Papers by Tingwen Liu

From What to Why: Improving Relation Extraction with Rationale Graph (2021.findings-acl)

Challenge:	Recent attempts to learn static representations of entities and references ignore their dynamic properties.
Approach:	They propose to learn static representations of entities and references ignoring their dynamic properties . a neighbor encoder learns entities' roles while a query-aware aggregator learns references' contributions .
Outcome:	The proposed approach achieves state-of-the-art results with different few-shot sizes.

Copied to clipboard

Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Xue Mengge, Tingwen Liu, Li Guo

Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing (2025.emnlp-main)

Challenge:	Existing neural relation extraction models are limited by entity type and textual context.
Approach:	They propose a novel RAtionale Graph to organize co-occurrence constraints among entity types, triggers and relations in a holistic graph view.
Outcome:	The proposed method outperforms baselines significantly and achieves state-of-the-art performance on document-level and sentence-level RE benchmarks.

Copied to clipboard

Wenyuan Zhang, Shuaiyi Nie, Jiawei Sheng, Zefeng Zhang, Xinghua Zhang, Yongquan He, Tingwen Liu

Reasoning

Challenge:	Existing studies on large language models (LLMs) fail to detect character knowledge errors, leading to low-quality automatic corpus construction.
Approach:	They propose to use a large language model to detect known knowledge errors and an agent-based reasoning method to improve error detection.
Outcome:	The proposed method improves the ability of LLMs to detect errors in known knowledge errors and unknown knowledge errors while playing roles.

LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion (2024.acl-long)

Copied to clipboard

Yilong Chen, Junyuan Shang, Zhenyu Zhang, Shiyao Cui, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu

SOTOPIA-: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents (2025.acl-long)

Challenge:	Existing methods to train a stronger and smaller model with the help of large models are limited by the model size and performance.
Approach:	They propose to learn competent initial points for smaller models by fusing parameters from larger models and introduce controllable receptive fields to model prior parameter characteristics.
Outcome:	The proposed method outperforms baselines in terms of effectiveness and efficiency.

Copied to clipboard

Wenyuan Zhang, Tianyun Liu, Mengxiao Song, Xiaodong Li, Tingwen Liu

Challenge:	Existing studies on the social simulation of large language model intelligent agents have shown that even expert agents 1 perform significantly worse on challenging social tasks compared to expert agents.
Approach:	They propose a framework that dynamically injects a variety of social strategies into expert agents, thereby automating the construction of high-quality social dialogue training corpus.
Outcome:	The proposed framework enables the integration of social strategies into language agents and improves their performance on social tasks.

AttnPO: Attention-Guided Process Supervision for Efficient Reasoning (2026.acl-long)

Copied to clipboard

Shuaiyi Nie, null Dingsiyu, Wenyuan Zhang, Linhao Yu, Tianmeng Yang, Yao Chen, Weichong Yin, Yu Sun, Hua Wu, Tingwen Liu

Responsible & Trustworthy NLP

Challenge:	Existing trajectory-level length penalties fail to effectively shorten reasoning length and degrade accuracy, as they treat all reasoning steps uniformly and lack fine-grained signals to distinguish redundancy from necessity.
Approach:	They propose a low-overhead process-supervised RL framework that leverages the model’s intrinsic attention signals for step-level credit assignment.
Outcome:	The proposed framework reduces reasoning length while improving performance across 9 benchmarks.

Event Causality Extraction with Event Argument Correlations (2022.coling-1)

Copied to clipboard

Shiyao Cui, Jiawei Sheng, Xin Cong, Quangang Li, Tingwen Liu, Jinqiao Shi

Syntactic Text Processing

Challenge:	Event Causality Identification (ECI) ignores crucial event structure and cause-effect component information, making it struggle for downstream applications.
Approach:	They propose a task to extract event causality pairs with their structured event information from plain text.
Outcome:	The proposed method captures the intra- and inter-event argument correlations for ECE and provides several future directions.

Discontinuous Named Entity Recognition as Maximal Clique Discovery (2021.acl-long)

Copied to clipboard

Yucheng Wang, Bowen Yu, Hongsong Zhu, Tingwen Liu, Nan Yu, Limin Sun

Relation Logical Reasoning and Relation-aware Entity Encoding for Temporal Knowledge Graph Reasoning (2025.coling-main)

Challenge:	Existing methods for named entity recognition break the recognition process into several sequential steps.
Approach:	They propose a method that breaks the recognition process into several sequential steps . they construct a segment graph for each sentence and a grid tagging scheme to learn it .
Outcome:	Experiments show that the proposed method outperforms the state-of-the-art model and achieves 5x speedup over the SOTA model.

Copied to clipboard

Longzhou Liu, Chenglong Xiao, Shanshan Wang, Tingwen Liu

Coarse-to-Fine Pre-training for Named Entity Recognition (2020.emnlp-main)

Challenge:	Current knowledge graph models focus on embedding entities and relations, overlooking the broader structure of the entire knowledge graph.
Approach:	They propose a Temporal Knowledge Graph Reasoning model that embeds relation embeddings into the TKG.
Outcome:	The proposed model outperforms state-of-the-art models on five public datasets . it uses relation-aware attention mechanisms to learn relation embeddings based on query relations .

Copied to clipboard

Xue Mengge, Bowen Yu, Zhenyu Zhang, Tingwen Liu, Yue Zhang, Bin Wang

Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph (2022.acl-long)

Challenge:	Named Entity Recognition (NER) is a task of discovering information entities and identifying their corresponding categories.
Approach:	They propose a NER-specific framework to inject coarse-to-fine named entity knowledge into pre-trained models by using a remote supervision strategy.
Outcome:	The proposed framework achieves significant improvements against several pre-trained base-lines, demonstrating its effectiveness in label-few and low-resource scenarios.

Copied to clipboard

Yanzeng Li, Jiangxia Cao, Xin Cong, Zhenyu Zhang, Bowen Yu, Hongsong Zhu, Tingwen Liu

Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation (2020.findings-emnlp)

Challenge:	Experimental results show that pre-trained Chinese language models ignore linguistics knowledge to learn representations.
Approach:	They propose a task-free enhancement module to integrate linguistics knowledge into Chinese pre-trained language models.
Outcome:	The proposed model improves Chinese pre-trained language models on 6 tasks with 10 benchmark datasets.

Copied to clipboard

Shiyao Cui, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Xuebin Wang, Jinqiao Shi

Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction (2020.coling-main)

Challenge:	Event detection (ED) is a key subtask of information extraction.
Approach:	They propose an architecture that exploits syntactic structure and typed dependency label information to perform event detection.
Outcome:	The proposed architecture exploits syntactic structure and typed dependency label information to perform ED.

Copied to clipboard

Bowen Yu, Xue Mengge, Zhenyu Zhang, Tingwen Liu, Wang Yubin, Bin Wang

Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking (2025.acl-long)

Challenge:	Existing approaches to remove noise from dependency trees are not optimal due to complexity and variability of natural language.
Approach:	They propose a dynamically pruned Graph Convolutional Network (DP-GCN) that prunes the dependency tree with rethinking in an end-to-end scheme.
Outcome:	The proposed model achieves impressive results compared to strong competitors.

Copied to clipboard

Yilong Chen, Junyuan Shang, Zhenyu Zhang, Yanxi Xie, Jiawei Sheng, Tingwen Liu, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang

ExpSeek: Self-Triggered Experience Seeking for Web Agents (2026.findings-acl)

Challenge:	Large language models face inherent performance bottlenecks under parameter constraints . challenging tokens induce abrupt gradient spikes across layers, exposing stress points .
Approach:	They propose an inner thinking transformer that reimagines layer computations as implicit thinking steps.
Outcome:	Empirical results show that ITT outperforms Transformer/Loop variants in 11 benchmarks.

Copied to clipboard

Wenyuan Zhang, Xinghua Zhang, Haiyang Yu, Shuaiyi Nie, Bingli Wu, Juwei Yue, Tingwen Liu, Yongbin Li

Challenge:	Existing methods for integrating experience into web agents are struggling to adapt to dynamically changing contextual observations during agent-environment interaction.
Approach:	They propose a model that shifts experience toward step-level proactive seeking by estimating step- level entropy thresholds and designing step-Level tailored experience content.
Outcome:	The proposed model achieves 9.3% and 7.5% performance improvements on Qwen3-8B and 32B models across four challenging web agent benchmarks.

NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time (2024.acl-long)

Copied to clipboard

Yilong Chen, Guoxia Wang, Junyuan Shang, Shiyao Cui, Zhenyu Zhang, Tingwen Liu, Shuohuan Wang, Yu Sun, Dianhai Yu, Hua Wu

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) with extended context windows are expensive and infeasible on fixed memory hardware due to the surprisingly large memory consumption of KV Cache.
Approach:	They propose a general framework for long-context KV cache eviction that achieves more optimal and efficient evict in a single operation during the encoding phase.
Outcome:	The proposed framework improves performance on short- and long-text tasks by 80% and 76% respectively, reducing KV Cache by up to 5 with over 95% performance maintenance.

CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction (2021.findings-acl)

Copied to clipboard

Jiawei Sheng, Shu Guo, Bowen Yu, Qian Li, Yiming Hei, Lihong Wang, Tingwen Liu, Hongbo Xu

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction (2025.findings-emnlp)

Challenge:	Existing methods assume that events appear in sentences without overlaps . overlapping event extraction is a challenging task in natural language understanding .
Approach:	They propose a joint learning framework with cascade decoding for overlapping event extraction . they sequentially perform type detection, trigger extraction and argument extraction based on the specific former prediction .
Outcome:	The proposed framework improves on a public event extraction benchmark . it sequentially performs type detection, trigger extraction and argument extraction .

Copied to clipboard

Yuanbo Xie, Yingjie Zhang, Tianyun Liu, Duohe Ma, Tingwen Liu

Robustness in NLP

Challenge:	Jailbreak attacks pose persistent threats to large language models . current safety alignment methods have insufficient safety alignment depth and unrobust internal defense mechanisms.
Approach:	a new safety alignment framework is developed to overcome jailbreak attacks . the framework forces the model to dynamically rebuild its refusal mechanisms from jailbreak states .
Outcome:	a new safety alignment framework reduces attack success rates by approximately 95% on four open-source LLM families and six representative attacks.

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning (2021.findings-emnlp)

Copied to clipboard

Xinghua Zhang, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Jiawei Sheng, Xue Mengge, Hongbo Xu

Towards Generalized Open Information Extraction (2022.findings-emnlp)

Challenge:	Named entity recognition (NER) is a method of detecting entity spans and classifying them into predefined categories.
Approach:	They propose a method to iteratively perform noisy label refinery by using self-collaborative denoising learning.
Outcome:	The proposed learning paradigm exploits reliable labels and communicates with unreliable annotations by collaborative denoising.

Copied to clipboard

Bowen Yu, Zhenyu Zhang, Jingyang Li, Haiyang Yu, Tingwen Sun, Jian Liu, Yongbin Li, Bin Wang

Porous Lattice Transformer Encoder for Chinese NER (2020.coling-main)

Challenge:	Open Information Extraction (OpenIE) models are evaluated on in-domain test sets aside from the training corpus, which violates the initial task principle of domain-independence.
Approach:	They propose to generalize OpenIE over unseen target domains with different data distributions from source training domains.
Outcome:	The proposed method beats the previous methods in both in- and out-of-domain settings by 6.0% in F1 score absolutely.

Copied to clipboard

Xue Mengge, Bowen Yu, Tingwen Liu, Yue Zhang, Erli Meng, Bin Wang

Universal Information Extraction with Meta-Pretrained Self-Retrieval (2023.findings-acl)

Challenge:	Existing methods to integrate word boundary information into character-level Chinese NER are inefficient and lack semantic interaction.
Approach:	They propose an extension of transformer encoder that is tailored for ChineseNER to incorporate lexicons into character-level Chinese NER by lattices.
Outcome:	The proposed extension performs 11.4 times faster than state-of-the-art methods while retaining the rich long-term dependencies.

Copied to clipboard

Xin Cong, Bowen Yu, Mengcheng Fang, Tingwen Liu, Haiyang Yu, Zhongkai Hu, Fei Huang, Yongbin Li, Bin Wang

Few-Shot Event Detection with Prototypical Amortized Conditional Random Field (2021.findings-acl)

Challenge:	Existing methods for IE are task-specific, resulting in specialized and isolated approaches for different tasks.
Approach:	They propose a method to retrieve task-specific knowledge from pretrained language models to enhance universal IE by using a Meta-Pretraining Algorithm.
Outcome:	The proposed method achieves the new state-of-the-art on 4 IE tasks, 12 datasets under fully-supervised, low-resource and few-shot scenarios.

Copied to clipboard

Xin Cong, Shiyao Cui, Bowen Yu, Tingwen Liu, Wang Yubin, Bin Wang

FITAnnotator: A Flexible and Intelligent Text Annotation System (2021.naacl-demos)

Challenge:	Existing approaches to event detection ignore the trigger discrepancy and cause errors.
Approach:	They propose a unified model which converts a few-shot tagging problem into a single-shot model by using a Gaussian distribution.
Outcome:	The proposed model performs better than existing identifythen-classify models on a few-shot tagging problem with a double-part taging scheme.

Copied to clipboard

Yanzeng Li, Bowen Yu, Li Quangang, Tingwen Liu

Challenge:	In this paper, we introduce FITAnnotator, a generic web-based tool for efficient text annotation.
Approach:	They propose a generic web-based tool for efficient text annotation.
Outcome:	The proposed tool is based on a fully modular architecture and provides three kinds of interfaces to annotate instances, evaluate annotation quality and manage the annotation task for annotators, reviewers and managers.

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning (2021.emnlp-main)

Copied to clipboard

Xinghua Zhang, Bowen Yu, Tingwen Liu, Zhenyu Zhang, Jiawei Sheng, Xue Mengge, Hongbo Xu

Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention (2020.acl-main)

Challenge:	Named entity recognition (NER) is a method of detecting entity spans and classifying them into predefined categories.
Approach:	They propose a method to iteratively perform noisy label refinery by using self-collaborative denoising learning.
Outcome:	The proposed learning paradigm exploits reliable labels and communicates with unreliable annotations by collaborative denoising.

Copied to clipboard

Yanzeng Li, Bowen Yu, Xue Mengge, Tingwen Liu

Document-level Relation Extraction with Dual-tier Heterogeneous Graph (2020.coling-main)

Challenge:	Pre-trained Chinese language models take character as the basic unit and learn representation according to character’s external contexts, ignoring the semantics expressed in the word, which is the smallest meaningful utterance in Chinese.
Approach:	They propose to pool character-level attention to the word level and propose to alleviate the potential issue of segmentation error propagation by multi-source information fusion.
Outcome:	The proposed approach improves on five Chinese NLP benchmark tasks against BERT, ERNIE and BERT-wwm.

Copied to clipboard

Zhenyu Zhang, Bowen Yu, Xiaobo Shu, Tingwen Liu, Hengzhu Tang, Wang Yubin, Li Guo

Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking (2024.findings-acl)

Challenge:	Existing methods focus on extracting relations from single sentence . document-level relation extraction requires a comprehension of the whole document .
Approach:	They propose a graph-based model with Dual-tier Heterogeneous Graph (DHG) for document-level relation extraction.
Outcome:	The proposed model achieves state-of-the-art performance on two widely used datasets.

Copied to clipboard

Zefeng Zhang, Jiawei Sheng, Zhang Chuang, Liangyunzhi Liangyunzhi, Wenyuan Zhang, Siqi Wang, Tingwen Liu

Maximal Clique Based Non-Autoregressive Open Information Extraction (2021.emnlp-main)

Challenge:	Existing methods to link ambiguous mentions to entities in multimodal knowledge graphs rely on partial correlations.
Approach:	They propose a framework that leverages multi-element correlations to bridge modality gap and enable fine-grained semantic matching by exploiting correlation between multimodal features and entities.
Outcome:	The proposed framework outperforms state-of-the-art models and confirms the effectiveness of the proposed method.

Copied to clipboard

Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, Bin Wang

Sparse Growing Transformer: Training-Time Sparse Depth Allocation via Progressive Attention Looping (2026.findings-acl)

Challenge:	Open Information Extraction (OpenIE) aims to discover textual facts from a given sentence.
Approach:	They propose a non-autoregressive framework that generates a fact graph and a graph with an edge linking two nodes that belong to the same fact.
Outcome:	The proposed framework outperforms current state-of-the-art methods on two benchmark datasets and significantly outperformed the existing ones.

Copied to clipboard

Yao Chen, Yilong Chen, Yinqi Yang, Junyuan Shang, Zhenyu Zhang, Zefeng Zhang, Shuaiyi Nie, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang, Tingwen Liu

HyperMem: Hypergraph Memory for Long-Term Conversations (2026.acl-long)

Challenge:	Existing approaches to increasing effective depth of LLMs rely on parameter reuse, extending computation through recursive execution.
Approach:	They propose a training-time sparse depth allocation framework that progressively increases depth for a small subset of parameters as training evolves.
Outcome:	The proposed model outperforms existing approaches to increasing the effective depth of language models while reducing training FLOPs overhead from approximately 16–20% to only 1–3% relative to a standard Transformer backbone.

Copied to clipboard

Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang, Tingwen Liu, Li Guo, Yafeng Deng

Natural Language Interfaces

Challenge:	Existing approaches to long-term memory management rely on pairwise relations, causing fragmented retrieval.
Approach:	They propose a hypergraph-based hierarchical memory architecture that explicitly models high-order associations using hyperedges.
Outcome:	Experiments show that HyperMem achieves state-of-the-art performance with 92.73% accuracy for long-term conversations.

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game (2026.acl-long)

Copied to clipboard

Yuanbo Xie, Yingjie Zhang, Yulin Li, Shouyou Song, Xiaokun Chen, Zhihan Liu, Liya Su, Tingwen Liu

Robustness in NLP

Challenge:	Retrieval-Augmented Generation (RAG) systems augment large language models with external knowledge, but introduce a critical security vulnerability: Knowledge Base Leakage.
Approach:	They propose a runtime defense mechanism inspired by stack canaries in software security . canaryRAG embeds carefully designed canary tokens into retrieved chunks and reformulates RAG extraction defense as a dual-path runtime integrity game.
Outcome:	The proposed system can detect and prevent RAG Knowledge Base Leakage in real time . it can be integrated into arbitrary RAG pipelines without retraining or structural modifications .

Polymorphic Universal Transformer (2026.acl-long)

Copied to clipboard

Yilong Chen, Zitian Gao, Yihao Xiao, Jason Klein Liu, Xinyu Yang, Yifan Luo, Haoming Luo, Zhengmao Ye, Tingwen Liu, Ran Tao, Bryan Dai

TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking (2020.coling-main)

Challenge:	Compute Distribution Skew is a pathological phenomenon in ultra-deep recurrent models . it causes over-smoothing, representation rank collapse, and degraded reasoning performance.
Approach:	They propose a dynamic architecture that redefines recursive computation by decoupling parameter count from depth.
Outcome:	The proposed model significantly improves representation rank and reasoning robustness while reducing computation by 64.7%.

Copied to clipboard

Yucheng Wang, Bowen Yu, Yueyang Zhang, Tingwen Liu, Hongsong Zhu, Limin Sun

Improving Reasoning Capabilities in Small Models through Mixture-of-layers Distillation with Stepwise Attention on Key Information (2025.emnlp-main)

Challenge:	Existing methods to extract entities and relations from unstructured text are susceptible to cascading errors due to the separation of entity detection and relation classification.
Approach:	They propose a one-stage joint extraction model that detects overlapping relations while being immune from exposure bias.
Outcome:	The proposed model can identify overlapping relations while being immune from exposure bias.

Copied to clipboard

Yao Chen, Jiawei Sheng, Wenyuan Zhang, Tingwen Liu