Papers by Zhen Tan
Semantic and Sentiment Dual-Enhanced Generative Model for Script Event Prediction (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods to model event associations struggle with semantic ambiguity and embedding bias. |
| Approach: | They propose a Semantic and Sentiment Dual-enhanced Generative Model to address these issues . it leverages two types of script event information to enhance the generative model . |
| Outcome: | The proposed model captures both global and local sentiments of events through its sentiment awareness mechanism. |
Dynamic-prototype Contrastive Fine-tuning for Continual Few-shot Relation Extraction with Unseen Relation Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to learn relations from labeled data overlook task interference in continual learning and memory requirements for different relations. |
| Approach: | They propose a framework to learn new relations from limited labeled data while preserving knowledge about previously learned relations. |
| Outcome: | The proposed framework is more practical and comprehensive for real-world scenarios. |
Bit-Flip Error Resilience in LLMs: A Comprehensive Analysis and Defense Framework (2025.emnlp-main)
Copied to clipboard
Yuhang Chen, Zhen Tan, Ajay Kumar Jaiswal, Huaizhi Qu, Xinyu Zhao, Qi Lin, Yu Cheng, Andrew Kwong, Zhichao Cao, Tianlong Chen
| Challenge: | Bit-flip errors (BFEs) are hardware faults where individual bits in memory or processing units are unintentionally flipped. |
| Approach: | They propose a novel defense strategy to mitigate bit-flip errors (BFEs) they propose bfe protection and a self-correction mechanism to minimize performance degradation . |
| Outcome: | The proposed defense strategy minimizes performance degradation while significantly improving robustness against BFEs. |
SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention (2025.acl-long)
Copied to clipboard
| Challenge: | Content analysis is labor-intensive and time-consuming process that requires multiple rounds of manual annotation, domain expert discussion, and rule-based refinement. |
| Approach: | They propose a multi-agent framework that effectively Simulates Content Analysis via Large language model (LLM) ag Ents. |
| Outcome: | The proposed framework achieves human-approximated performance across various content analysis tasks. |
DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature (2024.findings-emnlp)
Copied to clipboard
Dawei Li, Shu Yang, Zhen Tan, Jae Baik, Sukwon Yun, Joseph Lee, Aaron Chacko, Bojian Hou, Duy Duong-Tran, Ying Ding, Huan Liu, Li Shen, Tianlong Chen
| Challenge: | Recent advances in large language models have achieved promising performances across various applications, but the challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains. |
| Approach: | They propose a dynamic co-augmentation framework for the refinement of large language models and knowledge graphs in the context of Alzheimer's Disease. |
| Outcome: | The proposed framework can be used to study Alzheimer's Disease (AD) using LLMs and KGs. |
Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction (2026.findings-acl)
Copied to clipboard
Xu Shen, Qi Zhang, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen
| Challenge: | Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors. |
| Approach: | They propose a metacognitive framework that enables step-level error detection and self-correction in Large Language Model based multi-agent systems (MAS) . |
| Outcome: | The proposed framework outperforms baselines on the Who When benchmark and delivers consistent gains on AgentErrorBench. |
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)
Copied to clipboard
Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Rajan Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, Tomas Pfister
| Challenge: | Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations. |
| Approach: | They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval. |
| Outcome: | The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model. |
CLEEK: A Chinese Long-text Corpus for Entity Linking (2020.lrec-1)
Copied to clipboard
| Challenge: | Entity linking is a fundamental task in natural language processing, says nigel kilgstrom . existing corpora for entity linking in china are lacking and deficient, he says . kilsmstrom: a new method for entity disambiguation can be developed for Chinese . |
| Approach: | They build a Chinese corpus of multi-domain long text for entity linking . they evaluate the difficulty of documents with respect to entity linking using a measure . |
| Outcome: | The proposed corpus is based on 100 documents from diverse domains and is publicly accessible. |
EQA-RM: A Generative Embodied Reward Model with Test-time Scaling (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing generic Reward Models are ill-equipped for dynamic and interactive domains. |
| Approach: | They propose a novel generative multimodal reward model specifically architected for EQA that provides interpretable, structured reward feedback. |
| Outcome: | The proposed model outperforms proprietary benchmarks, including Gemini-2.5-Flash, GPT-4o, Claude-3.5-Haiku, and open-sourced state-of-the-art models such as RoVRM and VisualPRM. |
Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidance (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained Language Models (PLMs) are advanced but data labels are noisy due to the complex annotation process. |
| Approach: | They propose a framework for fine-tuning PLMs using noisy labels that incorporates guidance from Large Language Models like ChatGPT. |
| Outcome: | Experiments on synthetic and real-world noisy datasets show that the proposed framework outperforms the state-of-the-art framework. |
ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Reward-guided search methods have shown potential in enhancing tool-using agents . however, there is a lack of reliable evaluation benchmarks for PRMs in tool-use settings . |
| Approach: | They propose a large-scale benchmark specifically designed to evaluate PRMs for tool-using agents. |
| Outcome: | The proposed benchmark shows that tool reward models perform better in tool-using environments. |
Active Learning for Abstractive Text Summarization via LLM-Determined Curriculum and Certainty Gain Maximization (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Abstractive text summarization (ATS) requires laborious data annotation and time-consuming model training. |
| Approach: | They propose a novel active learning framework that asks large language models to rate difficulty of instances and then uses certainty gain maximization to select instances with a distribution that aligns well with the overall distribution. |
| Outcome: | The proposed framework improves stability, effectiveness, and efficiency of abstractive text summarization backbones. |
Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to detect causal relationships in unstructured texts ignore trivial knowledge which may prejudice performance. |
| Approach: | They propose a pipeline to build a commonsense-aware pre-trained model which integrates reliable task-specific knowledge from commonsens graphs. |
| Outcome: | The proposed pipeline integrates reliable task-specific knowledge from commonsense graphs. |
TranSFormer: Slow-Fast Transformer for Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Prior work has focused on treating subwords as basic units in developing such systems. |
| Approach: | They propose a slow-fast two-stream learning model that uses a “slow” branch to deal with subword sequences and a "fast" branch to cope with longer character sequences. |
| Outcome: | The proposed model shows consistent BLEU improvements (larger than 1 BLUE point) on several machine translation benchmarks. |
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens (2026.findings-acl)
Copied to clipboard
Chengshuai Zhao, Zhen Tan, Pingchuan Ma, Dawei Li, Bohan Jiang, Yancheng Wang, Yingzhen Yang, Huan Liu
| Challenge: | Chain-of-Thought (CoT) prompting has been shown to be effective in eliciting structured reasoning from large language models (LLMs). |
| Approach: | They propose a data distribution lens to understand when and why CoT reasoning fails . they propose 'data-based' training that trains LLMs from scratch . |
| Outcome: | The proposed model enables models to generate reasoning trajectories that approximate those observed during training. |
Task-Aware Resolution Optimization for Visual Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing visual large language models pre-assume a fixed resolution for downstream tasks, leading to sub-optimal performance. |
| Approach: | They propose a formula to determine the optimal resolution for a given vision-language task . they then propose 'parameter-efficient' fine-tuning technique to extend the visual input resolution . |
| Outcome: | The proposed method is based on rigorous experiments on vision-language tasks. |
Contextualization Distillation from Large Language Model for Knowledge Graph Completion (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing knowledge graph completion models lack textual information, which limits their performance . a plug-in-and-play approach is needed to train small models in descriptive context . |
| Approach: | They propose a plug-in-and-play approach to knowledge graph completion that prompts LLMs to generate descriptive context. |
| Outcome: | The proposed method improves performance on Wikipedia articles and synset definitions. |
Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data. |
| Approach: | They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students. |
| Outcome: | Experiments show that QR-Distill is superior to traditional methods. |
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judge (2025.emnlp-main)
Copied to clipboard
Dawei Li, Bohan Jiang, Liangjie Huang, Alimohammad Beigi, Chengshuai Zhao, Zhen Tan, Amrita Bhattacharjee, Yuxuan Jiang, Canyu Chen, Tianhao Wu, Kai Shu, Lu Cheng, Huan Liu
| Challenge: | Recent advances in Large Language Models (LLMs) inspire the "LLM-as-a-judge" paradigm . traditional methods of assessment and evaluation fail in dynamic and open-ended scenarios . |
| Approach: | They propose a paradigm where LLMs are leveraged to perform scoring, ranking, or selection for machine learning evaluation scenarios. |
| Outcome: | The proposed model-based judgment and evaluation paradigms are based on large language models and are compared to the current model-driven evaluation paradigm. |
Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) demonstrate exceptional instruct-following ability to complete downstream tasks. |
| Approach: | They propose a black-box combinatorial optimization framework that iteratively improves lexical choices in prompts by a search strategy related to word influence. |
| Outcome: | The proposed framework recovers the model's ability to instruct-follow and solve downstream tasks even when the variations are imperceptible to humans. |
Glue pizza and eat rocks - Exploiting Vulnerabilities in Retrieval-Augmented Generative Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases. |
| Approach: | They propose to exploit openness of RAG models by injecting deceptive content into the retrieval database, intentionally changing the model’s behavior. |
| Outcome: | The proposed model can be exploited through crafted content uploads with access to the retriever. |
Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks (2025.acl-long)
Copied to clipboard
| Challenge: | Multi-agent LLMs are prone to adversarial attacks because of constraints such as limited token bandwidth and latency between message delivery. |
| Approach: | They propose a permutation-invariant adversarial attack that optimizes prompt distribution across latency and bandwidth constraints to bypass distributed safety mechanisms within the system. |
| Outcome: | The proposed method outperforms conventional attacks by up to 7 on multiple models. |
PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to generate long music are inefficient and lack of structured representation. |
| Approach: | They propose a hierarchical discrete representation of audio for long audio-domain music generation using residual vector quantization on different levels of features. |
| Outcome: | The proposed method achieves competitive performance in terms of reconstruction quality and token per second (TPS) the proposed method facilitates training a language model that can generate well-structured long-form music for up to 3 minutes. |
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates (2023.tacl-1)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) has evolved from flat to overlapped and discontinuous . NER is a text recognition task that recognizes mentions that represent entities in text . |
| Approach: | They propose a two-stage span-based framework to solve a unified NER task using two stages . they extract entity spans, classify over all entity span pairs and combine them to train two stages. |
| Outcome: | The proposed framework beats all the current competitive baselines on eight benchmark datasets, obtaining the best performance of unified NER. |
AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for multi-agent collaboration rely on static or graph-based topologies lacking flexibility and adaptability. |
| Approach: | They propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure. |
| Outcome: | The proposed method achieves superior performance while significantly reducing communication overhead. |
Joint Event Extraction with Hierarchical Policy Network (2020.coling-main)
Copied to clipboard
| Challenge: | Existing work on event extraction (EE) is pipelined or uses a joint structure but does not utilize information interactions among event triggers, event arguments, and argument roles. |
| Approach: | They propose to exploit role information of arguments in an event and devise a Hierarchical Policy Network to perform joint EE. |
| Outcome: | The proposed system outperforms existing methods and is more powerful for sentences with multiple events. |
Curriculum Learning based Hierarchical Scoring and Analysis Framework for Question Answering Task Evaluation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods rely on rule-based matching with shallow semantic understanding or adopt LLM-as-a-Judge approaches that incur high cost and latency while offering limited error interpretability. |
| Approach: | They propose a curriculum learning based hierarchical framework for QA task evaluation that supports quick scoring and fine-grained error analysis. |
| Outcome: | The proposed framework outperforms baseline methods on quick scoring and error analysis tasks while being 25 faster. |
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)
Copied to clipboard
Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao
| Challenge: | Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios. |
| Approach: | They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions. |
| Outcome: | The proposed framework improves generalization and realism of large language models under complex and irregular table conditions. |
Large Language Models for Data Annotation and Synthesis: A Survey (2024.emnlp-main)
Copied to clipboard
Zhen Tan, Dawei Li, Song Wang, Alimohammad Beigi, Bohan Jiang, Amrita Bhattacharjee, Mansooreh Karami, Jundong Li, Lu Cheng, Huan Liu
| Challenge: | Existing surveys focus on LLMs' specific utility for data annotation and synthesis. |
| Approach: | They propose to use large language models to generate annotations from raw data . they also propose to review learning strategies for models utilizing LLM-generated annotations . |
| Outcome: | The proposed models can be used to improve the efficacy of machine learning models by generating and labeling raw data with relevant information. |
UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets (2025.emnlp-main)
Copied to clipboard
Pengyu Wang, Shaojun Zhou, Chenkun Tan, Xinghao Wang, Wei Huang, Zhen Ye, Zhaowei Li, Botian Jiang, Dong Zhang, Xipeng Qiu
| Challenge: | Existing datasets address understanding and generation in isolation, limiting the performance of unified vision large language models. |
| Approach: | They propose a dataset that facilitates mutual enhancement between multimodal understanding and generation. |
| Outcome: | The proposed framework integrates diverse visual and textual inputs and outputs, enabling comprehensive cross-modal reasoning and precise text-to-image alignment. |
CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)
Copied to clipboard
Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen
| Challenge: | a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages. |
| Approach: | They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models. |
| Outcome: | The proposed benchmarks show that the current models perform worse than the human ceiling. |
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) lack robustness in knowledge-intensive tasks due to noisy or irrelevant retrieved data. |
| Approach: | They propose a multi-agent debate-based RAG framework that integrates external knowledge sources into large language models to improve their accuracy. |
| Outcome: | The proposed framework is unsupervised and leverages pretrained LLMs without fine-tuning, making it easily adaptable to various tasks. |
The Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been focused on single-agent, white-box environments, but multi-agend systems (MAS) have a critical blind spot: supply chain vulnerabilities. |
| Approach: | They propose a black-box auditing framework that leverages an Evolutionary Algorithm to autonomously expose hidden threats. |
| Outcome: | The proposed framework achieves superior detection rates (up to 100% in specific configurations) and robustness across diverse architectures. |