Papers by Bing Zhu

An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation (2024.acl-long)

Challenge:	Existing approaches for synthetic QA data generation have limited or no success in improving the downstream Reading Comprehension task.
Approach:	They propose an end-to-end approach for synthetic QA data generation using a transformer-based encoder-decoder network that is trained end- to-end to generate both answers and questions.
Outcome:	The proposed model outperforms current state-of-the-art methods in the domain adaptation of QA models.

Copied to clipboard

Kun Zhu, Xiaocheng Feng, Xiyuan Du, Yuxuan Gu, Weijiang Yu, Haotian Wang, Qianglong Chen, Zheng Chu, Jingchang Chen, Bing Qin

Information Retrieval

Challenge:	Experimental results show that retrieval-augmented generation improves accuracy and relevance of large language models.
Approach:	They propose to introduce the information bottleneck theory into retrieval-augmented generation by maximizing mutual information between compression and ground output while minimizing mutual information .
Outcome:	The proposed approach improves accuracy and correctness of answer generation and conciseness with 2.5% compression rate.

Distilled Dual-Encoder Model for Vision-Language Understanding (2022.emnlp-main)

Copied to clipboard

Zekun Wang, Wenhui Wang, Haichao Zhu, Ming Liu, Bing Qin, Furu Wei

UniToolBench: A Benchmark for Tool-Augmented LLMs in Cross-Domain, Universal Task Automation (2026.findings-eacl)

Challenge:	Experimental results show that the proposed cross-modal attention distillation is crucial to the success of our framework.
Approach:	They propose a framework that distills knowledge of fusion-encoder teacher into dual-encoding student model.
Outcome:	The proposed model is competitive with the fusion-encoder teacher model in performance, but suffers from a lack of deep cross-modal interactions.

Copied to clipboard

Xiaojie Guo, Yang Zhang, Bing Zhang, Ryo Kawahara, Mikio Takeuchi, Yada Zhu

Structured Data in NLP

Challenge:	Existing benchmarks that focus on manually curated tool graphs lack scalability and diversity across domains.
Approach:	They propose a large-scale, cross-domain benchmark to evaluate LLMs' ability to reason over and utilize interconnected tools for automation.
Outcome:	The proposed benchmark incorporates automated tool graph construction by formulating link prediction as a probabilistic task, instead of relying on categorical LLM outputs.

A Chain-of-Task Framework for Instruction Tuning of LLMs Based on Chinese Grammatical Error Correction (2025.coling-main)

Copied to clipboard

Xinpeng Liu, Bing Xu, Muyun Yang, Hailong Cao, Conghui Zhu, Tiejun Zhao, Wenpeng Lu

Low-Resource NLP

Challenge:	Existing approaches to address Grammatical Error Correction (GEC) tasks are based on large scale labeled data, which leads to extremely high data annotation costs.
Approach:	They propose a Chain-of-Task framework to reduce over-correction in large language models . they propose supervised fine-tuning strategy and an algorithm for automatic dataset annotation .
Outcome:	The proposed framework achieves state-of-the-art on both FCGEC (in-domain) and NaCGEC (out-of domain) test sets.

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Copied to clipboard

Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach:	They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome:	The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.

Hierarchical Catalogue Generation for Literature Review: A Benchmark (2023.findings-emnlp)

Copied to clipboard

Kun Zhu, Xiaocheng Feng, Xiachong Feng, Yingsheng Wu, Bing Qin

Challenge:	Scientific literature review generation aims to extract and organize important information from an abundant collection of reference papers and produces corresponding reviews while lacking a clear and logical hierarchy.
Approach:	They propose a task to generate a hierarchical catalogue of a review paper given various references by using a database of 7.6k literature review catalogues and 389k reference papers.
Outcome:	The proposed method produces a hierarchical catalogue of a review paper given various references.

Knowledge-Selective Pretraining for Attribute Value Extraction (2023.findings-emnlp)

Copied to clipboard

Hui Liu, Qingyu Yin, Zhengyang Wang, Chenwei Zhang, Haoming Jiang, Yifan Gao, Zheng Li, Xian Li, Chao Zhang, Bing Yin, William Wang, Xiaodan Zhu

Learning to Ask Unanswerable Questions for Machine Reading Comprehension (P19-1)

Challenge:	Existing methods for AVE are limited on rare attributes due to poor generalization ability.
Approach:	They propose to leverage pretraining and transfer learning to address weaknesses in existing methods.
Outcome:	The proposed method achieves new state-of-the-art performance without pretraining on rare attributes with limited training resources.

Copied to clipboard

Haichao Zhu, Li Dong, Furu Wei, Wenhui Wang, Bing Qin, Ting Liu

Low-Resource NLP

Challenge:	Existing models for extractive reading comprehension are not good at deciding whether no answer is presented in the context.
Approach:	They propose a data augmentation technique by automatically generating relevant unanswerable questions according to an answerable question paired with its corresponding paragraph that contains the answer.
Outcome:	The proposed model performs better on the SQuAD 2.0 dataset than the baseline model and the BERT-large model.

Answering Ambiguous Questions through Generative Evidence Fusion and Round-Trip Prediction (2021.acl-long)

Copied to clipboard

Yifan Gao, Henghui Zhu, Patrick Ng, Cicero Nogueira dos Santos, Zhiguo Wang, Feng Nan, Dejiao Zhang, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Natural Language Interfaces

Challenge:	Open-domain question answering is a task to answer questions using passages with diverse topics.
Approach:	They propose a model that aggregates evidence from multiple passages to adaptively predict a single answer or a set of question-answer pairs for ambiguous questions.
Outcome:	The proposed model achieves state-of-the-art performance on AmbigQA dataset and shows competitive performance on NQ-Open and TriviaQA.

A Diffusion Model for Event Skeleton Generation (2023.findings-acl)

Copied to clipboard

Fangqi Zhu, Lin Zhang, Jun Gao, Bing Qin, Ruifeng Xu, Haiqin Yang

Structured Data in NLP

Challenge:	Existing methods for event schema generation are noise-sensitive and error-accumulating, e.g., inability to correct errors while generating schema.
Approach:	They propose a novel diffusion event graph model that embeds and roundes event graphs into learnable latent representations and a denoising process to maintain the model's robustness.
Outcome:	The proposed model achieves better results than existing state-of-the-art models on three IED bombing datasets.

Entity-level Factual Consistency of Abstractive Text Summarization (2021.eacl-main)

Copied to clipboard

Feng Nan, Ramesh Nallapati, Zhiguo Wang, Cicero Nogueira dos Santos, Henghui Zhu, Dejiao Zhang, Kathleen McKeown, Bing Xiang

Text Generation

Challenge:	Existing models exhibit entity hallucination, generating names of entities that are not present in the source document.
Approach:	They propose to use entity-level factual consistency to improve model quality . they propose to filter the training data to reduce entity hallucination problem .
Outcome:	The proposed model can reduce the entity hallucination problem by filtering the training data.

FinTextQA: A Dataset for Long-form Financial Question Answering (2024.acl-long)

Copied to clipboard

Jian Chen, Peilin Zhou, Yining Hua, Loh Xin, Kehui Chen, Ziyuan Li, Bing Zhu, Junwei Liang

Natural Language Interfaces

Challenge:	Existing financial question answering datasets lack scope diversity and question complexity.
Approach:	They propose to use a dataset for long-form question answering in finance to evaluate QA systems.
Outcome:	The proposed dataset includes 1,262 high-quality, source-attributed QA pairs extracted and selected from finance textbooks and government agency websites.

Learning to Describe for Predicting Zero-shot Drug-Drug Interactions (2023.emnlp-main)

Copied to clipboard

Fangqi Zhu, Yongqi Zhang, Lei Chen, Bing Qin, Ruifeng Xu

Evaluating Large Language Models with Enterprise Benchmarks (2025.naacl-industry)

Challenge:	Existing computational methods for DDI prediction fail to capture interactions for new drugs due to the lack of knowledge.
Approach:	They propose a problem setup as zero-shot DDI prediction that deals with the case of new drugs by using textual information from online databases.
Outcome:	The proposed method improves on several settings including zero-shot and few-shot DDI prediction and the selected texts are semantically relevant.

Copied to clipboard

Bing Zhang, Mikio Takeuchi, Ryo Kawahara, Shubhi Asthana, Maruf Hossain, Guang-Jie Ren, Kate Soule, Yifan Mai, Yada Zhu

Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering (2025.emnlp-main)

Challenge:	Existing benchmarks lack domain-specific datasets for evaluating large language models . existing benchmarks often lack domain specific datasets, which can be difficult to convert to standardized metrics or regulatory issues.
Approach:	They propose to use 25 publicly available domain-specific English benchmarks from diverse domains . they propose to combine a wide range of natural language processing tasks for holistic evaluation .
Outcome:	The proposed framework includes 25 publicly available domain-specific English benchmarks from diverse enterprise domains like financial services, legal, climate, cyber security, and 2 public Japanese finance benchmarks.

Copied to clipboard

Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Text Clustering

Challenge:	Existing taxonomy construction methods lack coherence and granularity . Existing approaches rely on manual or narrowly defined schemes .
Approach:	They propose a context-aware hierarchical taxonomy generation framework that integrates LLMs with dynamic clustering.
Outcome:	The proposed method outperforms existing methods in taxonomy coherence, granularity, and interpretability.

Benchmarking Diverse-Modal Entity Linking with Generative Models (2023.findings-acl)

Copied to clipboard

Sijia Wang, Alexander Hanbo Li, Henghui Zhu, Sheng Zhang, Pramuditha Perera, Chung-Wei Hang, Jie Ma, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Bing Xiang, Patrick Ng

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets (P19-1)

Challenge:	Existing models for diverse-mode entity linking (EL) work well on per modality configurations, but it is more challenging to design a unified model for diverse modality.
Approach:	They propose a generative diverse-modal model that integrates text, image and table . they propose combining a multimodal encoder-decoder paradigm with a fine-tuning GDMM .
Outcome:	The proposed model outperforms state-of-the-art models by 8.51 F1 on average for diverse-modal EL.

Copied to clipboard

Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao

Responsible & Trustworthy NLP

Challenge:	Natural Language Sentence Matching (NLSM) is a popular NLP task.
Approach:	They propose to use QuoraQP to train and evaluate NLSM models using a selection bias framework.
Outcome:	The proposed framework can improve generalization ability of trained models and give more trustworthy evaluation results for real-world adoptions.

Margin-aware Unsupervised Domain Adaptation for Cross-lingual Text Labeling (2020.findings-emnlp)

Copied to clipboard

Dejiao Zhang, Ramesh Nallapati, Henghui Zhu, Feng Nan, Cicero Nogueira dos Santos, Kathleen McKeown, Bing Xiang

Low-Resource NLP

Challenge:	Existing approaches to learn a model from labeled data are expensive or prohibitive.
Approach:	They propose an unsupervised domain adaptation algorithm that leverages labeled data in a source domain to learn a well-performing model in . they use the Margin Disparity Discrepancy algorithm to optimize the margin loss on the source domain.
Outcome:	The proposed approach improves on a recent theoretical work on cross-lingual document classification and NER by a large margin.

CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection (2022.findings-naacl)

Copied to clipboard

Zhen Li, Bing Xu, Conghui Zhu, Tiejun Zhao

MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training (2025.acl-long)

Challenge:	Existing methods for multimodal sentiment detection do not consider token-level feature fusion.
Approach:	They propose a method for multimodal sentiment detection using a combination of text and image to encode and fuse token-level features.
Outcome:	The proposed method can fuse multimodal features with token-level features on three publicly available multimodal datasets.

Copied to clipboard

Hui Huang, Jiaheng Liu, Yancheng He, Shilong Li, Bing Xu, Conghui Zhu, Muyun Yang, Tiejun Zhao

EMTIR-GRPO: Efficient Multi-Tool Augmented Large Language Models via Reinforcement Learning (2026.findings-acl)

Challenge:	Existing methods for complex instruction-following with elaborate constraints rely on a weaker model, especially GPT-4, limiting their application.
Approach:	They propose a Multi-granularity Self-Contrastive Training framework to improve instruction alignment without relying on a stronger model.
Outcome:	The proposed framework improves instruction-following with elaborate constraints without external supervision on coarse and fine granularity.

Copied to clipboard

Shixin Jiang, Zhihao Zhu, Jiafeng Liang, Yang Wu, Ming Liu, Bing Qin

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning (2026.eacl-long)

Challenge:	Tool-integrated reasoning (TIR) enables large language models to invoke external tools for tasks beyond their internal capacity but often suffers from tool overuse.
Approach:	They propose an algorithm that uses a composite reward to model tool costs and tool efficiency.
Outcome:	The proposed algorithm models heterogeneous tool costs and encourages more cost-effective tool-use strategies.

Copied to clipboard

Chuang Zhang, Zizhen Zhu, Yihao Wei, Bing Tian, Junyi Liu, Henan Wang, Wang Xavier, Yaxiao Liu

A Text-Centered Shared-Private Framework via Cross-Modal Prediction for Multimodal Sentiment Analysis (2021.findings-acl)

Challenge:	Large language models (LLMs) have superior reasoning capabilities compared to small language models, but incur substantially higher inference costs.
Approach:	They propose a system that cascades an LLM with an SLM to achieve a balance between accuracy and cost in complex reasoning tasks.
Outcome:	The proposed system improves the SLM’s reasoning ability and confidence calibration across diverse datasets and model backbones.

Copied to clipboard

Yang Wu, Zijie Lin, Yanyan Zhao, Bing Qin, Li-Nan Zhu

Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

Challenge:	Existing studies treat all three modal features equally and implicitly explore the interactions between different modalities.
Approach:	They propose a text-centered shared-private framework for multimodal fusion . they propose modalities that can provide shared and private semantics .
Outcome:	The proposed framework outperforms baselines on the MOSEI and MOSI datasets.

Copied to clipboard

Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Challenge:	Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach:	They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome:	The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering (2021.acl-long)

Copied to clipboard

Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models (2024.lrec-main)

Challenge:	Existing generative models for open-domain question answering focus on generating direct answers from unstructured textual information, but a large amount of knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.
Approach:	They propose a hybrid framework that takes both textual and tabular evidences as input and generates either direct answers or SQL queries depending on which form could better answer the question.
Outcome:	The proposed framework outperforms baseline models on OpenSQuAD datasets and can generate SQL queries on the associated databases to obtain the final answers.

Copied to clipboard

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

Length Controlled Generation for Black-box LLMs (2025.acl-long)

Challenge:	Experimental results show that SmartTrim accelerates the original model by 2-3 times with minimal performance degradation.
Approach:	They propose an adaptive acceleration framework which prunes redundant token representations and attention heads within each layer of the original model.
Outcome:	The proposed framework accelerates the original model by 2-3 times with minimal performance degradation across vision-language tasks.

Copied to clipboard

Yuxuan Gu, Wenjie Wang, Xiaocheng Feng, Weihong Zhong, Kun Zhu, Lei Huang, Ting Liu, Bing Qin, Tat-Seng Chua

Responsible & Trustworthy NLP

Challenge:	Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use.
Approach:	They propose an iterative sampling framework that regulates LLMs to generate length-constrained text without modifying the underlying parameters.
Outcome:	The proposed method achieves 100% success rates on Llama3.1 tasks with minimal additional computational overhead.

Supporting Clustering with Contrastive Learning (2021.naacl-main)

Copied to clipboard

Dejiao Zhang, Feng Nan, Xiaokai Wei, Shang-Wen Li, Henghui Zhu, Kathleen McKeown, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension (2021.findings-emnlp)

Challenge:	Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space, but different categories overlap with each other at the beginning of the learning process.
Approach:	They propose a framework to leverage contrastive learning to promote better separation between different categories by optimizing a clustering objective defined in the representation space.
Outcome:	The proposed framework improves state-of-the-art accuracy and normalized mutual information on short text clustering and combines top-down and bottom-up instance discrimination to achieve better distances.

Copied to clipboard

Haichao Zhu, Zekun Wang, Heng Zhang, Ming Liu, Sendong Zhao, Bing Qin

Improving Factual Consistency of Abstractive Summarization via Question Answering (2021.acl-long)

Challenge:	Existing domain adaptation paradigms for reading comprehension require large amounts of annotation data to achieve the desired task performance.
Approach:	They propose a few-shot domain adaptation paradigm for reading comprehension . they introduce self-attention attribution to weigh parameters and refine the lottery subnetwork .
Outcome:	The proposed model outperforms the full model fine-tuning adaptation on four out of five domains with a small amount of data available for adaptation.

Copied to clipboard

Feng Nan, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Kathleen McKeown, Ramesh Nallapati, Dejiao Zhang, Zhiguo Wang, Andrew O. Arnold, Bing Xiang

Summarization

Challenge:	Recent studies show that about 30% of summaries generated by neural text summarization suffer from fact fabrication.
Approach:	They propose an automatic evaluation metric to measure factual consistency and a learning algorithm that maximizes the metric during model training.
Outcome:	The proposed method improves factual consistency and overall quality of summarization models.

Continual Prompt Tuning for Dialog State Tracking (2022.acl-long)

Copied to clipboard

Qi Zhu, Bing Li, Fei Mi, Xiaoyan Zhu, Minlie Huang

Responsible & Trustworthy NLP

Challenge:	Existing methods to train a model on a sequence of tasks are not efficient enough to mitigate catastrophic forgetting.
Approach:	They propose a parameter-efficient framework that prevents forgetting and enables knowledge transfer between tasks by learning and freezing a pre-trained model.
Outcome:	The proposed framework avoids forgetting and enables knowledge transfer between tasks.

Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting (2020.acl-main)

Copied to clipboard

Guanhua Zhang, Bing Bai, Junqi Zhang, Kun Bai, Conghui Zhu, Tiejun Zhao

Text Classification

Challenge:	Recent research has found that text classification datasets contain certain unintended biases, such as text containing demographic identity-terms that are more likely to be abusive.
Approach:	They propose a model-agnostic debiasing framework that recovers the non-discrimination distribution using instance weighting, which does not require extra resources or annotations apart from a pre-defined set of demographic identity-terms.
Outcome:	The proposed framework alleviates the unintended biases without hurting models’ generalization ability.

Pairwise Supervised Contrastive Learning of Sentence Representations (2021.emnlp-main)

Copied to clipboard

Dejiao Zhang, Shang-Wen Li, Wei Xiao, Henghui Zhu, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang

Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning (2021.naacl-main)

Challenge:	Recent efforts to improve sentence representation learning have a common weakness . siamese or triplet loss only learns from individual sentence pairs or tripletes .
Approach:	They propose a discrimination-based approach to bridge entailment and contradiction understanding with categorical concept encoding.
Outcome:	The proposed method outperforms the state-of-the-art method on downstream tasks . it improves 10%–13% on clustering tasks and 5%–6% on STS tasks compared with the previous method .

Copied to clipboard

Hui Liu, Danqing Zhang, Bing Yin, Xiaodan Zhu

FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Existing zero-shot learning methods for multi-label text classification mostly learn a matching model between the feature space of text and the label space.
Approach:	They propose to use a graph encoder to incorporate label hierarchies to learn effective label representations on the zero-shot multi-label text classification problem.
Outcome:	The proposed approach outperforms previous non-pretrained methods on the zero-shot multi-label text classification task.

Copied to clipboard

Xin Guo, Haotian Xia, Zhaowei Liu, Hanyang Cao, Zhi Yang, Zhiqiang Liu, Sizhe Wang, Jinyi Niu, Chuqi Wang, Yanhui Wang, Xiaolong Liang, Xiaoming Huang, Bing Zhu, Zhongyu Wei, Yun Chen, Weining Shen, Liwen Zhang

BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering (2024.acl-long)

Challenge:	Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored.
Approach:	They propose to use a benchmark to evaluate large language models' financial domain knowledge and practical abilities.
Outcome:	The proposed benchmark evaluates large language models' financial domain knowledge and practical abilities.

Copied to clipboard

Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, Bing Qin

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated strong reasoning capabilities, but they still suffer from factual errors when tackling knowledge-intensive tasks.
Approach:	They propose a reasoning framework for knowledge-intensive multi-hop QA that prioritizes promising answers at each hop of question.
Outcome:	The proposed framework outperforms SOTA methods on four open-domain multi-hop reasoning datasets by 8.5%.

Parsing Tweets into Universal Dependencies (N18-1)

Copied to clipboard

Yijia Liu, Yi Zhu, Wanxiang Che, Bing Qin, Nathan Schneider, Noah A. Smith

Syntactic Text Processing

Challenge:	a new tweet treebank for English is designed to analyze tweets with universal dependencies (UD).
Approach:	They extend the universal dependencies guidelines to include special constructions in tweets that affect tokenization, part-of-speech tagging, and labeled dependencies.
Outcome:	The proposed method outperforms state-of-the-art parsers on other treebanks in accuracy and speed.

On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration (2026.findings-acl)

Copied to clipboard

Huaisheng Zhu, MingYu Liu, Junze Liu, Zhen Ge, Tian Wang, Jiri Gesi, Dakuo Wang, Weiqi Zhang, Houyu Zhang, Yufan Guo, Xian Li, Bing Yin, Sujay Sanghavi

Probing Language Models for Pre-training Data Detection (2024.acl-long)

Challenge:	Recent studies have demonstrated that masked diffusion models (MDMs) can surpass autoregressive models (ARMs) in various tasks.
Approach:	They propose a method to calibrate early token predictions without demonstration data by distilling an unnormalized target distribution into the original model.
Outcome:	Experiments on math, planning, and RLHF tasks show that COPSD improves both effectiveness and efficiency, and further enhances performance when combined with supervised fine-tuning.

Copied to clipboard

Zhenhua Liu, Tong Zhu, Chuanyuan Tan, Bing Liu, Haonan Lu, Wenliang Chen

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge (2023.findings-acl)

Challenge:	Large Language Models (LLMs) have shown impressive capabilities, while raising concerns about the data contamination due to privacy issues and leakage of benchmark datasets in the pre-training phase.
Approach:	They propose to utilize the probing technique to examine the model’s internal activations to detect pre-training data contamination by examining the model's internal activates.
Outcome:	The proposed method outperforms baselines and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy.

Copied to clipboard

Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang