signals.

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles (2024.findings-emnlp)

Copied to clipboard

Xiao Pu, Tianxing He, Xiaojun Wan

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

Challenge:	Prompt compression reduces inference time and costs while maintaining informativeness for different usage scenarios.
Approach:	They propose a framework that adapts a smaller language model to compress prompts for a larger model on a new task without additional training.
Outcome:	The proposed framework outperforms two baseline models in four tasks . iteratively generates and selects effective compressed prompts as task-specific demonstrations .

Copied to clipboard

Liqiang Xiao, Lu Wang, Hao He, Yaohui Jin

AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks (2023.findings-acl)

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

Copied to clipboard

Xinyi He, Mengyu Zhou, Mingjie Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian Yuan, Dongmei Zhang

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

Challenge:	Tabular data analysis is performed everyday across various domains.
Approach:	They propose to use a dataset of 467k tables with supervision labels for four types of field metadata.
Outcome:	The proposed framework improves the understanding capability of tabular models by incorporating distribution and knowledge information.

Copied to clipboard

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents (2026.acl-long)

Copied to clipboard

Yuanchen Bei, Tianxin Wei, Xuying Ning, Yanjun Zhao, Zhining Liu, Xiao Lin, Yada Zhu, Hendrik Hamann, Jingrui He, Hanghang Tong

Natural Language Interfaces

Challenge:	Existing benchmarks evaluate multi-session memory in text-only conversations or assess multimodal understanding within localized contexts.
Approach:	They propose a benchmark for evaluating multimodal long-term conversational memory in MLLM agents.
Outcome:	The proposed framework assesses key memory capabilities along three functional dimensions: memory extraction and test-time adaptation, memory reasoning, and memory knowledge management.

Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios (2026.findings-acl)

Copied to clipboard

Xin-Yu Xiao, Ye Tian, Erwei Yin, Zhixian He, Shiqi Wang, Yalei Liu, Qianchen Xia

Exploring Logically Dependent Multi-task Learning with Causal Inference (2020.emnlp-main)

Challenge:	Existing benchmarks focus on static, context-independent reasoning tasks and fail to capture constraints and dependencies of lunar missions.
Approach:	They propose a benchmark to assess the task-oriented reasoning and decision-making performance of large language models through 3,000 tasks derived from mission procedures and documentation.
Outcome:	The proposed model achieves 47.8% accuracy compared with 65.1% for human experts on 36 representative missions.

Copied to clipboard

Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin

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

Challenge:	Hierarchical multi-task learning models can utilize task dependencies by stacking encoders and outperform democratic ones.
Approach:	They propose a model that utilizes the labels of all lower-level tasks and a Gumbel sampling model to deal with cascading errors.
Outcome:	The proposed model outperforms democratic models on six out of seven subtasks and achieves state-of-the-art on the two English and one Chinese datasets.

Copied to clipboard

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

Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases (2024.findings-emnlp)

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

Copied to clipboard

Wenhao Huang, Qianyu He, Zhixu Li, Jiaqing Liang, Yanghua Xiao

Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies (2025.acl-long)

Challenge:	Definition bias is a negative phenomenon that can mislead models.
Approach:	They propose a framework that measures definition bias, bias-aware fine-tuning and task-specific bias mitigation to mitigate definition bias in information extraction.
Outcome:	The proposed framework mitigates definition bias in information extraction tasks by measuring definition bias, bias-aware fine-tuning, and task-specific bias mitigation.

Copied to clipboard

Zhengyu Chen, Siqi Wang, Teng Xiao, Yudong Wang, Shiqi Chen, Xunliang Cai, Junxian He, Jingang Wang

Diversified Multiple Instance Learning for Document-Level Multi-Aspect Sentiment Classification (2020.emnlp-main)

Challenge:	Existing scaling laws suggest augmenting model size and training data results in enhanced performance, but recent studies reveal deviations, particularly in large language models, where performance improvements decelerate—a phenomenon known as sub-scaling.
Approach:	They propose a sub-optimal scaling law that better predicts performance in sub-scaling regimes by examining data quality and training strategies.
Outcome:	The proposed scaling law better predicts performance in sub-scaling regimes, highlighting the importance of data quality and diversity.

Copied to clipboard

Yunjie Ji, Hao Liu, Bolei He, Xinyan Xiao, Hua Wu, Yanhua Yu

Information Retrieval

Challenge:	Experimental results show that D-MILN outperforms recent weakly-supervised baselines . document-level multi-aspect sentiment classification requires a lot of manual aspect-level annotations - which is time-consuming and laborious .
Approach:	They propose a novel Diversified Multiple Instance Learning Network to achieve DMSC with only document-level weak supervision.
Outcome:	The proposed method outperforms weakly-supervised baselines on TripAdvisor and BeerAdvocate datasets.

Enhancing Local Feature Extraction with Global Representation for Neural Text Classification (D19-1)

Copied to clipboard

Guocheng Niu, Hengru Xu, Bolei He, Xinyan Xiao, Hua Wu, Sheng Gao

Vanessa: Visual Connotation and Aesthetic Attributes Understanding Network for Multimodal Aspect-based Sentiment Analysis (2024.findings-emnlp)

Challenge:	Existing methods for text classification learn long dependency by deeply stacking or hybrid modeling.
Approach:	They propose a global-based local feature extraction architecture with global information incorporated into the local feature extractor.
Outcome:	The proposed architecture outperforms the previous best models on eight benchmark datasets.

Copied to clipboard

Luwei Xiao, Rui Mao, Xulang Zhang, Liang He, Erik Cambria

Sentiment Analysis

Challenge:	Existing methods to analyze images focus on superficial features or descriptions, omitting subtle contextual information.
Approach:	They propose a Visual Connotation and Aesthetic Attributes Understanding Network (Vanessa) for Multimodal Aspect-based Sentiment Analysis.
Outcome:	The proposed network captures both implicit and explicit sentimental cues and can be used to enrich textual sentiment analysis.

ChemAmp: Amplified Chemistry Tools via Composable Agents (2026.findings-acl)

Copied to clipboard

Zhucong Li, Powei Chang, Jin Xiao, Zhijian Zhou, Qianyu He, Jiaqing Liang, Fenglei Cao, Xu Yinghui, Yuan Qi

Challenge:	LLM-based agents are powerful tools for automating complex scientific workflows, especially in chemistry, but their single-task performance is limited by tool constraints.
Approach:	They propose a framework that optimizes the collective capabilities of specialized tools by dynamic coordination within individual tasks.
Outcome:	The proposed framework outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration.

From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Qianyu He, Jie Zeng, Qianxi He, Jiaqing Liang, Yanghua Xiao

A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation (2020.coling-main)

Challenge:	Large language models (LLMs) follow instructions with elaborate requirements, yet it remains under-explored how to enhance their ability to follow complex instructions with multiple constraints.
Approach:	They propose a method to obtain and utilize effective training data to enhance LLMs' ability to follow complex instructions with multiple constraints.
Outcome:	The proposed framework improves models' ability to follow instructions generally and generalize effectively across out-of-domain, in domain, and adversarial settings while maintaining general capabilities.

Copied to clipboard

Wenqing Chen, Jidong Tian, Liqiang Xiao, Hao He, Yaohui Jin

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

Challenge:	Paraphrase generation is a longstanding problem in natural language processing (NLP) Neural network-based methods have shown great progress on paraphrase generation.
Approach:	They propose a framework that integrates variational inference on a target-related latent variable to introduce the diversity.
Outcome:	The proposed framework outperforms baseline models on the metrics based on n-gram matching and semantic similarity, and it can generate multiple different paraphrases by assembling different syntactic variables.

Copied to clipboard

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

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models (2025.findings-acl)

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

Copied to clipboard

Qingyu Ren, Jie Zeng, Qianyu He, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu

InstructDiff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning (2026.acl-long)

Challenge:	In real-world scenarios, user instructions often contain soft constraints, which are semantically related and cannot be rule-based verified, posing challenges for large language models.
Approach:	They propose a pipeline to construct datasets with high-quality outputs for instructions containing soft constraints automatically and use Direct Preference Optimization (DPO) as the training method.
Outcome:	The proposed model improves the LLMs' soft constraint following ability by using direct preference optimization (DPO) and constraint quantity.

Copied to clipboard

Junyou Su, He Zhu, Xiao Luo, Liyu Zhang, Hong-Yu Zhou, Yun Chen, Peng Li, Yang Liu, Guanhua Chen

SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis (2020.coling-main)

Challenge:	Existing data selection methods suffer from severe domain specificity . existing methods for general instruction-following fail on reasoning tasks .
Approach:	They propose a framework that operationalizes contrastive entropy as a domain-adaptive selection criterion through warmup calibration, bi-directional NLL filtering, and entropic-based ranking.
Outcome:	Experiments show that InstructDiff outperforms baseline training on reasoning tasks while using only 10% of the data.

Copied to clipboard

Jie Zhou, Junfeng Tian, Rui Wang, Yuanbin Wu, Wenming Xiao, Liang He

UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models (2025.findings-naacl)

Challenge:	Pre-trained language models have been widely applied to cross-domain NLP tasks like sentiment analysis, but fine-tuning them on the source domain tends to overfit, leading to inferior results on the target domain.
Approach:	They propose to pre-train a sentiment-aware language model (SentiX) via domain-invariant sentiment knowledge from large-scale review datasets and utilize it for cross-domain sentiment analysis tasks without fine-tuning.
Outcome:	The proposed model achieves state-of-the-art in all the cross-domain sentiment analysis tasks and can be trained with only 1% samples and better than BERT with 90% samples.

Copied to clipboard

Yuzhe Yang, Yifei Zhang, Yan Hu, Yilin Guo, Ruoli Gan, Yueru He, Mingcong Lei, Xiao Zhang, Haining Wang, Qianqian Xie, Jimin Huang, Honghai Yu, Benyou Wang

Personalized Abstractive Summarization by Tri-agent Generation Pipeline (2024.findings-eacl)

Challenge:	Recent advances in large language models (LLMs) have expanded their potential applications in finance.
Approach:	They propose a framework to evaluate the ability of large language models to handle financial tasks using human expert evaluations and task-specific interactions.
Outcome:	The proposed framework evaluates the ability of large language models to handle complex financial tasks and combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios.

Copied to clipboard

Wen Xiao, Yujia Xie, Giuseppe Carenini, Pengcheng He

Diagnosing the First-Order Logical Reasoning Ability Through LogicNLI (2021.emnlp-main)

Challenge:	Existing research shows that large language models do not consistently satisfy users' preferences or expectations.
Approach:	They propose a tri-agent generation pipeline that includes a generator, an instructor, and an editor to enhance output personalization.
Outcome:	The proposed pipeline generates outputs that better meet user expectations on two abstractive summarization datasets.

Copied to clipboard

Jidong Tian, Yitian Li, Wenqing Chen, Liqiang Xiao, Hao He, Yaohui Jin

GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks (2026.acl-long)

Challenge:	Existing studies have focused on diagnosing LMs' reasoning abilities in natural language understanding tasks.
Approach:	They propose a diagnostic method for first-order logic reasoning with a proposed benchmark, LogicNLI.
Outcome:	The proposed method disentangles the target FOL reasoning from commonsense inference and can be used to diagnose LMs from four perspectives: accuracy, robustness, generalization, and interpretability.

Copied to clipboard

Jianwen Luo, Yiming Huang, Jinxiang Meng, Fangyu Lei, Shizhu He, Xiao Liu, Shanshan Jiang, Bin Dong, Jun Zhao, Kang Liu

Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning (2026.findings-acl)

Challenge:	Existing toolsets that use large language models are limited to single-task settings.
Approach:	They propose a framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios.
Outcome:	The proposed framework achieves up to 4.3 faster milestone completion in Minecraft compared to the previous state-of-the-art method and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks.

Copied to clipboard

Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, Zhi Wang

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following (2026.acl-long)

Challenge:	Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have substantially improved the reasoning abilities of Large Language Models (LLMs).
Approach:	They propose a method that balances exploration and exploitation in the hidden-state space of response trajectories.
Outcome:	The proposed model yields consistent improvements across models, algorithms and reasoning benchmarks.

Copied to clipboard

Qingyu Ren, Qianyu He, Powei Chang, Jie Zeng, Zeye Sun, Fei Yu, Jiaqing Liang, Yanghua Xiao

SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models (2026.findings-acl)

Challenge:	Existing reinforcement learning approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks.
Approach:	They propose a self-supervised reinforcement learning framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training.
Outcome:	The proposed framework achieves strong improvements across 3 in-domain and 5 out-of-domain datasets while maintaining computational efficiency.

Copied to clipboard

Yifu Huo, Chenglong Wang, Ziming Zhu, Shunjie Xing, Peinan Feng, Tongran Liu, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Zhengtao Yu, Tong Xiao

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Challenge:	Reinforcement learning (RL) training typically improves single-sample success rates but limited exploration of diverse reasoning trajectories.
Approach:	They propose a training paradigm that interleaves conventional RL with inverse reinforcement learning (IRL) they propose 'Steering Probability Squeezing' to enhance exploration without external supervision .
Outcome:	The proposed training paradigm improves Pass@k and improves exploration of diverse reasoning trajectories without external supervision.

Copied to clipboard

Nan He, Weichen Xiong, Hanwen Liu, Yi Liao, Lei Ding, Kai Zhang, Guohua Tang, Xiao Han, Yang Wei

Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models (2026.findings-acl)

Challenge:	Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach:	They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome:	The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.

Copied to clipboard

He Xiao, Qingyao Yang, Dirui Xie, Wendong XU, Zunhai Su, Runming Yang, Haobo Liu, Wenyong Zhou, Zhengwu Liu, Ngai Wong

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Challenge:	Large language models with billions of parameters are often over-provisioned . smaller models exhibit lower robustness under extreme low-bit quantization .
Approach:	They propose a hardware-native, metric-driven post-training quantization framework that keeps uniform bit-width within each layer while mixing precision across layers.
Outcome:	LieQ reduces large accuracy gap observed for large language models with billions of parameters while preserving standard multiplication kernels.

Copied to clipboard

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)

Challenge:	Existing research on reinforcement learning for LLMs under data scarcity has not been unified.
Approach:	They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric.
Outcome:	The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area.

Copied to clipboard

Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu

On the Zero-Shot Generalization of Machine-Generated Text Detectors (2023.findings-emnlp)

Challenge:	Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.
Approach:	They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs.
Outcome:	The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback.

Copied to clipboard

Xiao Pu, Jingyu Zhang, Xiaochuang Han, Yulia Tsvetkov, Tianxing He

Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Zhenqiang Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi W. Ma, Chaowei Xiao, Bo Li, Ahmed Abbasi, Dongwon Lee, Heng Ji, Denghui Zhang

Challenge:	rampant proliferation of large language models generates text indistinguishable from human-written language.
Approach:	They train neural detectors on outputs of a new generator and test their performance on held-out generators.
Outcome:	The proposed detectors can be built on training data from medium-sized models.

Copied to clipboard

Paraphrasing

Challenge:	Copyright Detective is the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs.
Approach:	They propose a system that detects copyright infringements and visualizes them . they use content recall testing, paraphrase-level similarity analysis and persuasive jailbreak probing .
Outcome:	The proposed system detects, analyzes, and visualizes potential copyright risks in LLM outputs.

SpiderFlow: Efficient Topology-Aware Scheduling for LLM Training Across Decentralized GPU Clusters (2026.acl-long)

Copied to clipboard

Zihan Chang, Shuibing He, Bo Zhou, Sheng Xiao, Siling Yang, Rui Wang, Zhe Pan

What Makes an Ideal Quote? Recommending “Unexpected yet Rational” Quotations via Novelty (2026.acl-long)

Challenge:	Existing approaches to training large language models lack topologyaware task scheduling mechanisms and model parallelization strategies.
Approach:	They propose a topology-aware scheduling system specifically designed for decentralized GPU clusters . they propose heuristic methods at the inter-cluster level with ILP-based optimization within clusters.
Outcome:	The proposed system reduces job completion time by 1.2-1.3 and improves throughput by 1.12-1.25 . it also reduces scheduling overhead by 20-90 on average compared to state-of-the-art scheduling systems.

Copied to clipboard

Powei Chang, Jin Xiao, Guanglei Yue, Qianyu He, Yanghua Xiao, Deqing Yang, Jiaqing Liang

Challenge:	Prior systems focus on topical relevance and overlook what makes quotes memorable.
Approach:	They propose a system that maps quotations and contexts into deep-meaning labels for label-enhanced retrieval.
Outcome:	The proposed system can recommend quotations that are contextually novel while semantically coherent.

Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models (2024.findings-acl)

Copied to clipboard

Yikai Zhang, Qianyu He, Xintao Wang, Siyu Yuan, Jiaqing Liang, Yanghua Xiao

DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models (2024.emnlp-main)

Challenge:	Multi-Modal Knowledge Graphs (MMKGs) are knowledge graphs that integrate and align information from diverse modalities (e.g., text and images).
Approach:	They propose a framework that integrates image-text pairs of long-tailed entities and a concept guidance module that offers explainability and enables human verification.
Outcome:	The proposed framework improves the accuracy of recognizing long-tailed image-text pairs compared to baselines and also offers flexibility and explainability.

Copied to clipboard

Yiming Huang, Jianwen Luo, Yan Yu, Yitong Zhang, Fangyu Lei, Yifan Wei, Shizhu He, Lifu Huang, Xiao Liu, Jun Zhao, Kang Liu

Programming Languages in NLP

Challenge:	DA-Code is a code generation benchmark designed to assess LLMs on agent-based data science tasks.
Approach:	They propose a code generation benchmark specifically designed for LLMs on agent-based data science tasks.
Outcome:	The benchmark performs better than existing frameworks, but lacks accuracy . it is based on real-world data, and includes examples that cover a wide range of tasks .

MetaPro Online: A Computational Metaphor Processing Online System (2023.acl-demo)

Copied to clipboard

Rui Mao, Xiao Li, Kai He, Mengshi Ge, Erik Cambria

Challenge:	Metaphors do not take literal meanings in contexts, which may cause difficulties for language learners and machines to understand them.
Approach:	They propose a computational metaphor processing online system that queries metaphoricity labels, paraphrases and concept mappings for non-domain-specific text.
Outcome:	The proposed system can query metaphoricity labels, paraphrases, and concept mappings for non-domain-specific text without coding background.

Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following (2025.findings-acl)

Copied to clipboard

Jie Zeng, Qianyu He, Qingyu Ren, Jiaqing Liang, Weikang Zhou, Zeye Sun, Fei Yu, Yanghua Xiao

Challenge:	Existing large language models struggle to follow multi-constraint instructions in real-world applications.
Approach:	They propose to quantify the difficulty distribution of constraints by a novel Difficulty Distribution Index (CDDI) they find that LLMs are more performant when presented with constraints in a “hard-to-easy” order.
Outcome:	The proposed model is more performant when presented with constraints in a “hard-to-easy” order, compared with existing models with different architectures and sizes of parameters.

APEX: Learning Adaptive Priorities for Multi-Objective Alignment in Vision-Language Generation (2026.findings-acl)

Copied to clipboard

Dongliang Chen, Xinlin Zhuang, Junjie Xu, Luojian Xie, Zehui Wang, Jiaxi Zhuang, Haolin Yang, Liang Dou, Xiao He, Xingjiao Wu, Ying Qian

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs (2026.findings-acl)

Challenge:	APEX optimizes for text-to-image generation by combining learning potential, conflict penalty, and progress need.
Approach:	They propose an algorithm that stabilizes heterogeneous rewards and dynamically schedules objectives . they propose a method that achieves better Pareto trade-offs across four heterogenous objectives based on P3 Adaptive Priorities .
Outcome:	The proposed algorithm achieves better pareto trade-offs across four heterogeneous objectives while maintaining competitive OCR accuracy.

Copied to clipboard

Zhongxiang Sun, Yi Zhan, Chenglei Shen, Weijie Yu, Xiao Zhang, Ming He, Jun Xu

Weicong Qin, Yi Xu, Weijie Yu, Teng Shi, Chenglei Shen, Ming He, Jianping Fan, Xiao Zhang, Jun Xu

Challenge:	Personalization can inadvertently distort factual reasoning when faced with factual queries.
Approach:	They propose a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior.
Outcome:	Experiments across multiple LLM backbones and personalization methods show that FPPS significantly improves factual accuracy while maintaining personalized performance.

Copied to clipboard

Information Retrieval

Challenge:	Existing methods rely on semantic similarity to align historical consultations with current queries due to the absence of ‘value’ labels, but this lacks exploration of needs in user consultations.
Approach:	They propose a consultation value assessment framework that evaluates historical consultations from three novel perspectives: (1) Scenario Scope Value, (2) Posterior Action Value, and (3) Time Decay Value.
Outcome:	The proposed model outperforms baselines on public and commercial datasets on both retrieval and ranking tasks.

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

Copied to clipboard

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

Learning to Contextually Aggregate Multi-Source Supervision for Sequence Labeling (2020.acl-main)

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

Copied to clipboard

Ouyu Lan, Xiao Huang, Bill Yuchen Lin, He Jiang, Liyuan Liu, Xiang Ren