Papers by Zhenghua Li

A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents (2021.naacl-main)

Challenge:	Unlike English letters, Chinese characters have rich and specific meanings.
Approach:	They propose to model Chinese words' internal structures as dependency trees with 11 labels for distinguishing syntactic relationships.
Outcome:	The proposed model of Chinese word-internal structures shows it can be used to parse sentences . it shows that the model can be applied to a sentence-level task with a competitive dependency parser.

Copied to clipboard

Qingrong Xia, Bo Zhang, Rui Wang, Zhenghua Li, Yue Zhang, Fei Huang, Luo Si, Min Zhang

Think Smart, Not Hard: Difficulty Adaptive Reasoning for Large Audio Language Models (2026.findings-acl)

Challenge:	Existing methods for fine-grained opinion mining (OM) are based on span-based annotations, but they are not effective.
Approach:	They propose a unified span-based approach for the end-to-end OM setting using syntactic constituents and multi-task learning to integrate them into the proposed model.
Outcome:	The proposed approach achieves significant improvements over previous work on the MPQA 2.0 dataset and reduces the number of wrongly-predicted opinion expressions and roles.

Copied to clipboard

Zhichao Sheng, Shilin Zhou, Chen Gong, Zhenghua Li

Towards Better Utilization of Multi-Reference Training Data for Chinese Grammatical Error Correction (2024.findings-acl)

Challenge:	Existing methods to determine whether to perform reasoning lack fine-grained mechanisms to adapt reasoning length to problem complexity.
Approach:	They propose a difficulty-adaptive reasoning method that dynamically links reasoning length to the model’s perceived problem difficulty.
Outcome:	The proposed method reduces average reasoning length by 50%, achieving higher efficiency without sacrificing accuracy.

Copied to clipboard

Yumeng Liu, Zhenghua Li, HaoChen Jiang, Bo Zhang, Chen Li, Ji Zhang

Distantly Supervised NER with Partial Annotation Learning and Reinforcement Learning (C18-1)

Challenge:	a high proportion of Chinese training data is multi-referenced for the grammatical error correction task . however, there are many ways to correct an erroneous input sentence . a systematic study on multi-referencing training data has been proposed .
Approach:	They propose two new approaches and a simple two-stage training strategy to better utilize multi-reference training data.
Outcome:	The proposed methods show that Chinese training data contain multiple references.

Copied to clipboard

Yaosheng Yang, Wenliang Chen, Zhenghua Li, Zhengqiu He, Min Zhang

Information Extraction & Text Mining

Challenge:	Existing approaches to named entity recognition (NER) in Chinese are limited by the lack of annotated data.
Approach:	They propose a method which can automatically populate annotated training data without humancost by using distant supervision.
Outcome:	The proposed method performs better than comparison systems on two datasets.

NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts (2023.findings-acl)

Copied to clipboard

Yue Zhang, Bo Zhang, Haochen Jiang, Zhenghua Li, Chen Li, Fei Huang, Min Zhang

Fast and Accurate End-to-End Span-based Semantic Role Labeling as Word-based Graph Parsing (2022.coling-1)

Challenge:	Recent studies on Chinese grammatical error correction focus on learning essays.
Approach:	They propose a Chinese grammatical error correction dataset that annotates multiple references for 12,500 sentences from three native domains.
Outcome:	The proposed dataset can be used to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains.

Copied to clipboard

Shilin Zhou, Qingrong Xia, Zhenghua Li, Yu Zhang, Yu Hong, Min Zhang

Semi-supervised Domain Adaptation for Dependency Parsing via Improved Contextualized Word Representations (2020.coling-main)

Challenge:	Using end-to-end span-based SRL, we propose a word-based graph parsing task for word-level representation of spans . compared with word-driven SRL, span-Based SRL is more complex due to difficulties in determining argument boundaries.
Approach:	They propose to cast end-to-end span-based SRL as a word-based graph parsing task . they propose a constrained Viterbi procedure to ensure the legality of the output graph .
Outcome:	The proposed model can parse 669/252 sentences per second without and with pre-trained models.

Copied to clipboard

Ying Li, Zhenghua Li, Min Zhang

DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check (2025.acl-long)

Challenge:	Recent advances in deep neural network models have improved parsing performance on in-domain texts . however, the problem is to improve performance on out-of-domain text data when there is only a small-scale out-domain labeled data.
Approach:	They propose to use adversarial learning and fine-tuning BERT to improve contextualized word representations on out-of-domain texts.
Outcome:	The proposed models achieve consistent improvement and fine-tune BERT processes boost parsing accuracy by a large margin.

Copied to clipboard

Ziheng Qiao, Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang

Searching for Best Practices in Retrieval-Augmented Generation (2024.emnlp-main)

Challenge:	Chinese spelling check (CSC) tasks require that incorrect characters are usually similar to the correct ones in either phonetics or glyph.
Approach:	They propose a plug-and-play decoding intervention with similarity of characters module for Chinese spelling check (CSC) they propose to incorporate phonetic and glyph similarities only during the inference phase.
Outcome:	The proposed method significantly improves Chinese spelling check models on benchmarks and on benchmark datasets.

Copied to clipboard

Xiaohua Wang, Zhenghua Wang, Xuan Gao, Feiran Zhang, Yixin Wu, Zhibo Xu, Tianyuan Shi, Zhengyuan Wang, Shizheng Li, Qi Qian, Ruicheng Yin, Changze Lv, Xiaoqing Zheng, Xuanjing Huang

Information Retrieval

Challenge:	Retrieval-augmented generation (RAG) techniques have proven to be effective in integrating up-to-date information, mitigating hallucinations, and enhancing response quality, especially in specialized domains.
Approach:	They propose several strategies for deploying RAG that balance performance and efficiency.
Outcome:	The proposed approaches can significantly enhance question-answering capabilities and accelerate the generation of multimodal content using a “retrieval as generation” strategy.

Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation (2025.coling-main)

Copied to clipboard

Xuebin Wang, Lei Zhang, Zhenghua Li, Shilin Zhou, Chen Gong, Yang Hou

Multimodality

Challenge:	Recent studies on Chinese Word Segmentation (CWS) have focused on the cross-domain scenarios, but there is a high cost of manually annotating high-quality data.
Approach:	They propose to explicitly mine word boundaries from parallel speech-text data by using the Montreal Forced Aligner toolkit to perform character-level alignment on speech- text data.
Outcome:	The proposed approach is based on character-level alignment on speech-text data and a robust complete-then-train (CTT) strategy.

Semantic Role Labeling with Heterogeneous Syntactic Knowledge (2020.coling-main)

Copied to clipboard

Qingrong Xia, Rui Wang, Zhenghua Li, Yue Zhang, Min Zhang

MPL: Multiple Programming Languages with Large Language Models for Information Extraction (2025.findings-acl)

Challenge:	Recent work on incorporating syntactic knowledge into neural semantic role labeling has gained much attention . incorporating heterogeneous syntaktic knowledge brings significant improvements over strong baselines .
Approach:	They propose to encode heterogeneous syntactic knowledge for SRL from explicit and implicit representations from heterogenous treebanks.
Outcome:	The proposed approaches improve on two widely-used benchmark datasets.

Copied to clipboard

Bo Li, Gexiang Fang, Wei Ye, Zhenghua Xu, Jinglei Zhang, Hao Cheng, Shikun Zhang

Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models (2025.findings-acl)

Challenge:	Existing research focuses on Python for code-style simulation, overlooking the potential of other widely-used PLs during the supervised fine-tuning phase.
Approach:	They propose a framework that incorporates programming languages into IE tasks . they introduce function-prompt with virtual running to simulate code-style inputs .
Outcome:	The proposed framework exploits the potential of different programming languages during the supervised fine-tuning phase.

Copied to clipboard

Yanggan Gu, Junzhuo Li, Sirui Huang, Xin Zou, Zhenghua Li, Xuming Hu

MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error Correction (2022.naacl-main)

Challenge:	Existing methods for aligning small language models with human values model preference knowledge from large language models (LLMs) however, this limitation hinders student SLMs from capturing nuanced preferences for multiple responses.
Approach:	They propose a framework which models teacher's preference knowledge as a probability distribution over all potential preferences, thereby providing more nuanced supervisory signals.
Outcome:	The proposed framework outperforms existing methods on four benchmark tasks and achieves 20% improvement on AlpacaEval 2 and Arena-Hard.

Copied to clipboard

Yue Zhang, Zhenghua Li, Zuyi Bao, Jiacheng Li, Bo Zhang, Chen Li, Fei Huang, Min Zhang

A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models (2024.emnlp-main)

Challenge:	Using a multi-reference multi-source evaluation dataset, Chinese grammatical error correction (CGEC) is relatively scarce.
Approach:	They propose a multi-reference multi-source evaluation dataset for Chinese grammar error correction . the dataset contains 7,063 sentences written by Chinese-as-a-Second-Language learners .
Outcome:	The proposed dataset can be used to evaluate Chinese grammar errors in Chinese.

Copied to clipboard

Houquan Zhou, Zhenghua Li, Bo Zhang, Chen Li, Shaopeng Lai, Ji Zhang, Fei Huang, Min Zhang

Self-Correction Makes LLMs Better Parsers (2025.findings-emnlp)

Challenge:	Using an LLM for Chinese spelling correction tasks is completely different from previous approaches . given a Chinese character, there may exist many others with the same or similar pronunciations, or with similar shapes.
Approach:	They propose a training-free prompt-free approach to leverage large language models for Chinese spelling correction task.
Outcome:	The proposed model significantly improves performance on five public datasets, enabling them to compete with state-of-the-art domain-general CSC models.

Copied to clipboard

Ziyan Zhang, Yang Hou, Chen Gong, Zhenghua Li

Bridging Pre-trained Language Models and Hand-crafted Features for Unsupervised POS Tagging (2022.findings-acl)

Challenge:	Large language models (LLMs) have achieved remarkable success across various natural language processing tasks, but they still face challenges in performing fundamental NLP tasks, such as syntactic parsing.
Approach:	They propose a method that leverages grammar rules from existing treebanks to guide LLMs in correcting previous errors.
Outcome:	The proposed method significantly improves performance on in-domain and cross-domain datasets.

Copied to clipboard

Houquan Zhou, Yang Li, Zhenghua Li, Min Zhang

Stacked AMR Parsing with Silver Data (2021.findings-emnlp)

Challenge:	Large-scale pre-trained language models (PLMs) have made extraordinary progress in most NLP tasks, but they fail to achieve state-of-the-art (SOTA) performance.
Approach:	They propose a Guassian HMM variant for unsupervised POS tagging that incorporates contexualized word representations into the decoder.
Outcome:	The proposed model outperforms state-of-the-art models on Penn Treebank and multilingual Universal Dependencies treebank v2.0.

Copied to clipboard

Qingrong Xia, Zhenghua Li, Rui Wang, Min Zhang

Efficient Second-Order TreeCRF for Neural Dependency Parsing (2020.acl-main)

Challenge:	Lack of large-scale annotated data is one main challenge for abstract meaning representation (AMR) parsing.
Approach:	They propose to use silver data to train a pre-trained abstract meaning representation model.
Outcome:	The proposed model outperforms previous models on the AMR2.0 dataset and is faster than the SOTA model.

Copied to clipboard

Yu Zhang, Zhenghua Li, Min Zhang

Green & Sustainable NLP

Challenge:	In the deep learning (DL) era, dependency parsing models are extremely simplified with little hurt on performance thanks to the remarkable capability of multi-layer BiLSTMs in context representation.
Approach:	They propose to extend the biaffine parser to a second-order TreeCRF extension to reduce the complexity of the inside-outside algorithm.
Outcome:	The proposed extension can be used to batchify the inside and Viterbi algorithms and avoid the complex outside algorithm via efficient back-propagation.

Multi-grained Chinese Word Segmentation with Weakly Labeled Data (2020.coling-main)

Copied to clipboard

Chen Gong, Zhenghua Li, Bowei Zou, Min Zhang

SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser (2022.emnlp-main)

Challenge:	Existing work on single-grained word segmentation (SWS) focuses on segmenting a sentence into multiple word sequences to preserve all words of different granularities.
Approach:	They propose to use a graph-based parser to accommodate weakly labeled data for MWS by employing a simple yet competitive graph-basic parsers with local loss.
Outcome:	The proposed model outperforms the state-of-the-art model on weakly labeled data on a high-quality dataset from canonical newswire (NEWS) and non-canonical web (BAIKE) data.

Copied to clipboard

Yue Zhang, Bo Zhang, Zhenghua Li, Zuyi Bao, Chen Li, Min Zhang

High-order Joint Constituency and Dependency Parsing (2024.lrec-main)

Challenge:	Existing approaches to grammatical error correction are unreliable when processing ungrammatically . a new approach is proposed that incorporates dependency syntactic information into the encoder part of GEC models.
Approach:	They propose a syntax-enhanced grammatical error correction approach called SynGEC that incorporates dependency syntactic information into the encoder part of GEC models.
Outcome:	The proposed approach outperforms strong baselines and achieves competitive performance on mainstream English and Chinese GEC datasets.

Copied to clipboard

Yanggan Gu, Yang Hou, Zhefeng Wang, Xinyu Duan, Zhenghua Li

UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation (2025.findings-emnlp)

Challenge:	Syntactic parsing aims to reveal how sentences are syntactically structured.
Approach:	They propose to produce compatible constituency and dependency trees simultaneously for input sentences . they adopt a much more efficient decoding algorithm and explore joint modeling at training phase .
Outcome:	The proposed model significantly improves matching ratio of whole trees compared to separate models . the proposed model adopts a much more efficient decoding algorithm .

Copied to clipboard

Tianlong Li, Wenhao Liu, Muling Wu, Shihan Dou, Zhenghua Wang, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang

Supervised Treebank Conversion: Data and Approaches (P18-1)

Challenge:	Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs).
Approach:	They propose a method that uses an Unsupervisedly-Built Personalized Lexicon (UPL) during the decoding phase to manipulate LLM’s personality traits.
Outcome:	The proposed method can modulate the personality expression of large language models by dynamically altering their predicted probability of upcoming words in a pluggable fashion.

Copied to clipboard

Xinzhou Jiang, Zhenghua Li, Bo Zhang, Min Zhang, Sheng Li, Luo Si

A Syntax-aware Multi-task Learning Framework for Chinese Semantic Role Labeling (D19-1)

Challenge:	Existing work on treebank conversion focuses on unsupervised treebanks . lack of manually labeled data means that sentences have two syntactic trees at the same time.
Approach:	They propose supervised treebank conversion using bi-tree aligned sentences . they propose two conversion approaches based on state-of-the-art deep biaffine parser .
Outcome:	The proposed method outperforms the state-of-the-art deep biaffine parser on the English WSJ dataset by 0.97 (93.76% -92.79%)

Copied to clipboard

Qingrong Xia, Zhenghua Li, Min Zhang

Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks (2020.acl-main)

Challenge:	Semantic role labeling (SRL) aims to identify the predicate-argument structure of a sentence.
Approach:	They propose to use a unified span-based model for Chinese SRL as a strong baseline.
Outcome:	The proposed framework achieves state-of-the-art 87.54 and 88.5 F1 scores on the Chinese Proposition Bank and CoNLL-2009 datasets.

Copied to clipboard

Bo Zhang, Yue Zhang, Rui Wang, Zhenghua Li, Min Zhang

Multimodality

Challenge:	Opinion role labeling (ORL) is a fine-grained opinion analysis task . due to the scarcity of labeled data, ORL remains challenging for data-driven methods due to its complexity and complexity.
Approach:	They propose to integrate syntactic knowledge into ORL models by comparing and integrating different representations and using dependency graph convolutional networks to encode parser information at different processing levels.
Outcome:	The proposed model achieves 4.34 higher F1 score than the current state-of-the-art.

Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling (2024.lrec-main)

Copied to clipboard

Chenhui Dou, Chen Gong, Zhenghua Li, Zhefeng Wang, Baoxing Huai, Min Zhang

Improving Seq2Seq Grammatical Error Correction via Decoding Interventions (2023.findings-emnlp)

Challenge:	Named entity recognition (CNER) is a fundamental task in natural language processing (NLP).
Approach:	They propose a tree parsing approach for jointly modeling Chinese named entity recognition (CNER) with multi-grained word segmentation (MWS) and POS tagging tasks.
Outcome:	The proposed approach achieves better or comparable performance with current methods.

Copied to clipboard

Houquan Zhou, Yumeng Liu, Zhenghua Li, Min Zhang, Bo Zhang, Chen Li, Ji Zhang, Fei Huang

Data Augmentation for Cross-domain Parsing via Lightweight LLM Generation and Tree Hybridization (2025.coling-main)

Challenge:	Existing approaches to grammatical error correction (GEC) are sequence-to-sequence and sequence-edit.
Approach:	They propose a unified decoding intervention framework that employs an external critic to assess the appropriateness of the token to be generated incrementally.
Outcome:	The proposed framework outperforms baselines and state-of-the-art methods on English and Chinese datasets.

Copied to clipboard

Ziyan Zhang, Yang Hou, Chen Gong, Zhenghua Li

Responsible & Trustworthy NLP

Challenge:	Existing approaches for constituency parsing are expensive and lack high-quality labeled data.
Approach:	They propose a data augmentation method via lightweight large language model (LLM) generation and tree hybridization to generate a large number of structurally diverse instances.
Outcome:	The proposed method achieves significant improvements on five target domains with a lightweight LLM generation cost.

MuCPAD: A Multi-Domain Chinese Predicate-Argument Dataset (2022.naacl-main)

Copied to clipboard

Yahui Liu, Haoping Yang, Chen Gong, Qingrong Xia, Zhenghua Li, Min Zhang

Challenge:	Recent studies show that shallow semantic role labeling (SRL) performance drops under out-of-domain setting.
Approach:	They propose to annotate a multi-domain Chinese predicate-argument dataset using a frame-free annotation methodology and strict double annotation for improving data quality.
Outcome:	The proposed dataset is compared with a dataset from six different domains.

M-CNER: A Corpus for Chinese Named Entity Recognition in Multi-Domains (L18-1)

Copied to clipboard

Qi Lu, YaoSheng Yang, Zhenghua Li, Wenliang Chen, Min Zhang

Information Extraction & Text Mining

Challenge:	NER is one of the most important natural language processing tasks.
Approach:	They propose to annotate sentences from human-computer interaction, social media, and e-commerce using two rounds of annotation.
Outcome:	The proposed system performs the best on all the data sets.

Character-Level Chinese Dependency Parsing via Modeling Latent Intra-Word Structure (2024.findings-acl)

Copied to clipboard

Yang Hou, Zhenghua Li

DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset (2020.emnlp-main)

Challenge:	Existing word-level dependency parsing methods in Chinese lack explicit word boundaries due to the lack of word boundaries.
Approach:	They propose to model latent internal structures within Chinese words by constrained Eisner algorithm . they propose to guarantee a single root for intra-word structures and establish inter-word dependencies .
Outcome:	The proposed model outperforms existing models on Chinese treebanks and shows that it can predict plausible intra-word structures.

Copied to clipboard

Lijie Wang, Ao Zhang, Kun Wu, Ke Sun, Zhenghua Li, Hua Wu, Min Zhang, Haifeng Wang

Programming Languages in NLP

Challenge:	Existing text-to-SQL parsing methods mainly focus on English, but there is no labeled data available for the language . a larges-scale and pragmatic Chinese dataset is used for cross-domain text- to-Sql task .
Approach:	They propose a larges-scale Chinese dataset for a cross-domain text-to-SQL task . they analyze questions from several representative applications and use an effective data construction framework .
Outcome:	The proposed dataset contains 200 databases, 813 tables, and 23,797 question/SQL pairs.

A Probabilistic Toolkit for Multi-grained Word Segmentation in Chinese (2025.coling-demos)

Copied to clipboard

Xi Ma, Yang Hou, Xuebin Wang, Zhenghua Li

Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing (2021.emnlp-main)

Challenge:	Existing tools for word segmentation are based on different linguistic theories or target different scenarios.
Approach:	They propose a probabilistic toolkit for multi-grained word segmentation in Chinese . they adopt semi-Markov CRF for single-grain word segmenting (SWS) .
Outcome:	The proposed approach can produce marginal probabilities of words during inference and significantly improve performance in the cross-domain scenario.

Copied to clipboard

Kun Wu, Lijie Wang, Zhenghua Li, Ao Zhang, Xinyan Xiao, Hua Wu, Min Zhang, Haifeng Wang

Programming Languages in NLP

Challenge:	Existing approaches to parse text-to-SQL data are lacking labeled data for unseen evaluation databases.
Approach:	They propose a framework for enhancing SQL queries by automatically producing large numbers of SQL queries based on an abstract syntax tree grammar.
Outcome:	The proposed framework can produce high-quality natural language questions over strong baselines.

Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations (N19-1)

Copied to clipboard

Meishan Zhang, Zhenghua Li, Guohong Fu, Min Zhang

APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing (2021.findings-emnlp)

Challenge:	Syntax integration has been demonstrated highly effective in neural machine translation (NMT).
Approach:	They propose a method to integrate source-side syntax implicitly for neural machine translation . they use hidden representations of a well-trained end-to-end dependency parser to concatenate them with ordinary word embeddings to enhance basic NMT models.
Outcome:	The proposed method outperforms existing methods on two translation tasks . it can be easily integrated into the widely-used sequence-to-sequence (Seq2Sequen) framework .

Copied to clipboard

Ying Li, Meishan Zhang, Zhenghua Li, Min Zhang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan

Robustness in NLP

Challenge:	Existing models for dependency parsing use labeled training data for several fixed domains, but performance drops when labeles only exist for several out-domains.
Approach:	They propose a model for multi-source cross-domain dependency parsing that uses a parameter generation network and adversarial network for learning domain-invariant representations.
Outcome:	The proposed model improves cross-domain parsing performance by about 2 points over strong BERT-enhanced baselines over a recently released dataset for multi-domain dependency parse.

Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling (2026.findings-acl)

Copied to clipboard

Zhenghua Wang, Yiran Ding, Changze Lv, Yixin Wu, Tianlong Li, Zhibo Xu, Muling Wu, Tianyuan Shi, Shizheng Li, Qi Qian, Xuanjing Huang, Xiaoqing Zheng

Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)

Challenge:	Existing methods to address the "lost-in-the-middle" problem suffer from high latency or suboptimal hand-crafted scaling strategies.
Approach:	They propose a layer-specific positional embedding scaling method that assigns distinct scaling factors to each layer.
Outcome:	Experiments show that the proposed method mitigates positional attention bias and delivers consistent improvements across multiple long-context benchmarks.

Copied to clipboard

Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang

A Training-free LLM-based Approach to General Chinese Character Error Correction (2025.acl-long)

Challenge:	Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted.
Approach:	They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space.
Outcome:	The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns.

Copied to clipboard

Houquan Zhou, Bo Zhang, Zhenghua Li, Ming Yan, Min Zhang

Mixture of Small and Large Models for Chinese Spelling Check (2025.acl-long)

Challenge:	Chinese spelling correction (CSC) is a crucial task that aims to correct character errors in text.
Approach:	They propose a task that handles missing and redundant characters and an additional prompt-based large language model to improve performance.
Outcome:	The proposed task is based on a high-quality dataset and a prompt-based large language model.

Copied to clipboard

Ziheng Qiao, Houquan Zhou, Zhenghua Li

Challenge:	Chinese Spelling Check (CSC) tasks have been developed to correct spelling errors in given sentences . fine-tuned BERT-based models show excellent performance but suffer from edit pattern overfitting . a novel mixture approach that effectively combines small models and LLMs during beam search decoding phase improves accuracy and fluency of LLM.
Approach:	They propose a dynamic mixture approach that effectively combines small models and LLMs during beam search decoding phase.
Outcome:	The proposed method significantly boosts error correction capabilities, achieving state-of-the-art results across multiple datasets.

CopyNE: Better Contextual ASR by Copying Named Entities (2024.acl-long)

Copied to clipboard

Shilin Zhou, Zhenghua Li, Yu Hong, Min Zhang, Zhefeng Wang, Baoxing Huai

Multimodality

Challenge:	Existing approaches to transcribe contextual named entities (NEs) treat entities as tokens and generate them token-by-token, which may result in incomplete transcriptions of entities.
Approach:	They propose a mechanism that can copy entities from the NE dictionary and reduce errors during entity transcription.
Outcome:	The proposed mechanism can copy entities from the NE dictionary, reducing errors during entity transcription, ensuring the completeness of the entity.

Span-based Semantic Role Labeling as Lexicalized Constituency Tree Parsing (2025.findings-acl)

Copied to clipboard

Yang Hou, Zhenghua Li