Papers by Han Huang
CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection (2021.findings-acl)
Copied to clipboard
Henry Weld, Guanghao Huang, Jean Lee, Tongshu Zhang, Kunze Wang, Xinghong Guo, Siqu Long, Josiah Poon, Caren Han
| Challenge: | Existing toxic language detection models focus on the single utterance level without deeper understanding of context. |
| Approach: | They propose a dataset for in-game toxic language detection enabling joint intent classification and slot filling analysis, which is the core task of Natural Language Understanding (NLU). |
| Outcome: | The proposed framework handles utterance and token-level patterns, and rich contextual chatting history. |
Sample Design Engineering: An Empirical Study on Designing Better Fine-Tuning Samples for Information Extraction with LLMs (2024.emnlp-industry)
Copied to clipboard
| 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. |
Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners (2024.emnlp-main)
Copied to clipboard
Shimao Zhang, Changjiang Gao, Wenhao Zhu, Jiajun Chen, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang
| Challenge: | Large Language Models (LLMs) have shown impressive language capabilities, but most of them have very unbalanced performance across different languages. |
| Approach: | They propose to use question translation data to enhance LLMs' multilingual capabilities by using mechanistic interpretability methods. |
| Outcome: | The proposed method improves multilingual alignment even with unannotated answers in English and a wide range of languages even with instruction-tuned LLMs. |
Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation (2023.emnlp-main)
Copied to clipboard
Jiayu Lin, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
| Challenge: | Existing work describes paragraph-level counter-argument generation task as paragraph-based . however, sentence-level generation can be quite different due to its unique constraints and brevity-focused challenges. |
| Approach: | They propose a benchmark framework for sentence-level counter-argument generation . they use an annotated debate forum dataset to generate high-quality counter-argments . |
| Outcome: | The proposed framework and evaluator are competitive in counter-argument generation tasks. |
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators (2025.findings-acl)
Copied to clipboard
Jianling Li, ShangZhan Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, WangHaojie WangHaojie, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Triton is a high-level Python-like programming language for building efficient GPU kernels. |
| Approach: | They propose a TritonBench benchmark that provides a comprehensive evaluation of Tritonic operators on widely deployed GPUs. |
| Outcome: | The proposed benchmarks show that current LLMs struggle to generate efficient Triton operators on widely deployed GPUs aligned with industry applications. |
Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for aspect-based sentiment analysis of review text use only a few keywords describing each aspect/sentiment without using any labeled examples. |
| Approach: | They propose a weakly-supervised approach for aspect-based sentiment analysis which uses only a few keywords describing each aspect/sentiment without using any labeled examples. |
| Outcome: | The proposed method generates quality joint topics and outperforms baselines significantly on benchmark datasets. |
The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning (2026.acl-long)
Copied to clipboard
Renmiao Chen, Yida Lu, Shiyao Cui, Xuan Ouyang, Victor Shea-Jay Huang, Shumin Zhang, Chengwei Pan, Han Qiu, Minlie Huang
| Challenge: | Recent advances in multimodal reasoning may pose new safety risks . evaluators neglect reasoningbased safety, where harm emerges only through MLLMs . |
| Approach: | They introduce a benchmark for multi-image reasoning safety that includes 2,676 instances . they find that models with more advanced multi- image reasoning are more vulnerable . |
| Outcome: | The proposed benchmark consists of 2,676 instances covering 9 multi-image relations . the results show that models with more advanced multi- image reasoning are more vulnerable . |
The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Event schemas encode knowledge of stereotypical structures of events and their connections . previous work on event schema induction focuses on atomic events or linear temporal sequences . |
| Approach: | They propose a Temporal Complex Event Schema: a graph-based schema representation that encompasses events, arguments, temporal connections and argument relations. |
| Outcome: | The proposed model outperforms existing models on HITS@1 by 17.8%. |
Temporal Scaling Law for Large Language Models (2025.emnlp-main)
Copied to clipboard
Yizhe Xiong, Xiansheng Chen, Xin Ye, Hui Chen, Zijia Lin, Haoran Lian, Zhenpeng Su, Wei Huang, Jianwei Niu, Jungong Han, Guiguang Ding
| Challenge: | Existing studies have found that the test loss of LLMs scales as power-laws with model size, computational budget, and dataset size. |
| Approach: | They propose a concept of Temporal Scaling Law to study test loss of LLMs . they break down test loss into fine-grained token positions and develop a dynamic hyperbolic-law . |
| Outcome: | The proposed model predicts the test loss of LLMs as the training steps scale up. |
Layer-wise Fusion with Modality Independence Modeling for Multi-modal Emotion Recognition (2023.acl-long)
Copied to clipboard
Jun Sun, Shoukang Han, Yu-Ping Ruan, Xiaoning Zhang, Shu-Kai Zheng, Yulong Liu, Yuxin Huang, Taihao Li
| Challenge: | Existing studies focus on developing models that exploit the unification of multiple modalities. |
| Approach: | They propose to maintain modality independence by using a multi-modal transformer model that fuses all modalities. |
| Outcome: | The proposed model outperforms state-of-the-art models in multi-modal emotion recognition. |
If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs (2026.acl-long)
Copied to clipboard
Siqi Fan, Xiusheng Huang, Yiqun Yao, Xuezhi Fang, Kang Liu, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang
| Challenge: | Existing benchmarks for large language models (LLMs) fail to capture these dynamics, focusing on static, open-ended evaluations. |
| Approach: | They propose a benchmark to assess lifelong learning in large language models . they use two episodic datasets rich in narrative structure and character interactions . |
| Outcome: | Experiments on LLMs show that non-parametric methods outperform parametric ones in managing stateful learning. |
Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for reinforcement learning with verifiable rewards (RLVR) rely on static objective functions and rigid clipping strategies that misalign with the model’s evolving reasoning capabilities. |
| Approach: | They propose to incorporate Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC) to overcome limitations of static mechanisms. |
| Outcome: | Extensive experiments on nine reasoning tasks show the proposed paradigm outperforms state-of-the-art methods. |
Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing unsupervised reinforcement learning methods lack the capacity to adapt to the model’s evolving reasoning capabilities during training. |
| Approach: | They propose an unsupervised reinforcement learning algorithm that adapts rewards to balance consensus and exploration based on the Free Energy Principle. |
| Outcome: | Empirical evaluations on nine datasets show that FREIA outperforms baseline methods on reasoning tasks. |
Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing classification models only consider the temporal variations of existing data . current models focus on English corpora, leaving time as domains unexplored . |
| Approach: | They propose a framework to generalize classifiers over time on four languages, English, Danish, French, and German. |
| Outcome: | The proposed framework can generalize classifiers over time on four languages, English, Danish, French, and German. |
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning (2026.acl-long)
Copied to clipboard
Jingcheng Hu, Yinmin Zhang, Shijie Shang, Xiaobo Yang, Yue Peng, Zhewei Huang, Hebin Zhou, Xin Wu, Jie Cheng, Fanqi Wan, Xiangwen Kong, Chengyuan Yao, Kaiwen Yan, Ailin Huang, Hongyu Zhou, Qi Han, Zheng Ge, Xiangyu Zhang, Heung-Yeung Shum
| Challenge: | Parallel Coordinated Reasoning (PaCoRe) overcomes a central limitation of contemporary language models: their inability to scale test-time compute (TTC) far beyond sequential reasoning under a fixed context window. |
| Approach: | They propose a training-and-inference framework to overcome a central limitation of language models: their inability to scale test-time compute (TTC) under a fixed context window. |
| Outcome: | The proposed model scales to multi-million-token effective TTC without exceeding context limits. |
Orthogonal Subspace Learning for Language Model Continual Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for continual learning in language models suffer catastrophic forgetting when learning sequential tasks. |
| Approach: | They propose an orthogonal low-rank adaptation approach for continual learning in language models that uses orthogons to learn sequentially. |
| Outcome: | The proposed approach outperforms state-of-the-art methods on continual learning benchmarks and preserves generalization ability of LLMs on unseen tasks. |
“I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents (2025.emnlp-main)
Copied to clipboard
Jianshuo Dong, Yutong Zhang, Liu Yan, Zhenyu Zhong, Tao Wei, Ke Xu, Minlie Huang, Chao Zhang, Han Qiu
| Challenge: | Large language models (LLMs) exhibit prompt leakage vulnerabilities, raising intellectual property and confidentiality concerns. |
| Approach: | They use probing techniques to capture LLMs’ intent-related internal representations and show that they internalize prompt leakage intents in their hidden states before generating tokens. |
| Outcome: | The proposed probes achieve 90%+ AUROC across all tested models, even when applied to new system prompts and attacks. |
Few-Shot Named Entity Recognition: An Empirical Baseline Study (2021.emnlp-main)
Copied to clipboard
Jiaxin Huang, Chunyuan Li, Krishan Subudhi, Damien Jose, Shobana Balakrishnan, Weizhu Chen, Baolin Peng, Jianfeng Gao, Jiawei Han
| Challenge: | Existing methods to build named entity recognition systems with limited labeled data are lacking. |
| Approach: | They propose three orthogonal schemes to build named entity recognition systems when labeled data is limited. |
| Outcome: | The proposed NER systems outperform existing methods on few-shot and training-free settings. |
Text Classification Using Label Names Only: A Language Model Self-Training Approach (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current text classification methods require a large number of labeled documents as training data. |
| Approach: | They propose a model that uses only the label name of each class to train classification models on unlabeled data without using any labeled examples. |
| Outcome: | The proposed model achieves 90% accuracy on four benchmark datasets using label names as the only supervision . |
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for inductive reasoning over knowledge graphs lack the ability to model the logical structures of complex queries. |
| Approach: | They propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs that encodes linearized query structures and entities using pre-trained language models to find answers. |
| Outcome: | The proposed framework encodes query structures and entities using pre-trained language models to find answers. |
APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs (2025.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Sun Ao, Hao Zhou, Jie Zhou, Zhiyuan Liu, Maosong Sun
| Challenge: | Long-context inference is crucial for advancing large language models, but its prefill speed remains a bottleneck. |
| Approach: | They propose an efficient long-context inference framework that leverages multi-host approximate attention to enhance prefill speed. |
| Outcome: | The proposed framework achieves speedups of 9.2, 4.2, and 1.6 without any degradation in performance. |
GSID: Generative Semantic Indexing for E-Commerce Product Understanding (2025.emnlp-industry)
Copied to clipboard
Haiyang Yang, Qinye Xie, Qingheng Zhang, Chen Li Yu, Huike Zou, Chengbao Lian, Shuguang Han, Fei Huang, Jufeng Chen, Bo Zheng
| Challenge: | Structured product information is a major bottleneck for the efficiency of e-commerce platforms. |
| Approach: | They propose a data-driven approach to generate product structured representations using product metadata. |
| Outcome: | Extensive experiments show that GSID can generate better product representations on real-world e-commerce platforms. |
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety (2026.acl-long)
Copied to clipboard
Junxiao Yang, Haoran Liu, Jinzhe Tu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Jiaqi Weng, Jialing Tao, Hui Xue, Hongning Wang, Han Qiu, Minlie Huang
| Challenge: | Large language models (LLMs) have demonstrated better safety performance in high-resource languages than in low-resourced languages. |
| Approach: | They propose language-agnostic semantic alignment (LASA) which anchors safety alignment directly in semantic bottlenecks. |
| Outcome: | The proposed approach significantly improves safety across all languages: average attack success rate drops from 24.7% to 2.8% on LLaMA-3.1-8B-Instruct and remains within 3–4% across Qwen2.5 and Qwend3 Instruct models (7B–32B). |
Social Bot-Aware Graph Neural Network for Early Rumor Detection (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models do not distinguish genuine users from social bots, and their failure in identifying rumors timely. |
| Approach: | They propose to account for social bots’ behavior and construct a Social Bot-Aware Graph Neural Network to model early propagation of posts and then use it to detect rumors. |
| Outcome: | The proposed method achieves significant improvements over baselines and identifies rumors within 3 hours while maintaining more than 90% accuracy. |
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)
Copied to clipboard
Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun
| Challenge: | Existing benchmarks focus on character-centric approach and fail to reflect real-world applications. |
| Approach: | RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds. |
| Outcome: | RMTBench features 80 diverse characters and over 8,000 dialogue rounds. |
TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)
Copied to clipboard
Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan
| Challenge: | Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures. |
| Approach: | They propose a toolkit that supports pre-training models of different modalities. |
| Outcome: | The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks. |
Definition Modelling for Appropriate Specificity (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing definition generation techniques have faced various problems such as the out-of-vocabulary problem and over/under-specificity problems. |
| Approach: | They propose to leverage a pre-trained encoder-decoder model and introduce a re-ranking mechanism to model specificity in definitions. |
| Outcome: | The proposed method significantly outperforms the state-of-the-art method on standard evaluation datasets and shows that it addresses the over/under-specificity problems. |
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
Yingqian Cui, Pengfei He, Jingying Zeng, Hui Liu, Xianfeng Tang, Zhenwei Dai, Yan Han, Chen Luo, Jing Huang, Zhen Li, Suhang Wang, Yue Xing, Jiliang Tang, Qi He
| Challenge: | Chain-of-Thought (CoT) reasoning has improved the performance of large language models (LLMs) however, the detailed reasoning process in CoT often incurs long generation times and high computational costs due to the inclusion of unnecessary steps. |
| Approach: | They propose a method to identify critical reasoning steps using perplexity as a measure of their importance. |
| Outcome: | The proposed method achieves a better balance between reasoning accuracy and efficiency of CoT. |
Multi-Objective Forward Reasoning and Multi-Reward Backward Refinement for Product Review Summarization (2024.lrec-main)
Copied to clipboard
| Challenge: | Product review summarization aims to generate a concise summary based on product reviews . factual accuracy, aspect comprehensiveness, and content relevance are challenges . |
| Approach: | They propose an FB-Thinker framework to improve product review summarization ability . they propose two Chinese product review summary datasets for instruction-tuning and evaluation . |
| Outcome: | The proposed framework improves product review summarization with forward reasoning and backward refinement. |
CSP:Code-Switching Pre-training for Neural Machine Translation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train neural machine translation models are data-hungry and low-resource . et al., 2018; Radford e.t., 2019; Yang ee.,2019) proposes a new pre-training method for NMT . |
| Approach: | They propose a new pre-training method which randomly replaces some words in the input sentence with their translation words in target language. |
| Outcome: | The proposed method improves on unsupervised and supervised NMT models by making full use of monolingual corpora. |
Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area . current code-switching methods suffer from term boundary detection issues and out-of-dictionary problems. |
| Approach: | They propose a test-time code-switching framework which bridges the gap between bilingual training and monolingual test- time prediction. |
| Outcome: | The proposed framework achieves an average improvement of 3.7% on four cross-lingual datasets. |
FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection (2024.acl-long)
Copied to clipboard
| Challenge: | Open Domain Question Answering (ODQA) is a longstanding task in Natural Language Processing that involves generating an answer solely based on a given question. |
| Approach: | They propose a novel approach that executes sentence selection on the encoded passages to enhance the inference speed while reducing the context length required for generating answers. |
| Outcome: | The proposed approach can increase inference speed by **2.3X-5.7X** while maintaining the model’s performance. |
A Bounding Box is Worth One Token - Interleaving Layout and Text in a Large Language Model for Document Understanding (2025.findings-acl)
Copied to clipboard
Jinghui Lu, Haiyang Yu, Yanjie Wang, Yongjie Ye, Jingqun Tang, Ziwei Yang, Binghong Wu, Qi Liu, Hao Feng, Han Wang, Hao Liu, Can Huang
| Challenge: | Existing methods for integrating spatial layouts with text have limitations . existing methods produce overly long text sequences or lack autoregressive traits of LLMs . |
| Approach: | They introduce Interleaving Layout and Text in a Large Language Model (LayTextLLM) they use OCR-derived text and spatial layouts to integrate with LLMs for document understanding . |
| Outcome: | The proposed model shows an increase in performance in KIE and VQA tasks. |
Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)
Copied to clipboard
Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li
| Challenge: | Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization . |
| Approach: | They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume. |
| Outcome: | Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency. |
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding (2024.emnlp-main)
Copied to clipboard
Weilin Zhao, Yuxiang Huang, Xu Han, Wang Xu, Chaojun Xiao, Xinrong Zhang, Yewei Fang, Kaihuo Zhang, Zhiyuan Liu, Maosong Sun
| Challenge: | Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) drafting efficiency has become a bottleneck in the final speedup of speculative drafting, therefore generating longer drafts at less cost can lead to better speedup. |
| Approach: | They propose a method that uses existing model to drafting and target LLM to verify draft in a low-cost parallel manner. |
| Outcome: | The proposed method can achieve speedups of up to 2.4 over speculative decoding and 3.9 over vanilla decoding without fine-tuning draft and target models. |
WildDoc: How Far Are We from Achieving Comprehensive and Robust Document Understanding in the Wild? (2025.emnlp-main)
Copied to clipboard
An-Lan Wang, Jingqun Tang, Lei Liao, Hao Feng, Qi Liu, Xiang Fei, Jinghui Lu, Han Wang, Hao Liu, Yuliang Liu, Xiang Bai, Can Huang
| Challenge: | Existing benchmarks for document understanding in the wild are based on scanned or digital documents . however, these benchmarks fail to capture the challenges posed by documents in the real world . |
| Approach: | They propose a new benchmark that incorporates a diverse set of manually captured document images reflecting real-world conditions. |
| Outcome: | The proposed model is based on a set of manually captured document images reflecting real-world conditions and is compared with digital or scanned documents. |
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training (2025.findings-acl)
Copied to clipboard
Zhijun Wang, Jiahuan Li, Hao Zhou, Rongxiang Weng, Jingang Wang, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Shujian Huang
| Challenge: | Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data. |
| Approach: | They investigate the existence of code-switching in the pre-training corpus and categorize it into four types within two quadrants. |
| Outcome: | The proposed approach improves performance across benchmarks and representation space. |
Knowledge-driven Augmentation and Retrieval for Integrative Temporal Adaptation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies either overlook temporal shifts or hardly capture rich shifting patterns of both semantic and knowledge. |
| Approach: | They develop a temporal adaptive learning framework that captures temporal shifts . they use medical ontology and other knowledge sources to integrate temporal adaptation . |
| Outcome: | The proposed framework improves classification tasks across multiple domains and domains with knowledge integration. |
Model-Agnostic Meta Learning for Class Imbalance Adaptation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to address class imbalance and data difficulty have been used to train models. |
| Approach: | They propose a framework that prioritizes challenging samples and minority classes over hard examples and their semantically similar neighbors to address class imbalance. |
| Outcome: | The proposed framework outperforms baselines on six imbalanced datasets and achieves substantial improvements for minority classes. |
MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation methods focus on fluency and factual reliability, while neglecting figurative quality. |
| Approach: | They propose a set of human evaluation metrics focused on the translation of figurative language and a parallel metaphor corpus generated by post-editing. |
| Outcome: | The proposed evaluation protocol estimates four aspects of MT: Metaphorical Equivalence, Emotion, Authenticity, and Quality. |
Speculating LLMs’ Chinese Training Data Pollution from Their Tokens (2025.emnlp-main)
Copied to clipboard
Qingjie Zhang, Di Wang, Haoting Qian, Liu Yan, Tianwei Zhang, Ke Xu, Qi Li, Minlie Huang, Hewu Li, Han Qiu
| Challenge: | Experiments on GPT and other 23 LLMs indicate that tokens widely exist while GPT’s vocabulary behaves the worst: more than 23% long Chinese tokens (i.e., a token with more than two Chinese characters) are either porn or online gambling. |
| Approach: | They propose to locate Polluted Chinese (PoC) tokens in LLMs and build a PoC token detector to label them in vocabularies by considering each token’s semantics and related contents from the search engines. |
| Outcome: | The proposed method predicts that the ratio of “*” related webpages in GPT-4o's training data is around 0.5%. |
Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings (2025.findings-acl)
Copied to clipboard
Shujian Yang, Shiyao Cui, Chuanrui Hu, Haicheng Wang, Tianwei Zhang, Minlie Huang, Jialiang Lu, Han Qiu
| Challenge: | Recent studies show that character substitutions in toxic Chinese text can confuse state-of-the-art LLMs. |
| Approach: | They propose a taxonomy of 3 perturbation strategies and 8 specific approaches in Chinese text to assess if they can detect perturbed Chinese toxic contents. |
| Outcome: | The proposed model can detect perturbed Chinese text with 8 different approaches . the proposed model is compared with 9 other LLMs from the US and China . |
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking (2025.acl-long)
Copied to clipboard
Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun
| Challenge: | Existing studies in retrieval-augmented generation (RAG) do not sufficiently address the design of complex engineering solutions. |
| Approach: | They propose a retrieval-augmented generation system that leverages tree-based exploration and bi-point thinking mechanism to generate reliable solutions. |
| Outcome: | Experiments show that the proposed system achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications. |
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Reward (2025.findings-emnlp)
Copied to clipboard
Han Weng, Puzhen Wu, Cui Longjie, Yi Zhan, Boyi Liu, Yuanfeng Song, Dun Zeng, Yingxiang Yang, Qianru Zhang, Dong Huang, Xiaoming Yin, Yang Sun, Xing Chen
| Challenge: | Existing methods to enhance performance of large language models (LLMs) on Text-to-SQL tasks rely on execution-based or LLM-based reward models. |
| Approach: | They propose a reward model framework for RL-based Text-to-SQL that employs the GMNScore outcome reward model. |
| Outcome: | The proposed reward model outperforms existing reward models on standard benchmarks including Spider and BIRD. |
MEIC-DT: Memory-Efficient Incremental Clustering for Long-Text Coreference Resolution with Dual-Threshold Constraints (2026.findings-acl)
Copied to clipboard
Kangyang Luo, Shuzheng Si, Yuzhuo Bai, Cheng Gao, Zhitong Wang, Cheng Huang, Yingli Shen, Yufeng Han, Wenhao Li, Cunliang Kong, Maosong Sun
| Challenge: | Existing supervised neural methods are underexplored for coreference resolution, especially in incremental clustering. |
| Approach: | They propose a dual-threshold incremental clustering approach based on a lightweight Transformer. |
| Outcome: | Experiments on common benchmarks show that MEIC-DT achieves highly competitive coreference performance under stringent memory constraints. |
Leveraging Bidding Graphs for Advertiser-Aware Relevance Modeling in Sponsored Search (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing relevance models rely on query-keyword pairs but keywords are usually short texts with scarce semantic information, which may not accurately reflect the underlying advertising purposes. |
| Approach: | They propose a bidding-graph augmented triple-based relevance model with three towers to deeply fuse the bidding graphs and semantic textual data. |
| Outcome: | The proposed model outperforms existing models on a large industry dataset and consistently outperformed existing models. |
BCL: Bayesian In-Context Learning Framework for Information Extraction (2026.findings-acl)
Copied to clipboard
Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu, Shizhou Huang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Zhang Huaping, Lei Li
| Challenge: | Existing information extraction (IE) tasks rely on in-context learning with large language models. |
| Approach: | They propose a Bayesian-based in-context learning framework that refines label representations across IE tasks using particle filtering and Bayes updates. |
| Outcome: | The proposed framework improves performance over existing methods (up to 30%) it underperforms one-shot prompting by a substantial margin on NER tasks and CodeIE fails on RE tasks with near-zero micro-F1. |
MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper (2025.emnlp-main)
Copied to clipboard
Runjia Zeng, Guangyan Sun, Qifan Wang, Tong Geng, Sohail Dianat, Xiaotian Han, Raghuveer Rao, Xueling Zhang, Cheng Han, Lifu Huang, Dongfang Liu
| Challenge: | Empirical evaluations show that Mixture of Expert Prompt Tuning outperforms state-of-the-art parameter efficient baselines on SuperGLUE. |
| Approach: | They propose a pretrain-then-fine-tune paradigm for manifold mapping using multiple prompt experts. |
| Outcome: | Empirical results show that the proposed approach outperforms state-of-the-art methods on SuperGLUE while reducing activated prompts by 79.25%. |
Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs (2026.findings-acl)
Copied to clipboard
Yue Huang, Haomin Zhuang, Jiayi Ye, Han Bao, Yanbo Wang, Hang Hua, Siyuan Wu, Pin-Yu Chen, Xiangliang Zhang
| Challenge: | prevailing taxonomies neglect robustness and honesty, yielding safer-on-paper but less useful systems. |
| Approach: | They propose a soft-gating pipeline where a guardian predicts a binary risk label plus a concise explanation and prepends this advice to the original query for re-inference. |
| Outcome: | The proposed model maintains safety while reducing over-refusal. |
EventPlus: A Temporal Event Understanding Pipeline (2021.naacl-demos)
Copied to clipboard
Mingyu Derek Ma, Jiao Sun, Mu Yang, Kung-Hsiang Huang, Nuan Wen, Shikhar Singh, Rujun Han, Nanyun Peng
| Challenge: | Event information is a type of common sense knowledge that helps people understand how stories evolve and provides predictive hints for future events. |
| Approach: | They propose a temporal event understanding pipeline that integrates state-of-the-art components. |
| Outcome: | The proposed pipeline can be easily adapted to other domains, including biomedical domains. |
PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)
Copied to clipboard
Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang
| Challenge: | Current outcome-centric verification paradigms neglect potential errors in the derivation process. |
| Approach: | They propose a process-aware RLVR training paradigm utilizing verifiers selected via **PRIME**. |
| Outcome: | The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models. |
M2PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning (2024.emnlp-main)
Copied to clipboard
Taowen Wang, Yiyang Liu, James Liang, Junhan Zhao, Yiming Cui, Yuning Mao, Shaoliang Nie, Jiahao Liu, Fuli Feng, Zenglin Xu, Cheng Han, Lifu Huang, Qifan Wang, Dongfang Liu
| Challenge: | Multimodal Large Language Models (MLLMs) exhibit remarkable performance across a wide range of domains. |
| Approach: | They propose a multimodal prompt tuning approach for efficient instruction tuning of MLLMs. |
| Outcome: | The proposed approach shows superior performance on multimodal evaluation datasets compared to state-of-the-art methods. |
PPT: Pre-trained Prompt Tuning for Few-shot Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Prompt tuning for pre-trained language models has shown remarkable performance . however, prompt tuning is still not fully explored . |
| Approach: | They propose to pre-train prompts by adding soft prompts into the pre-training stage to obtain a better initialization. |
| Outcome: | The proposed framework outperforms full-model tuning under full-data and few-shot learning settings. |
RobustQA: Benchmarking the Robustness of Domain Adaptation for Open-Domain Question Answering (2023.findings-acl)
Copied to clipboard
Rujun Han, Peng Qi, Yuhao Zhang, Lan Liu, Juliette Burger, William Yang Wang, Zhiheng Huang, Bing Xiang, Dan Roth
| Challenge: | Existing ODQA datasets consist mainly of Wikipedia corpus, and are insufficient to study models’ generalizability across diverse domains. |
| Approach: | They propose a benchmark to evaluate ODQA's domain robustness using Wikipedia corpus . they annotate QA pairs in retrieval datasets with rigorous quality control . |
| Outcome: | The proposed benchmark improves model performance on annotated QA pairs in retrieval datasets with rigorous quality control. |
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention (2026.acl-long)
Copied to clipboard
Yuxiang Huang, Mingye Li, Xu Han, Chaojun Xiao, Weilin Zhao, Ao Sun, Ziqi Yuan, Hao Zhou, Fandong Meng, Zhiyuan Liu
| Challenge: | Existing methods for long-video inference use compression or sparse attention . existing methods restrict LMMs from handling longer, more complex videos . |
| Approach: | They propose a sequence-parallel framework with optimized attention that accelerates long-video inference across multiple GPUs. |
| Outcome: | The proposed framework delivers speedups of 12.72x, 1.70x, and 1.18x over FlashAttn, ZigZagRing, and APB without significant performance loss. |
AMEX: Android Multi-annotation Expo Dataset for Mobile GUI Agents (2025.findings-acl)
Copied to clipboard
Yuxiang Chai, Siyuan Huang, Yazhe Niu, Han Xiao, Liang Liu, Guozhi Wang, Dingyu Zhang, Shuai Ren, Hongsheng Li
| Challenge: | a new dataset is being developed to improve the capabilities of mobile GUI-control agents. |
| Approach: | They propose a dataset designed for generalist mobile GUI-control agents . they use screenshots from popular mobile applications to create a detailed GUI-annotated dataset . |
| Outcome: | The Android Multi-annotation EXpo (AMEX) is a large-scale dataset for generalist mobile GUI-control agents . it includes screenshots from popular mobile applications, which are annotated at multiple levels . |
Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering (2020.coling-main)
Copied to clipboard
| Challenge: | Existing text VQA systems generate an answer by selecting from optical character recognition (OCR) texts or a fixed vocabulary. |
| Approach: | They propose a localization-aware answer prediction network that generates the answer and predicts a bounding box as evidence of the generated answer. |
| Outcome: | The proposed network outperforms existing methods on three benchmark datasets for the text VQA task by a noticeable margin. |
Revisiting Entropy in Reinforcement Learning for Large Reasoning Models (2026.findings-acl)
Copied to clipboard
Renren Jin, Pengzhi Gao, Yuqi Ren, Zhuowen Han, Tongxuan Zhang, Wuwei Huang, Wei Liu, Jian Luan, Deyi Xiong
| Challenge: | Reinforcement learning with verifiable rewards (RLVR) has emerged as a paradigm for enhancing the reasoning capabilities of large language models. |
| Approach: | They propose a positive-advantage reweighting approach that regulates model entropy by adjusting the loss weights assigned to tokens with positive advantages during RLVR training. |
| Outcome: | The proposed approach regulates model entropy by adjusting loss weights assigned to tokens with positive advantages during RLVR training while maintaining competitive performance. |
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)
Copied to clipboard
Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu
| Challenge: | Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models. |
| Approach: | They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression. |
| Outcome: | Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution. |
Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining (2023.emnlp-main)
Copied to clipboard
Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei
| Challenge: | Recent studies have discussed its capability to assist language models for various applications. |
| Approach: | They propose a structure to organize arguments using the **Hi**erarchical **Ar**gumentation **G**raph (Hi-ArG) and propose two approaches to exploit Hi-AarG, including a text-graph multi-modal model GreaseArR and a framework augmented with graph information. |
| Outcome: | The proposed structure supersedes existing language models on two argumentation tasks while incorporating graph information during further training improves vanilla language models. |
Large Language Models Are Cross-Lingual Knowledge-Free Reasoners (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models have demonstrated impressive reasoning capabilities across multiple languages, but the relationship between capabilities in different languages is less explored. |
| Approach: | They decompose the process of reasoning tasks into two separate components: knowledge retrieval and knowledge-free reasoning. |
| Outcome: | The proposed model can be transferred across source-target languages despite secondary impact of resource in some specific target languages, while cross-lingual knowledge retrieval significantly hinders the transfer. |
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)
Copied to clipboard
Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang
| Challenge: | Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks. |
| Approach: | They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task. |
| Outcome: | The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines. |
A3: Android Agent Arena for Mobile GUI Agents with Essential-State Procedural Evaluation (2026.findings-acl)
Copied to clipboard
Yuxiang Chai, Shunye Tang, Han Xiao, Weifeng Lin, Hanhao Li, Jiayu Zhang, Liang Liu, Pengxiang Zhao, Guangyi Liu, Guozhi Wang, Shuai Ren, Rongduo Han, Haining Zhang, Siyuan Huang, Hongsheng Li
| Challenge: | Existing evaluation methods for mobile GUI agents rely on static frame assessments or offline static apps. |
| Approach: | They propose an evaluation system that leverages large language models as reward models to verify task completion and process achievement. |
| Outcome: | The proposed system addresses the limitations of traditional function based evaluation methods on online dynamic apps. |
LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs (2025.acl-long)
Copied to clipboard
Kaibo Liu, Zhenpeng Chen, Yiyang Liu, Jie M. Zhang, Mark Harman, Yudong Han, Yun Ma, Yihong Dong, Ge Li, Gang Huang
| Challenge: | TrickCatcher generates test cases that pass existing tests yet contain bugs . a recent study found that tricky bugs are not detected by test suites . |
| Approach: | They propose an LLM-powered approach to generating test cases for uncovering bugs in plausible programs . they use a PUT and specification to generate program variants, an input generator and an Llm to construct test inputs . |
| Outcome: | The proposed approach achieves recall, precision, and F1 scores that are 1.80, 2.65, and 1.66 . trickCatcher generates program variants based on the program under test and its specification . |
GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)
Copied to clipboard
Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun
| Challenge: | Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically. |
| Approach: | They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance. |
| Outcome: | The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs. |
Understanding the Dark Side of LLMs’ Intrinsic Self-Correction (2025.acl-long)
Copied to clipboard
Qingjie Zhang, Di Wang, Haoting Qian, Yiming Li, Tianwei Zhang, Minlie Huang, Ke Xu, Hewu Li, Liu Yan, Han Qiu
| Challenge: | Recent studies show that LLMs’ intrinsic self-correction fails without oracle labels as feedback. |
| Approach: | They propose to use one simple task and three complex tasks with state-of-the-art LLMs like ChatGPT, Llama, and DeepSeek to interpret LLM's intrinsic self-correction. |
| Outcome: | The proposed methods reveal the dark side of LLMs’ intrinsic self-correction for different tasks, especially for those failure cases. |
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine (2026.findings-acl)
Copied to clipboard
Jiatan Huang, Mingchen Li, Zonghai Yao, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong yu
| Challenge: | Existing methods for retrieving medical textual knowledge Graphs struggle to perform well, a study finds . existing methods struggle to provide accurate answers to complex questions, he says . |
| Approach: | They synthesize user queries integrating diverse topological structures, relational information, and complex textual descriptions. |
| Outcome: | a new dataset for medical textual knowledge graphs shows that existing methods struggle to perform well . main bottlenecks lie in the scarcity of existing medical TKGs and the limited expressiveness of their topological structures . |
DIAG-NRE: A Neural Pattern Diagnosis Framework for Distantly Supervised Neural Relation Extraction (P19-1)
Copied to clipboard
| Challenge: | Existing methods for labeling relational facts require significant expert labor to write relation-specific patterns, which makes them too sophisticated to generalize quickly. |
| Approach: | They propose a neural pattern diagnosis framework that can summarize and refine relation-specific patterns with human experts in the loop. |
| Outcome: | The proposed framework can summarize and refine high-quality relational patterns from noise data with human experts in the loop. |
Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)
Copied to clipboard
Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni
| Challenge: | MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture. |
| Approach: | They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content. |
| Outcome: | The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context. |
Length-Aware Multi-Kernel Transformer for Long Document Classification (2024.starsem-1)
Copied to clipboard
| Challenge: | Existing SOTA models segment long texts into equal-length snippets, but they have new challenges of context fragmentation and generalizability due to sentence boundaries and varying text lengths. |
| Approach: | They propose a Length-Aware Multi-Kernel Transformer to encode long documents by transformers and vectorize text length by the kernels to promote model robustness over varying document lengths. |
| Outcome: | The proposed model outperforms existing models on five benchmarks from health and law domains up to an absolute 10.9% improvement. |
OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems (2024.acl-long)
Copied to clipboard
Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, Maosong Sun
| Challenge: | Large Language Models (LLMs) and Large Multimodal Models have exceeded general human capabilities in various tasks. |
| Approach: | They present an Olympiad-level bilingual multimodal scientific benchmark featuring 8,476 problems from Olympiad level mathematics and physics competitions. |
| Outcome: | The best performing model, GPT-4V, attains an average score of 17.97% on OlympiadBench, with a mere 10.74% in physics, highlighting the benchmark rigor and the intricacy of physical reasoning. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
LawBench: Benchmarking Legal Knowledge of Large Language Models (2024.emnlp-main)
Copied to clipboard
Zhiwei Fei, Xiaoyu Shen, Dawei Zhu, Fengzhe Zhou, Zhuo Han, Alan Huang, Songyang Zhang, Kai Chen, Zhixin Yin, Zongwen Shen, Jidong Ge, Vincent Ng
| Challenge: | LegalBench evaluated 20 LLMs in 162 legal tasks in 20 countries and jurisdictions. |
| Approach: | They present a comprehensive evaluation of 21 popular Large Language Models and the first comparative analysis of the empirical results. |
| Outcome: | The proposed benchmarks are based on the Bloom’s cognitive taxonomy and are compared to 21 popular LLMs. |
Syntax-Aware Retrieval Augmentation for Neural Symbolic Regression (2025.emnlp-main)
Copied to clipboard
| Challenge: | Symbolic regression is a powerful technique for discovering mathematical expressions that best fit observed data. |
| Approach: | They propose a syntax-aware retrieval-augmented mechanism that leverages syntactic structure of symbolic expressions to perform context-awful retrieval from a pre-constructed token datastore. |
| Outcome: | The proposed method outperforms representative baselines on symbolic regression benchmarks and is validated on multiple symbolic regression datasets. |
PolicyLLM: Towards Excellent Comprehension of Public Policy for Large Language Models (2026.findings-acl)
Copied to clipboard
Han Bao, Penghao Zhang, Yue Huang, Zhengqing Yuan, Yanchi Ru, SU Rui, Yujun Zhou, Xiangqi Wang, Kehan Guo, Nitesh V Chawla, Yanfang Ye, Xiangliang Zhang
| Challenge: | Large Language Models (LLMs) are increasingly integrated into real-world decision-making, but their ability to comprehend and reason about policy-related content remains underexplored. |
| Approach: | They propose a bilingual benchmark evaluating policy comprehension comprising 21K cases across a broad spectrum of policy areas. |
| Outcome: | The proposed model shows stronger performance on application-oriented policy tasks than on memorization or conceptual understanding, and yields the highest accuracy on structured reasoning tasks. |
Multi-Value-Product Retrieval-Augmented Generation for Industrial Product Attribute Value Identification (2025.emnlp-industry)
Copied to clipboard
Huike Zou, Haiyang Yang, Yindu Su, Chen Li Yu, Qinye Xie, Chengbao Lian, Qingheng Zhang, Shuguang Han, Fei Huang, Jufeng Chen
| Challenge: | Existing methods for product attribute value identification suffer from cascading errors and lack of generalization capability. |
| Approach: | They propose a multi-level retrieval scheme that uses products and attribute values as distinct hierarchical levels in PAVI domain. |
| Outcome: | The proposed method performs better than the state-of-the-art methods on a real-world industrial dataset. |
HealMe: Harnessing Cognitive Reframing in Large Language Models for Psychotherapy (2024.acl-long)
Copied to clipboard
Mengxi Xiao, Qianqian Xie, Ziyan Kuang, Zhicheng Liu, Kailai Yang, Min Peng, Weiguang Han, Jimin Huang
| Challenge: | Large Language Models (LLMs) can be used in psychotherapy to overcome challenges such as shame, distrust, and resource scarcity. |
| Approach: | They propose a cognitive reframing therapy method that uses empathetic dialogue to address deep-rooted negative thoughts and fosters rational, balanced perspectives. |
| Outcome: | The proposed model outperforms other models in terms of empathy, guidance, and logical coherence, demonstrating its effectiveness and potential positive impact on psychotherapy. |
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoning (2025.findings-emnlp)
Copied to clipboard
Xiaotian Han, Yiren Jian, Xuefeng Hu, Haogeng Liu, Yiqi Wang, Qihang Fan, Yuang Ai, Huaibo Huang, Ran He, Zhenheng Yang, Quanzeng You
| Challenge: | InfiMM-WebMath-40B is a dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens . |
| Approach: | InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it contains 24 million web pages, 85 million image URLs, and 40 billion text tokens . |
| Outcome: | InfiMM-WebMath-40B is a high-quality dataset of interleaved image-text documents . it consists of 24 million web pages, 85 million image URLs, and 40 billion text tokens . |
MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)
Copied to clipboard
Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query. |
| Approach: | They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis. |
| Outcome: | The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO. |
PEGRL: Improving Machine Translation by Post-Editing Guided Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) has shown strong promise for LLM-based machine translation . however, translation-oriented RL remains challenged by high-variance policy gradients induced by Monte Carlo baselines and large trajectory space that favors global exploration over fine-grained local optimization. |
| Approach: | They propose a two-stage RL framework that uses post-editing as an auxiliary task to stabilize training and guide overall optimization. |
| Outcome: | The proposed framework supports global exploration and fine-grained optimization while supporting global exploration. |
Attributes as Textual Genes: Leveraging LLMs as Genetic Algorithm Simulators for Conditional Synthetic Data Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Genetic Prompt combines genetic algorithms with Large Language Models to augment synthetic data generation. |
| Approach: | They propose a framework that combines genetic algorithms with LLMs to augment synthetic data generation. |
| Outcome: | The proposed framework outperforms state-of-the-art models and shows robust performance across generator models. |
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability. |
| Approach: | They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses. |
| Outcome: | The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences. |
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026.acl-long)
Copied to clipboard
Zhen Fang, Ruiyan Han, XinYu Sun, Yuchen Ma, Ziheng Wang, Yu Zeng, Zehui Chen, Lin Chen, Wenxuan Huang, Wei-Jie Xu, Yi Cao, Feng Zhao
| Challenge: | Unified Multimodal Models have achieved remarkable success in cross-modal comprehension, but a gap persists in their ability to translate internal knowledge into faithful and controllable synthesis. |
| Approach: | They propose a self-improvement framework that partitions a single UMM into three collaborative roles: Proposer, Solver, and Judge. |
| Outcome: | The proposed framework improves on TIIF, DPG, CompBench and UniCycle benchmarks. |
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction (2022.emnlp-main)
Copied to clipboard
Zhoujin Tian, Chaozhuo Li, Shuo Ren, Zhiqiang Zuo, Zengxuan Wen, Xinyue Hu, Xiao Han, Haizhen Huang, Denvy Deng, Qi Zhang, Xing Xie
| Challenge: | Existing approaches focus on minimizing distances between words in aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. |
| Approach: | They propose a ranking-oriented induction model to learn personalized mapping function for each word. |
| Outcome: | The proposed model can learn personalized mapping function for each word on public datasets including rich-resource and low-resourced languages. |
Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study (2025.findings-emnlp)
Copied to clipboard
Yujun Zhou, Jiayi Ye, Zipeng Ling, Yufei Han, Yue Huang, Haomin Zhuang, Zhenwen Liang, Kehan Guo, Taicheng Guo, Xiangqi Wang, Xiangliang Zhang
| Challenge: | Existing benchmarks that rely on final-answer accuracy fail to capture the quality of the reasoning process. |
| Approach: | They propose a fine-grained evaluation framework that assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing. |
| Outcome: | The proposed framework assesses logical reasoning across three dimensions: overall accuracy, stepwise soundness, and representation-level probing. |
RoCoIns: Enhancing Robustness of Large Language Models through Code-Style Instructions (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in following human instructions and solving NLU tasks. |
| Approach: | They propose to use code style instructions to replace typically natural language instructions to provide more precise instructions and strengthen the robustness of LLMs. |
| Outcome: | The proposed method outperforms natural language models on eight robustness datasets and achieves an improvement of 5.68% in test set accuracy and a reduction of 5.66 points in Attack Success Rate (ASR). |
IPL: Leveraging Multimodal Large Language Models for Intelligent Product Listing (2024.emnlp-industry)
Copied to clipboard
Kang Chen, Qing Zhang, Chengbao Lian, Yixin Ji, Xuwei Liu, Shuguang Han, Guoqiang Wu, Fei Huang, Jufeng Chen
| Challenge: | Unlike professional Business-to-Consumer (B2C) e-commerce platforms, consumer-to consumer (C2C), is mainly targeting individual sellers. |
| Approach: | They develop an intelligent product listing tool that generates product descriptions using various product attributes such as category, brand, color, condition, etc. |
| Outcome: | The proposed tool outperforms the base model in domain-specific tasks while producing less hallucination. |
Biomedical Event Extraction based on Knowledge-driven Tree-LSTM (N19-1)
Copied to clipboard
| Challenge: | Biomedical event extraction requires domain-specific knowledge and deep understanding of complex contexts. |
| Approach: | They propose a knowledge base-driven tree-structured long short-term memory networks framework . tree-LSTM framework incorporates dependency structures and entity properties from ontologies . |
| Outcome: | The proposed framework is based on the BioNLP shared task with Genia dataset and achieves state-of-the-art results. |
Large Language Models Can Self-Improve (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have excellent performance in various tasks, but fine-tuning requires extensive supervision. |
| Approach: | They propose to use a pre-trained Large Language Model to generate rationale-augmented answers for unlabeled questions and fine-tune the LLM using those self-generated solutions as target outputs. |
| Outcome: | The proposed approach improves the general reasoning ability of a 540B-parameter LLM without any ground truth label. |
Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on short dialogues, but mainly on short debates. |
| Approach: | They propose to use Large Language Models to construct an automated debate judge to evaluate multi-turn debates. |
| Outcome: | The proposed system improves on the PanelBench benchmark, which compares its performance to actual debate outcomes. |
New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs (2026.acl-long)
Copied to clipboard
Shiyao Cui, QingLin Zhang, Di Wang, Yida Lu, Zhexin Zhang, Jinhua Gao, Jinglin Yang, Min He, Han Qiu, Minlie Huang
| Challenge: | Neologisms can foster new linguistic consensus by stabilizing shared meanings and usage in common communicative norms. |
| Approach: | They propose a taxonomy that captures the origins and consensus-verification criteria of toxic neologisms . they propose 'SeTox' framework that integrates real-time web context for naeologim detection . |
| Outcome: | The proposed framework outperforms large-scale models in detecting neologism toxicity. |
Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From (2025.emnlp-main)
Copied to clipboard
| Challenge: | Cross-lingual context retrieval is a fundamental aspect of cross-lingual alignment, but the performance and mechanism of it for large language models (LLMs) remains unclear. |
| Approach: | They evaluate cross-lingual context retrieval of over 40 large language models . they use cross-linguistic machine reading comprehension as a representative scenario . |
| Outcome: | The results show that open LLMs show strong cross-lingual context retrieval ability . the results also show that their oracle performances improve after training . |
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models (2024.emnlp-main)
Copied to clipboard
Zhengxuan Wu, Yuhao Zhang, Peng Qi, Yumo Xu, Rujun Han, Yian Zhang, Jifan Chen, Bonan Min, Zhiheng Huang
| Challenge: | Modern language models fail to follow human instructions while being faithful . a trade-off exists between instruction following and faithfulness when training LMs . |
| Approach: | They propose a method that relies on Reject-sampling by Self-instruct with Continued Fine-tuning to train LMs to follow human instructions while being faithful. |
| Outcome: | The proposed method outperforms vanilla MTL with high-quality data, but with significantly smaller data. |
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models (2026.acl-long)
Copied to clipboard
Xin Cheng, Wangding Zeng, Damai Dai, Qinyu Chen, Bingxuan Wang, Zhenda Xie, Kezhao Huang, Xingkai Yu, Zhewen Hao, Han Zhang, Yu-Kun Li, Huishuai Zhang, Dongyan Zhao, Wenfeng Liang
| Challenge: | Mixture-of-Experts (MoE) scales capacity via conditional computation, but lacks knowledge lookup primitive. |
| Approach: | They propose a conditional memory instantiated via Deep Sparse Embedding (DSE) they propose 'u-shaped scaling law' that identifies optimal balance between MoE experts and DSE memory . |
| Outcome: | The proposed model outperforms an iso-parameter and isoFLOPs MoE baseline across knowledge and reasoning benchmarks and is infrastructure-efficient. |
Self-Adjust Softmax (2025.emnlp-main)
Copied to clipboard
Chuanyang Zheng, Yihang Gao, Guoxuan Chen, Han Shi, Jing Xiong, Xiaozhe Ren, Chao Huang, Zhenguo Li, Yu Li
| Challenge: | Usually, tokens with larger attention scores are important for the final prediction. |
| Approach: | They propose to modify softmax(z) to z softmax and its normalized variant to improve the Transformer attention mechanism by making minor adjustments to the softmax function. |
| Outcome: | The proposed model provides enhanced gradient properties compared to the vanilla softmax function. |
JADE: Corpus for Japanese Definition Modelling (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing corpus for definition modelling techniques is limited to English . this study aimed to develop a corpus that provides definitions of words and phrases . |
| Approach: | They investigated and released a corpus for Japanese definition modelling . the JADE provides 630k sets of targets, their definitions, and usage examples as contexts . |
| Outcome: | The JADE corpus provides 630k sets of targets, their definitions, and usage examples as contexts for 41k unique targets. |
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for instruction-tuning data contain redundancy and low-quality samples. |
| Approach: | They propose an instruction data selection framework based on weighted in-context influence . they show that sample difficulty negatively correlates with in-constext influence. |
| Outcome: | The proposed method outperforms baselines under constrained data budgets while demonstrating that sample difficulty negatively correlates with in-context influence. |
PruneVid: Visual Token Pruning for Efficient Video Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to video token pruning face significant computational challenges due to the redundancy inherent in video data. |
| Approach: | They propose a training-free visual token pruning method that reduces the redundancy inherent in video data and leverages LLMs’ inherent ability to selectively prune visual tokens irrelevant to specific queries. |
| Outcome: | The proposed method can prune over 80% of tokens while maintaining competitive performance when combined with different video LLMs. |
InterIDEAS: Philosophical Intertextuality via LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | a new dataset aims to bridge philosophy, literary studies, and natural language processing (NLP) by integrating theories of intertextuality with bibliometric techniques. |
| Approach: | They propose a dataset that bridges philosophy, literary studies, and natural language processing (NLP) it combines theories of intertextuality from literary studies with bibliometric techniques and recent LLMs . |
| Outcome: | a new dataset bridges philosophy, literary studies, and natural language processing (NLP) to analyze intertextuality . the proposed method helps scholars understand the intellectual, social, and historical relations embedded in texts . it also contributes to the development of language models, authors say . |
CmEAA: Cross-modal Enhancement and Alignment Adapter for Radiology Report Generation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for automatic radiology report generation suffer from data bias. |
| Approach: | They propose a method that connects a vision encoder with a frozen large language model by using a cross-modal enhancement and alignment adapter. |
| Outcome: | The proposed model outperforms existing state-of-the-art methods on IU X-Ray and MIMIC-CXR datasets. |
FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation (2025.acl-long)
Copied to clipboard
Junyu Luo, Zhizhuo Kou, Liming Yang, Xiao Luo, Jinsheng Huang, Zhiping Xiao, Jingshu Peng, Chengzhong Liu, Jiaming Ji, Xuanzhe Liu, Sirui Han, Ming Zhang, Yike Guo
| Challenge: | Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years, but there is a notable lack of effective and specialized multimodal evaluation datasets in the financial domain. |
| Approach: | They introduce FinMME, a multimodal large language model with 11,000 financial research samples and 20 annotators. |
| Outcome: | The proposed model performs better than state-of-the-art models, highlighting its challenging nature. |
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting (2025.findings-acl)
Copied to clipboard
Hao Feng, Shu Wei, Xiang Fei, Wei Shi, Yingdong Han, Lei Liao, Jinghui Lu, Binghong Wu, Qi Liu, Chunhui Lin, Jingqun Tang, Hao Liu, Can Huang
| Challenge: | Current document image parsing solutions rely on specialized models or generate content autoregressively. |
| Approach: | They propose a multimodal document image parsing model that integrates specialized models with autogeneous content generation. |
| Outcome: | The proposed model achieves state-of-the-art performance across diverse page-level and element-level settings while ensuring superior efficiency. |
LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)
Copied to clipboard
Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang
| Challenge: | Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs. |
| Approach: | They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal . |
| Outcome: | The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts. |
Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training (2021.emnlp-main)
Copied to clipboard
| Challenge: | Named entity recognition models require abundant high-quality annotations to train . distant supervision may induce incomplete and noisy labels, making supervised learning ineffective. |
| Approach: | They propose a noise-robust learning scheme for training named entity recognition models using only distantly-labeled data and a self-training method that uses contextualized augmentations created by pre-trained language models. |
| Outcome: | The proposed method outperforms existing supervised NER models on three datasets by significant margins. |
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation (2025.acl-long)
Copied to clipboard
Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li
| Challenge: | Extensive experiments demonstrate that treating attention as a feature map and applying convolution as . a processing method significantly enhances Transformer performance. |
| Approach: | They propose to use the convolution operator to mimic the processing methods in computer vision to treat attention as a feature map and apply it to neighboring attention scores across different heads. |
| Outcome: | The proposed model can be adapted to various attention-related models and achieves high performance. |
FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information (2022.emnlp-main)
Copied to clipboard
| Challenge: | FormLM is a pre-trained language model for creating semi-structured forms where questions and descriptions are organized by predefined structures. |
| Approach: | They propose to enhance pre-trained language model with form structural information to model online forms and recommend form creation ideas. |
| Outcome: | The proposed model outperforms general-purpose language models on all tasks, with an improvement by 4.71 on Question Recommendation and 10.6 on Block Type Suggestion in terms of ROUGE-1 and Macro-F1, respectively. |
DocRED: A Large-Scale Document-Level Relation Extraction Dataset (P19-1)
Copied to clipboard
Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, Maosong Sun
| Challenge: | Existing relation extraction methods focus on extracting intra-sentence relations for single entities. |
| Approach: | They propose a relation extraction dataset from Wikipedia and Wikidata with three features . document-level relation extraction is a task to identify relational facts between entities . |
| Outcome: | The proposed dataset is the largest human-annotated dataset for document-level RE from plain text. |